Average Metrics Analysis¶

This .ipynb runs the averageMetrics.py script, and generates multiple analysis plots and charts. 1) P/R per class, per transform, as a table for each model. 2) P/R difference per class, per transform as a table. 4) Per class, Per transform precision and recall averaged over every model (Box plot). 5) Per class, per model performance averaged over all transforms (Box plot). 6) Precision/Recall performance per class, per model, averaged based on the "categories" of transforms (Value/Spatial, sub-categories of each)

import os
import ast
import subprocess
from multiprocessing import Process, Queue
from multiprocessing import Pool
import glob
import json
import pandas as pd
from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval
from pycocotools.coco import COCO
import numpy as np
import time
import matplotlib.pyplot as plt
from IPython.display import display, HTML

%matplotlib inline
# Resize the ipynb width settings.
display(HTML("<style>.container { width:85% !important; }</style>"))

class ListTable(list):
    """ Overridden list class which takes a 2-dimensional list of 
        the form [[1,2,3],[4,5,6]], and renders an HTML Table in 
        IPython Notebook. """
    
    def _repr_html_(self):
        html = ["<table>"]
        for row in self:
            html.append("<tr>")
            
            for col in row:
                html.append("<td>{0}</td>".format(col))
            
            html.append("</tr>")
        html.append("</table>")
        return ''.join(html)
print('Imports successful!')

Imports successful!

dataDir='../data/inputs'
dataType='val2017'
annFile = '%s/annotations/%s_%s.json'%(dataDir,'instances',dataType)
annType = 'bbox'
cocoGt=COCO(annFile)
cats = cocoGt.loadCats(cocoGt.getCatIds())
nms=[cat['name'] for cat in cats]

transformNames = [
 'None',
 'gaussianblur_1',
 'gaussianblur_10',
 'gaussianblur_20',
 'superpixels_0p1',
 'superpixels_0p5',
 'superpixels_0p85',
 'colorspace_25',
 'colorspace_50',
 'averageblur_5_11',
 'medianblur_1',
 'sharpen_0',
 'sharpen_1',
 'sharpen_2',
 'addintensity_-80',
 'addintensity_80',
 'elementrandomintensity_1',
 'multiplyintensity_0p25',
 'multiplyintensity_2',
 'contrastnormalization_0',
 'contrastnormalization_1',
 'contrastnormalization_2',
 'elastic_1',
 'scaled_1p25',
 'scaled_0p75',
 'scaled_0p5',
 'scaled_(1p25, 1p0)',
 'scaled_(0p75, 1p0)',
 'scaled_(1p0, 1p25)',
 'scaled_(1p0, 0p75)',
 'translate_(0p1, 0p1)',
 'translate_(0p1, -0p1)',
 'translate_(-0p1, 0p1)',
 'translate_(-0p1, -0p1)',
 'translate_(0p1, 0)',
 'translate_(-0p1, 0)',
 'translate_(0, 0p1)',
 'translate_(0, -0p1)',
 'rotated_3',
 'rotated_5',
 'rotated_10',
 'rotated_45',
 'rotated_60',
 'rotated_90',
 'flipH',
 'flipV',
 'dropout',
 ]

# Build up the transform lists for 'category' based performance analysis.
valueTransforms = transformNames[:23]
spatialTransforms = transformNames[23:]
blurTransforms = [ 'gaussianblur_1',
 'gaussianblur_10',
 'gaussianblur_20',
 'averageblur_5_11',
 'medianblur_1']
regionTransforms = [ 'superpixels_0p1',
 'superpixels_0p5',
 'superpixels_0p85',
 'averageblur_5_11']
colorTransforms = ['colorspace_25',
 'colorspace_50',
 'multiplyintensity_0p25',
 'multiplyintensity_2',
 'contrastnormalization_0',
 'contrastnormalization_1',
 'contrastnormalization_2']
lightingTransforms = ['sharpen_0',
 'sharpen_1',
 'sharpen_2',
 'addintensity_-80',
 'addintensity_80',
 'elementrandomintensity_1']
scalingTransforms = [ 'scaled_1p25',
 'scaled_0p75',
 'scaled_0p5',
 'scaled_(1p25, 1p0)',
 'scaled_(0p75, 1p0)',
 'scaled_(1p0, 1p25)',
 'scaled_(1p0, 0p75)']
orientationTransforms = [ 'rotated_3',
 'rotated_5',
 'rotated_10',
 'rotated_45',
 'rotated_60',
 'rotated_90',
 'flipH',
 'flipV']
translationTransforms = ['translate_(0p1, 0p1)',
 'translate_(0p1, -0p1)',
 'translate_(-0p1, 0p1)',
 'translate_(-0p1, -0p1)',
 'translate_(0p1, 0)',
 'translate_(-0p1, 0)',
 'translate_(0, 0p1)',
 'translate_(0, -0p1)']
distortionTransforms = ['elastic_1',
 'dropout']
transformCategoryHeadersList = ['valueTransforms', 'spatialTransforms', 'blurTransforms', 'regionTransforms', 
                       'colorTransforms', 'lightingTransforms', 'scalingTransforms',
                       'orientationTransforms', 'translationTransforms', 
                       'distortionTransforms']
transformCategoryValuesList = [valueTransforms, spatialTransforms, blurTransforms, regionTransforms, colorTransforms,
                              lightingTransforms, scalingTransforms, orientationTransforms, translationTransforms, 
                              distortionTransforms]


modelNames = ['e2e_faster_rcnn_R-50-C4_2x',
'e2e_faster_rcnn_R-50-FPN_2x',
'e2e_faster_rcnn_R-101-FPN_2x',
'e2e_faster_rcnn_X-101-64x4d-FPN_2x',
'e2e_mask_rcnn_R-50-C4_2x',
'e2e_mask_rcnn_R-50-FPN_2x',
'e2e_mask_rcnn_R-101-FPN_2x',
'retinanet_R-50-FPN_2x',
'retinanet_R-101-FPN_2x',
'retinanet_X-101-64x4d-FPN_2x']

loading annotations into memory...
Done (t=0.68s)
creating index...
index created!

Read metrics for each model and transform, and parse them into pandas data frames.¶

metricsColumns = ['model','transform','class','precision','recall','accuracy','TP','FP','FN']
metricsList = []
metrics = pd.DataFrame([], columns=metricsColumns)
regenerate=False


def f(tup):
    print('%s,%s,%s running...'%(tup[1], tup[2], str(tup[0])))
    result = subprocess.check_output(args=["python", "averageMetrics.py", "-c", str(tup[0]), '-r',
                             'basic', tup[1], tup[2]])
    output = result.decode("utf-8")
    # Parse output into a python dict.
    p = re.compile('.+?precision')
    m = p.search(output)
    start = m.start()
    metricStr = output[start:].strip()
    metricObject = ast.literal_eval(metricStr)
    return [tup[1], tup[2], str(tup[0]), metricObject['precision']
                       ,metricObject['recall'],metricObject['accuracy'],metricObject['TP'],
                       metricObject['FP'], metricObject['FN']]

if regenerate:
    # Multiprocess method.
    classLabels = list(map(lambda item: item['id'], cats))
    argumentsList = []
    for model in modelNames:
        for transform in transformNames:
            for classLabel in classLabels:
                argumentsList.append([classLabel, model, transform])


    startTime = time.time()
    p = Pool(6)
    metricsList = p.map(f, argumentsList)
    endTime = time.time()
    print('Total time to run was %s seconds.'%(str(endTime-startTime)))

    # # Single process method.
    # classLabels = list(map(lambda item: item['id'], cats))
    # startTime = time.time()
    # for model in modelNames:
    #     for transform in transformNames:
    #         for i, classLabel in enumerate(classLabels):
    #             print('%s,%s,%s running...'%(model, transform, classLabel))
    #             result = subprocess.check_output(args=["python", "averageMetrics.py", "-c", str(classLabel), '-r',
    #                                      'basic', model, transform])
    #             output = result.decode("utf-8")
    #             # Parse output into a python dict.
    #             p = re.compile('.+?precision')
    #             m = p.search(output)
    #             start = m.start()
    #             metricStr = output[start:].strip()
    #             metricObject = ast.literal_eval(metricStr)
    #             metricsList.append([model, transform, classLabel, metricObject['precision']
    #                                ,metricObject['recall'],metricObject['accuracy'],metricObject['TP'],
    #                                metricObject['FP'], metricObject['FN']])

    # endTime = time.time()
    # print('Total time to run was %s seconds.'%(str(endTime-startTime)))

    # Build the pandas dataframe.
    metrics = pd.DataFrame(metricsList, columns=metricsColumns)
    # Save the pandas dataframe.
    metrics.to_csv('./metrics_dataframe.csv', index=True)

    #Total time to run was 30180.934909582138 seconds.

# Read the pandas dataframe.
metrics = pd.read_csv('./metrics_dataframe.csv', index_col='Unnamed: 0')
metrics.head()

Analysis plots¶

Plot of precision and recall over all models, classes, and transforms¶

This plot fully characterizes performance over all combinations of models, classes, and image data sets (transformed and 'None').

fig_size = [0,0]
fig_size[0] = 12
fig_size[1] = 6
plt.rcParams["figure.figsize"] = fig_size

precisionDF = metrics[['precision', 'recall']]
precisionDF.plot.hist(alpha=0.5)

<matplotlib.axes._subplots.AxesSubplot at 0x1121bd850>

Plots of precision and recall on the original images, per model.¶

These histograms show the initial precision and recall performance over all classes, and provide a way to compare initial performance based off of the histogram distributions. It should be noted that when viewing these plots, precision and recall are considered separately. Thus, a model that seems to have a histogram indicating that many classes have high precision may have correspondingly low recall for these classes. But, this kind of issue cannot be determined from the plots below.

# Set figure size
fig_size = [0,0]
fig_size[0] = 22
fig_size[1] = 10
plt.rcParams["figure.figsize"] = fig_size


f, axarr = plt.subplots(2, 5)
f.suptitle('Original Precision Histogram for Every Model', fontsize=16)
for i, model in enumerate(modelNames):
    axarr[int(i/5), i%5].hist(metrics[(metrics['model'] == model) & (metrics['transform'] == 'None')]['precision'])
    axarr[int(i/5), i%5].set_title(model)


f, axarr = plt.subplots(2, 5)
f.suptitle('Original Recall Histogram for Every Model', fontsize=16)
for i, model in enumerate(modelNames):
    axarr[int(i/5), i%5].hist(metrics[(metrics['model'] == model) & (metrics['transform'] == 'None')]['recall'])
    axarr[int(i/5), i%5].set_title(model)

Precision tables per class, per model, per transform.¶

These tables provide an absolute number for precision, given a particular model, transform, and class. The provide an absolute summary of performance, and can be further categorized into many further sub-metrics and plots along the dimensions of the table.

#pd.set_option('display.max_rows', 300)
#display(metrics)
for model in modelNames:
    # Create new table with columns as class (names) and rows as transform.
    table = ListTable()
    table.append(['transform'] + nms)
    modelDF = metrics[metrics['model'] == model]
    
    for transform in transformNames:
        # Get all precision metrics for the transform.
        modelTransformDF = modelDF[modelDF['transform'] == transform]
        precisionSeries = modelTransformDF['precision']
        precisionSeries = list(map(lambda item: '%.3f'%(item), precisionSeries.tolist()))
        table.append([transform] + precisionSeries)
    
    # Display the precision table for the model.
    print('Precision for model %s'%model)
    display(table)

Precision for model e2e_faster_rcnn_R-50-C4_2x

Precision for model e2e_faster_rcnn_R-50-FPN_2x

Precision for model e2e_faster_rcnn_R-101-FPN_2x

Precision for model e2e_faster_rcnn_X-101-64x4d-FPN_2x

Precision for model e2e_mask_rcnn_R-50-C4_2x

Precision for model e2e_mask_rcnn_R-50-FPN_2x

Precision for model e2e_mask_rcnn_R-101-FPN_2x

Precision for model retinanet_R-50-FPN_2x

Precision for model retinanet_R-101-FPN_2x

Precision for model retinanet_X-101-64x4d-FPN_2x

Recall tables per class, per model, per transform.¶

These tables provide an absolute number for recall, given a particular model, transform, and class. The provide an absolute summary of performance, and can be further categorized into many further sub-metrics and plots along the dimensions of the table.

#pd.set_option('display.max_rows', 300)
#display(metrics)
for model in modelNames:
    # Create new table with columns as class (names) and rows as transform.
    table = ListTable()
    table.append(['transform'] + nms)
    modelDF = metrics[metrics['model'] == model]
    
    for transform in transformNames:
        # Get all precision metrics for the transform.
        modelTransformDF = modelDF[modelDF['transform'] == transform]
        precisionSeries = modelTransformDF['recall']
        precisionSeries = list(map(lambda item: '%.3f'%(item), precisionSeries.tolist()))
        table.append([transform] + precisionSeries)
    
    # Display the recall table for the model.
    print('Recall for model %s'%model)
    display(table)

Recall for model e2e_faster_rcnn_R-50-C4_2x

Recall for model e2e_faster_rcnn_R-50-FPN_2x

Recall for model e2e_faster_rcnn_R-101-FPN_2x

Recall for model e2e_faster_rcnn_X-101-64x4d-FPN_2x

Recall for model e2e_mask_rcnn_R-50-C4_2x

Recall for model e2e_mask_rcnn_R-50-FPN_2x

Recall for model e2e_mask_rcnn_R-101-FPN_2x

Recall for model retinanet_R-50-FPN_2x

Recall for model retinanet_R-101-FPN_2x

Recall for model retinanet_X-101-64x4d-FPN_2x

Precision Difference tables per class, per model, per transform.¶

Tables showing the difference between the original image set ('None' transform), and the transformed image set. A positive value represents an increase in performance, while a negative value represents a decrease in performance. These tables should give an idea of how the performance of a specific model is affected given a specific transform, and a specific class. It can be used to determine how much a specific transform affects precision over all classes, and to how much the recall of a model is increased or decreased given the transform.

for model in modelNames:
    # Create new table with columns as class (names) and rows as transform.
    table = ListTable()
    table.append(['transform'] + nms)
    modelDF = metrics[metrics['model'] == model]
    
    originalPrecisionSeries = metrics[(metrics['model'] == model)&(metrics['transform'] == 'None')]['precision']
    for transform in transformNames:
        # Get all precision metrics for the transform.
        modelTransformDF = modelDF[modelDF['transform'] == transform]
        precisionSeries = modelTransformDF['precision']
        #import pdb; pdb.set_trace()
        precisionSeries = np.array(precisionSeries.tolist()) - np.array(originalPrecisionSeries.tolist())
        precisionSeries = list(map(lambda item: '%.3f'%(item), precisionSeries))
        table.append([transform] + precisionSeries)
    
    # Display the precision table for the model.
    print('Precision for model %s'%model)
    display(table)

Precision for model e2e_faster_rcnn_R-50-C4_2x

Precision for model e2e_faster_rcnn_R-50-FPN_2x

Precision for model e2e_faster_rcnn_R-101-FPN_2x

Precision for model e2e_faster_rcnn_X-101-64x4d-FPN_2x

Precision for model e2e_mask_rcnn_R-50-C4_2x

Precision for model e2e_mask_rcnn_R-50-FPN_2x

Precision for model e2e_mask_rcnn_R-101-FPN_2x

Precision for model retinanet_R-50-FPN_2x

Precision for model retinanet_R-101-FPN_2x

Precision for model retinanet_X-101-64x4d-FPN_2x

Recall Difference tables per class, per model, per transform.¶

Tables showing the difference between the original image set ('None' transform), and the transformed image set. These tables should give an idea of how the performance of a specific model is affected given a specific transform, and a specific class. It can be used to determine how much a specific transform affects performance over all classes, and to how much the recall of a model is increased or decreased given the transform.

for model in modelNames:
    # Create new table with columns as class (names) and rows as transform.
    table = ListTable()
    table.append(['transform'] + nms)
    modelDF = metrics[metrics['model'] == model]
    
    originalPrecisionSeries = metrics[(metrics['model'] == model)&(metrics['transform'] == 'None')]['recall']
    for transform in transformNames:
        # Get all precision metrics for the transform.
        modelTransformDF = modelDF[modelDF['transform'] == transform]
        precisionSeries = modelTransformDF['recall']
        #import pdb; pdb.set_trace()
        precisionSeries = np.array(precisionSeries.tolist()) - np.array(originalPrecisionSeries.tolist())
        precisionSeries = list(map(lambda item: '%.3f'%(item), precisionSeries))
        table.append([transform] + precisionSeries)
    
    # Display the precision table for the model.
    print('Recall for model %s'%model)
    display(table)

Recall for model e2e_faster_rcnn_R-50-C4_2x

Recall for model e2e_faster_rcnn_R-50-FPN_2x

Recall for model e2e_faster_rcnn_R-101-FPN_2x

Recall for model e2e_faster_rcnn_X-101-64x4d-FPN_2x

Recall for model e2e_mask_rcnn_R-50-C4_2x

Recall for model e2e_mask_rcnn_R-50-FPN_2x

Recall for model e2e_mask_rcnn_R-101-FPN_2x

Recall for model retinanet_R-50-FPN_2x

Recall for model retinanet_R-101-FPN_2x

Recall for model retinanet_X-101-64x4d-FPN_2x

Precision averaged over every model on a Per transform, Per class basis.¶

These box plots should show how much each transform affects recall on a specific class, regardless of what model is used. Note: It takes about 3 Minutes to generate all of these plots.

# Set figure size
fig_size = [0,0]
fig_size[0] = 25
fig_size[1] = 15
plt.rcParams["figure.figsize"] = fig_size

classLabels = list(map(lambda item: item['id'], cats))
for transform in transformNames:
    # Create figure and get plot axis.
    f, axarr = plt.subplots(1, 1)
    ax1 = axarr

    # Generate the 'data' set for the boxplot.
    data = []
    for classLabel in classLabels:
        classPrecisionList = metrics[(metrics['transform'] == transform)&(metrics['class'] == classLabel)]
        data.append(classPrecisionList['precision'].tolist())
        

    # Generate the boxplot from the data set.
    data = np.array(data)
    data = data.T
    bp = ax1.boxplot(data)

    # Add a horizontal grid to the plot, but make it very light in color
    # so we can use it for reading data values but not be distracting
    ax1.yaxis.grid(True, linestyle='-', which='major', color='lightgrey', alpha=0.5)
    # Hide these grid behind plot objects
    ax1.set_axisbelow(True)
    ax1.set_xlabel('Class')
    ax1.set_ylabel('Precision')
    ax1.set_title(transform)
    ax1.set_xticklabels(nms,
                    rotation=90, fontsize=10)
    display(f)

/anaconda2/lib/python2.7/site-packages/matplotlib/pyplot.py:537: RuntimeWarning: More than 20 figures have been opened. Figures created through the pyplot interface (`matplotlib.pyplot.figure`) are retained until explicitly closed and may consume too much memory. (To control this warning, see the rcParam `figure.max_open_warning`).
  max_open_warning, RuntimeWarning)

Recall averaged over every model on a Per transform, Per class basis.¶

These box plots should show how much each transform affects recall on a specific class, regardless of what model is used. Note: It takes about 3 Minutes to generate all of these plots.

# Set figure size
fig_size = [0,0]
fig_size[0] = 25
fig_size[1] = 15
plt.rcParams["figure.figsize"] = fig_size

classLabels = list(map(lambda item: item['id'], cats))
for transform in transformNames:
    # Create figure and get plot axis.
    f, axarr = plt.subplots(1, 1)
    ax1 = axarr

    # Generate the 'data' set for the boxplot.
    data = []
    for classLabel in classLabels:
        classPrecisionList = metrics[(metrics['transform'] == transform)&(metrics['class'] == classLabel)]
        data.append(classPrecisionList['recall'].tolist())
        

    # Generate the boxplot from the data set.
    data = np.array(data)
    data = data.T
    bp = ax1.boxplot(data)

    # Add a horizontal grid to the plot, but make it very light in color
    # so we can use it for reading data values but not be distracting
    ax1.yaxis.grid(True, linestyle='-', which='major', color='lightgrey', alpha=0.5)
    # Hide these grid behind plot objects
    ax1.set_axisbelow(True)
    ax1.set_xlabel('Class')
    ax1.set_ylabel('Recall')
    ax1.set_title(transform)
    ax1.set_xticklabels(nms,
                    rotation=90, fontsize=10)
    display(f)

/home/dcompgriff/anaconda2/envs/py36/lib/python3.6/site-packages/matplotlib/pyplot.py:528: RuntimeWarning: More than 20 figures have been opened. Figures created through the pyplot interface (`matplotlib.pyplot.figure`) are retained until explicitly closed and may consume too much memory. (To control this warning, see the rcParam `figure.max_open_warning`).
  max_open_warning, RuntimeWarning)

Precision averaged over transforms and classes on the original image set.¶

This should give some insight into what models have better recall, no matter the class, and can be used to compare agains the metrics reported in papers.

# Set figure size
fig_size = [0,0]
fig_size[0] = 15
fig_size[1] = 8
plt.rcParams["figure.figsize"] = fig_size

classLabels = list(map(lambda item: item['id'], cats))
data = []
# Create figure and get plot axis.
f, axarr = plt.subplots(1, 1)
ax1 = axarr
for model in modelNames:
    # Generate the 'data' set for the boxplot.
    modelPrecisionList = metrics[(metrics['model'] == model)&(metrics['transform']=='None')]
    data.append(modelPrecisionList['precision'].tolist())
    
# Generate the boxplot from the data set.
data = np.array(data)
data = data.T
bp = ax1.boxplot(data, showmeans=True)

# Add a horizontal grid to the plot, but make it very light in color
# so we can use it for reading data values but not be distracting
ax1.yaxis.grid(True, linestyle='-', which='major', color='lightgrey', alpha=0.5)
# Hide these grid behind plot objects
ax1.set_axisbelow(True)
ax1.set_xlabel('Model')
ax1.set_ylabel('Precision')
ax1.set_title('Per Model Precision Box Plots on Original Images')
ax1.set_xticklabels(modelNames,rotation=90, fontsize=10)

[Text(0,0,'e2e_faster_rcnn_R-50-C4_2x'),
 Text(0,0,'e2e_faster_rcnn_R-50-FPN_2x'),
 Text(0,0,'e2e_faster_rcnn_R-101-FPN_2x'),
 Text(0,0,'e2e_faster_rcnn_X-101-64x4d-FPN_2x'),
 Text(0,0,'e2e_mask_rcnn_R-50-C4_2x'),
 Text(0,0,'e2e_mask_rcnn_R-50-FPN_2x'),
 Text(0,0,'e2e_mask_rcnn_R-101-FPN_2x'),
 Text(0,0,'retinanet_R-50-FPN_2x'),
 Text(0,0,'retinanet_R-101-FPN_2x'),
 Text(0,0,'retinanet_X-101-64x4d-FPN_2x')]

Recall averaged over transforms and classes on the original image set.¶

This should give some insight into what models have better recall, no matter the class, and can be used to compare agains the metrics reported in papers.

# Set figure size
fig_size = [0,0]
fig_size[0] = 15
fig_size[1] = 8
plt.rcParams["figure.figsize"] = fig_size

classLabels = list(map(lambda item: item['id'], cats))
data = []
# Create figure and get plot axis.
f, axarr = plt.subplots(1, 1)
ax1 = axarr
for model in modelNames:
    # Generate the 'data' set for the boxplot.
    modelPrecisionList = metrics[(metrics['model'] == model)&(metrics['transform']=='None')]
    data.append(modelPrecisionList['recall'].tolist())
    
# Generate the boxplot from the data set.
data = np.array(data)
data = data.T
bp = ax1.boxplot(data, showmeans=True)

# Add a horizontal grid to the plot, but make it very light in color
# so we can use it for reading data values but not be distracting
ax1.yaxis.grid(True, linestyle='-', which='major', color='lightgrey', alpha=0.5)
# Hide these grid behind plot objects
ax1.set_axisbelow(True)
ax1.set_xlabel('Model')
ax1.set_ylabel('Recall')
ax1.set_title('Per Model Recall Box Plots on Original Images')
ax1.set_xticklabels(modelNames,rotation=90, fontsize=10)

[Text(0,0,'e2e_faster_rcnn_R-50-C4_2x'),
 Text(0,0,'e2e_faster_rcnn_R-50-FPN_2x'),
 Text(0,0,'e2e_faster_rcnn_R-101-FPN_2x'),
 Text(0,0,'e2e_faster_rcnn_X-101-64x4d-FPN_2x'),
 Text(0,0,'e2e_mask_rcnn_R-50-C4_2x'),
 Text(0,0,'e2e_mask_rcnn_R-50-FPN_2x'),
 Text(0,0,'e2e_mask_rcnn_R-101-FPN_2x'),
 Text(0,0,'retinanet_R-50-FPN_2x'),
 Text(0,0,'retinanet_R-101-FPN_2x'),
 Text(0,0,'retinanet_X-101-64x4d-FPN_2x')]

Precision averaged over transforms and classes on a Per model basis.¶

This should give some insight into what models have better recall, no matter the class, and no matter the image variation.

# Set figure size
fig_size = [0,0]
fig_size[0] = 15
fig_size[1] = 8
plt.rcParams["figure.figsize"] = fig_size

classLabels = list(map(lambda item: item['id'], cats))
data = []
# Create figure and get plot axis.
f, axarr = plt.subplots(1, 1)
ax1 = axarr
for model in modelNames:
    # Generate the 'data' set for the boxplot.
    modelPrecisionList = metrics[metrics['model'] == model]
    data.append(modelPrecisionList['precision'].tolist())
    
# Generate the boxplot from the data set.
data = np.array(data)
data = data.T
bp = ax1.boxplot(data, showmeans=True)

# Add a horizontal grid to the plot, but make it very light in color
# so we can use it for reading data values but not be distracting
ax1.yaxis.grid(True, linestyle='-', which='major', color='lightgrey', alpha=0.5)
# Hide these grid behind plot objects
ax1.set_axisbelow(True)
ax1.set_xlabel('Model')
ax1.set_ylabel('Precision')
ax1.set_title('Per Model Precision Box Plots')
ax1.set_xticklabels(modelNames,rotation=90, fontsize=10)

[Text(0,0,'e2e_faster_rcnn_R-50-C4_2x'),
 Text(0,0,'e2e_faster_rcnn_R-50-FPN_2x'),
 Text(0,0,'e2e_faster_rcnn_R-101-FPN_2x'),
 Text(0,0,'e2e_faster_rcnn_X-101-64x4d-FPN_2x'),
 Text(0,0,'e2e_mask_rcnn_R-50-C4_2x'),
 Text(0,0,'e2e_mask_rcnn_R-50-FPN_2x'),
 Text(0,0,'e2e_mask_rcnn_R-101-FPN_2x'),
 Text(0,0,'retinanet_R-50-FPN_2x'),
 Text(0,0,'retinanet_R-101-FPN_2x'),
 Text(0,0,'retinanet_X-101-64x4d-FPN_2x')]

Recall averaged over transforms and classes on a Per model basis.¶

This should give some insight into what models have better precision, no matter the class, and no matter the image variation.

# Set figure size
fig_size = [0,0]
fig_size[0] = 15
fig_size[1] = 8
plt.rcParams["figure.figsize"] = fig_size

classLabels = list(map(lambda item: item['id'], cats))
data = []
# Create figure and get plot axis.
f, axarr = plt.subplots(1, 1)
ax1 = axarr
for model in modelNames:
    # Generate the 'data' set for the boxplot.
    modelPrecisionList = metrics[metrics['model'] == model]
    data.append(modelPrecisionList['recall'].tolist())
    
# Generate the boxplot from the data set.
data = np.array(data)
data = data.T
bp = ax1.boxplot(data, showmeans=True)

# Add a horizontal grid to the plot, but make it very light in color
# so we can use it for reading data values but not be distracting
ax1.yaxis.grid(True, linestyle='-', which='major', color='lightgrey', alpha=0.5)
# Hide these grid behind plot objects
ax1.set_axisbelow(True)
ax1.set_xlabel('Model')
ax1.set_ylabel('Recall')
ax1.set_title('Per Model Recall Box Plots')
ax1.set_xticklabels(modelNames,rotation=90, fontsize=10)

[Text(0,0,'e2e_faster_rcnn_R-50-C4_2x'),
 Text(0,0,'e2e_faster_rcnn_R-50-FPN_2x'),
 Text(0,0,'e2e_faster_rcnn_R-101-FPN_2x'),
 Text(0,0,'e2e_faster_rcnn_X-101-64x4d-FPN_2x'),
 Text(0,0,'e2e_mask_rcnn_R-50-C4_2x'),
 Text(0,0,'e2e_mask_rcnn_R-50-FPN_2x'),
 Text(0,0,'e2e_mask_rcnn_R-101-FPN_2x'),
 Text(0,0,'retinanet_R-50-FPN_2x'),
 Text(0,0,'retinanet_R-101-FPN_2x'),
 Text(0,0,'retinanet_X-101-64x4d-FPN_2x')]

F1 averaged over transforms and classes on a Per model basis.¶

This should give some insight into what models have better precision, no matter the class, and no matter the image variation.

# Set figure size
fig_size = [0,0]
fig_size[0] = 15
fig_size[1] = 8
plt.rcParams["figure.figsize"] = fig_size

classLabels = list(map(lambda item: item['id'], cats))
data = []
# Create figure and get plot axis.
f, axarr = plt.subplots(1, 1)
ax1 = axarr
for model in modelNames:
    # Generate the 'data' set for the boxplot.
    modelPrecisionList = metrics[metrics['model'] == model]['precision'].tolist()
    modelRecallList = metrics[metrics['model'] == model]['recall'].tolist()
    modelF1List = []
    for i in range(len(modelPrecisionList)):
        try:
            f1 = (2*modelPrecisionList[i]*modelRecallList[i]) / (modelPrecisionList[i]+modelRecallList[i])
        except:
            f1 = 0
        
        modelF1List.append(modelPrecisionList[i]*modelRecallList[i])
    data.append(modelF1List)
    
# Generate the boxplot from the data set.
data = np.array(data)
data = data.T
bp = ax1.boxplot(data, showmeans=True)

# Add a horizontal grid to the plot, but make it very light in color
# so we can use it for reading data values but not be distracting
ax1.yaxis.grid(True, linestyle='-', which='major', color='lightgrey', alpha=0.5)
# Hide these grid behind plot objects
ax1.set_axisbelow(True)
ax1.set_xlabel('Model')
ax1.set_ylabel('F1')
ax1.set_title('Per Model F1 Box Plots')
ax1.set_xticklabels(modelNames,rotation=90, fontsize=10)

[Text(0,0,'e2e_faster_rcnn_R-50-C4_2x'),
 Text(0,0,'e2e_faster_rcnn_R-50-FPN_2x'),
 Text(0,0,'e2e_faster_rcnn_R-101-FPN_2x'),
 Text(0,0,'e2e_faster_rcnn_X-101-64x4d-FPN_2x'),
 Text(0,0,'e2e_mask_rcnn_R-50-C4_2x'),
 Text(0,0,'e2e_mask_rcnn_R-50-FPN_2x'),
 Text(0,0,'e2e_mask_rcnn_R-101-FPN_2x'),
 Text(0,0,'retinanet_R-50-FPN_2x'),
 Text(0,0,'retinanet_R-101-FPN_2x'),
 Text(0,0,'retinanet_X-101-64x4d-FPN_2x')]

Precision performance differences per model, averaged based on the "categories" of transforms (Value/Spatial, sub-categories of each) over all classes¶

These plots should provide some insight into the sensitivity of a given model and class to a specific kind of image transform. The two high level categories are value and spatial. The sub-categories of value based transforms are blur based, region based, color based, and lighting based. The sub-categories of spatial based transforms are scaling based, orientation based, translation based, and distortion based.

# Set figure size
fig_size = [0,0]
fig_size[0] = 15
fig_size[1] = 8
plt.rcParams["figure.figsize"] = fig_size

classLabels = list(map(lambda item: item['id'], cats))
for model in modelNames:
    data = []
    f, axarr = plt.subplots(1, 1)
    ax1 = axarr
    categoryPrecisionList = []
    originalPrecisionList = metrics[(metrics['transform'] == 'None')&(metrics['model'] == model)]['precision'].tolist()
    for i, category in enumerate(transformCategoryHeadersList):
        for transform in transformCategoryValuesList[i]:
            # Generate the precision differences on a category by category basis.
            transformPrecisionList = metrics[(metrics['transform'] == transform)&(metrics['model'] == model)]['precision'].tolist()
            diffPrecisionList = np.array(transformPrecisionList) - np.array(originalPrecisionList)
            categoryPrecisionList.extend(diffPrecisionList)
        # Append the set of all precision differences for the set of transforms in the category as a 
        # single box withing the box plot.
        data.append(np.array(categoryPrecisionList).mean())

    # Generate the boxplot from the data set.
    data = np.array(data)
    #data = data.T
    #means = data.mean(axis=0)
    #bp = ax1.boxplot(data, showmeans=True)
    ind = np.arange(data.shape[0])  # the x locations for the groups
    barp = ax1.bar(ind, data)

    # Add a horizontal grid to the plot, but make it very light in color
    # so we can use it for reading data values but not be distracting
    ax1.yaxis.grid(True, linestyle='-', which='major', color='lightgrey', alpha=0.5)
    # Hide these grid behind plot objects
    ax1.set_axisbelow(True)
    ax1.set_xlabel('Model')
    ax1.set_ylabel('Average Precision Difference.')
    ax1.set_title(model)
    ax1.set_xticks(ind)
    ax1.set_xticklabels(transformCategoryHeadersList,rotation=90, fontsize=10)

Recall performance differences per model, averaged based on the "categories" of transforms (Value/Spatial, sub-categories of each) over all classes¶

These plots should provide some insight into the sensitivity of a given model and class to a specific kind of image transform. The two high level categories are value and spatial. The sub-categories of value based transforms are blur based, region based, color based, and lighting based. The sub-categories of spatial based transforms are scaling based, orientation based, translation based, and distortion based.

# Set figure size
fig_size = [0,0]
fig_size[0] = 15
fig_size[1] = 8
plt.rcParams["figure.figsize"] = fig_size

classLabels = list(map(lambda item: item['id'], cats))
for model in modelNames:
    data = []
    f, axarr = plt.subplots(1, 1)
    ax1 = axarr
    categoryPrecisionList = []
    originalPrecisionList = metrics[(metrics['transform'] == 'None')&(metrics['model'] == model)]['recall'].tolist()
    for i, category in enumerate(transformCategoryHeadersList):
        for transform in transformCategoryValuesList[i]:
            # Generate the precision differences on a category by category basis.
            transformPrecisionList = metrics[(metrics['transform'] == transform)&(metrics['model'] == model)]['recall'].tolist()
            diffPrecisionList = np.array(transformPrecisionList) - np.array(originalPrecisionList)
            categoryPrecisionList.extend(diffPrecisionList)
        # Append the set of all precision differences for the set of transforms in the category as a 
        # single box withing the box plot.
        data.append(np.array(categoryPrecisionList).mean())

    # Generate the boxplot from the data set.
    data = np.array(data)
    #data = data.T
    #means = data.mean(axis=0)
    #bp = ax1.boxplot(data, showmeans=True)
    ind = np.arange(data.shape[0])  # the x locations for the groups
    barp = ax1.bar(ind, data)

    # Add a horizontal grid to the plot, but make it very light in color
    # so we can use it for reading data values but not be distracting
    ax1.yaxis.grid(True, linestyle='-', which='major', color='lightgrey', alpha=0.5)
    # Hide these grid behind plot objects
    ax1.set_axisbelow(True)
    ax1.set_xlabel('Model')
    ax1.set_ylabel('Average Recall Difference.')
    ax1.set_title(model)
    ax1.set_xticks(ind)
    ax1.set_xticklabels(transformCategoryHeadersList,rotation=90, fontsize=10)

	model	transform	class	precision	recall	accuracy	TP	FP	FN
0	e2e_faster_rcnn_R-50-C4_2x	None	1	0.694159	0.273512	0.244097	3009.731163	1326.064786	7994.268837
1	e2e_faster_rcnn_R-50-C4_2x	None	2	0.524687	0.156833	0.137323	49.559314	44.895615	266.440686
2	e2e_faster_rcnn_R-50-C4_2x	None	3	0.414337	0.120997	0.103325	233.765708	330.426081	1698.234292
3	e2e_faster_rcnn_R-50-C4_2x	None	4	0.719739	0.247889	0.226068	91.966830	35.811194	279.033170
4	e2e_faster_rcnn_R-50-C4_2x	None	5	0.779220	0.573851	0.493597	82.060714	23.250596	60.939286

transform	person	bicycle	car	motorcycle	airplane	bus	train	truck	boat	traffic light	fire hydrant	stop sign	parking meter	bench	bird	cat	dog	horse	sheep	cow	elephant	bear	zebra	giraffe	backpack	umbrella	handbag	tie	suitcase	frisbee	skis	snowboard	sports ball	kite	baseball bat	baseball glove	skateboard	surfboard	tennis racket	bottle	wine glass	cup	fork	knife	spoon	bowl	banana	apple	sandwich	orange	broccoli	carrot	hot dog	pizza	donut	cake	chair	couch	potted plant	bed	dining table	toilet	tv	laptop	mouse	remote	keyboard	cell phone	microwave	oven	toaster	sink	refrigerator	book	clock	vase	scissors	teddy bear	hair drier	toothbrush
None	0.694	0.525	0.414	0.720	0.779	0.745	0.852	0.486	0.531	0.272	0.723	0.596	0.689	0.418	0.492	0.655	0.624	0.751	0.649	0.605	0.867	0.816	0.872	0.858	0.140	0.585	0.097	0.040	0.656	0.109	0.306	0.107	0.066	0.579	0.247	0.058	0.315	0.307	0.392	0.266	0.353	0.298	0.422	0.226	0.228	0.390	0.588	0.428	0.540	0.428	0.529	0.305	0.566	0.550	0.626	0.438	0.382	0.628	0.395	0.754	0.466	0.744	0.634	0.642	0.095	0.141	0.464	0.157	0.466	0.607	0.229	0.443	0.795	0.324	0.387	0.312	0.562	0.718	0.000	0.230
gaussianblur_1	0.714	0.528	0.451	0.770	0.749	0.719	0.812	0.536	0.546	0.325	0.740	0.706	0.600	0.269	0.545	0.676	0.522	0.704	0.542	0.598	0.849	0.750	0.925	0.875	0.110	0.529	0.189	0.091	0.655	0.068	0.219	0.000	0.067	0.579	0.000	0.000	0.396	0.479	0.478	0.322	0.509	0.253	0.414	0.216	0.000	0.463	0.644	0.313	0.284	0.553	0.549	0.332	0.584	0.545	0.592	0.378	0.382	0.731	0.308	0.826	0.527	0.812	0.642	0.710	0.175	0.114	0.528	0.139	0.449	0.714	0.000	0.360	0.807	0.406	0.484	0.312	0.600	0.817	0.000	0.261
gaussianblur_10	0.728	0.000	0.417	0.000	0.000	0.700	0.487	0.000	0.000	0.500	0.667	0.750	0.333	0.000	1.000	0.223	0.208	0.667	0.000	0.500	0.778	0.000	0.000	1.000	0.000	0.182	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.103	0.115	0.100	0.000	0.000	0.000	0.417	0.812	0.120	0.000	0.238	1.000	0.500	0.800	0.611	0.214	0.417	0.250	0.000	0.000	1.000	0.462	1.000	0.270	0.714	0.125	0.000	0.000	0.000	0.250	0.000	0.000	0.000	0.500	0.000	0.000	0.000	0.000	0.000	0.000	1.000
gaussianblur_20	0.516	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	1.000	0.043	0.000	0.167	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.071	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000
superpixels_0p1	0.670	0.803	0.261	0.696	0.783	0.750	0.638	0.300	0.138	0.056	0.315	0.641	0.152	0.294	0.443	0.663	0.424	0.838	0.479	0.325	0.723	0.650	0.993	1.000	0.000	0.384	0.000	0.000	0.449	0.214	0.167	0.000	0.120	0.321	0.000	0.000	0.154	1.000	0.346	0.230	0.386	0.237	0.000	0.200	0.000	0.379	0.790	0.142	0.578	0.574	0.354	0.289	0.545	0.587	0.278	0.149	0.313	1.000	0.315	0.889	0.490	0.938	0.349	0.802	0.000	0.000	0.333	0.170	0.333	0.655	0.000	0.324	0.450	0.384	0.554	0.324	0.000	0.587	0.000	0.000
superpixels_0p5	0.607	0.000	0.170	0.636	0.729	0.767	0.377	0.253	0.046	0.016	0.217	0.429	0.099	0.228	0.342	0.625	0.248	0.429	0.353	0.122	0.818	1.000	0.595	1.000	0.000	0.169	0.000	0.000	0.065	0.000	0.000	0.000	0.000	0.290	0.000	0.000	0.057	0.000	0.000	0.118	0.000	0.181	0.000	0.310	0.000	0.400	0.600	0.100	0.000	0.273	0.328	0.410	0.000	0.721	0.216	0.058	0.132	1.000	0.033	0.000	0.295	0.895	0.282	0.848	0.000	0.000	0.236	0.000	0.429	0.294	0.000	0.200	0.452	0.750	0.696	0.078	0.000	0.354	0.000	0.000
superpixels_0p85	0.512	0.000	0.111	1.000	0.136	0.000	0.500	0.143	0.018	0.004	0.108	0.326	0.000	0.000	0.270	1.000	0.000	1.000	0.000	0.000	0.000	1.000	1.000	0.000	0.000	0.100	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.143	0.000	0.000	0.000	0.000	0.400	0.043	0.200	0.141	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.400	0.400	0.333	0.000	0.000	0.000	0.047	0.000	0.000	0.090	0.000	0.000	0.000	0.225	0.000	0.000	0.000	0.000	0.000	0.000	1.000	0.000	0.000	0.833	0.000	0.000	0.000	0.000	0.400	0.000	0.000
colorspace_25	0.730	0.437	0.476	0.750	0.770	0.753	0.884	0.494	0.636	0.241	0.682	0.849	0.639	0.261	0.437	0.591	0.531	0.726	0.537	0.497	0.884	0.748	0.897	0.867	0.155	0.504	0.145	0.000	0.589	0.037	0.215	0.000	0.034	0.498	0.000	0.000	0.320	0.530	0.457	0.274	0.572	0.234	0.433	0.181	0.050	0.358	0.430	0.238	0.571	0.553	0.263	0.000	1.000	0.599	0.656	0.276	0.362	0.651	0.274	0.800	0.517	0.871	0.578	0.772	0.125	0.138	0.396	0.140	0.427	0.762	0.000	0.405	0.804	0.367	0.487	0.271	0.800	0.750	0.000	0.240
colorspace_50	0.743	0.451	0.449	0.763	0.798	0.743	0.841	0.471	0.568	0.222	0.674	0.781	0.724	0.218	0.453	0.622	0.507	0.684	0.531	0.502	0.874	0.645	0.920	0.866	0.178	0.466	0.131	0.062	0.572	0.048	0.241	0.000	0.047	0.546	0.000	0.000	0.309	0.602	0.386	0.263	0.529	0.210	0.438	0.262	0.123	0.395	0.645	0.414	0.000	1.000	0.331	0.000	1.000	0.606	0.832	0.211	0.349	0.740	0.214	0.786	0.564	0.736	0.584	0.697	0.119	0.000	0.431	0.122	0.692	0.856	0.000	0.434	0.710	0.374	0.513	0.319	0.667	0.676	0.000	0.000
averageblur_5_11	0.731	0.462	0.466	0.834	0.778	0.768	0.770	0.651	0.520	0.311	0.728	0.673	0.475	0.294	0.415	0.457	0.571	0.671	0.414	0.520	0.795	0.755	0.937	0.904	0.055	0.550	0.224	0.074	0.594	0.136	0.304	0.000	0.080	0.542	0.000	0.000	0.434	0.606	0.386	0.395	0.432	0.200	0.468	0.255	0.168	0.454	0.658	0.222	0.478	0.488	0.486	0.338	0.693	0.485	0.725	0.450	0.339	0.854	0.300	0.923	0.513	0.834	0.558	0.700	0.222	0.000	0.475	0.236	0.353	0.752	0.000	0.529	0.846	0.414	0.664	0.289	0.333	0.843	0.000	0.353
medianblur_1	0.699	0.685	0.465	0.845	0.721	0.776	0.702	0.594	0.527	0.223	0.814	0.718	0.632	0.442	0.353	0.611	0.441	0.687	0.479	0.528	0.777	0.755	0.931	0.885	0.041	0.508	0.130	0.099	0.507	0.082	0.231	0.000	0.090	0.428	0.000	0.000	0.422	0.557	0.435	0.368	0.449	0.235	0.491	0.240	0.000	0.457	0.591	0.221	0.610	0.518	0.558	0.285	0.723	0.491	0.538	0.412	0.362	0.768	0.331	0.877	0.557	0.809	0.559	0.767	0.122	0.090	0.630	0.183	0.638	0.778	0.000	0.382	0.607	0.412	0.698	0.256	0.500	0.705	0.000	0.213
sharpen_0	0.699	0.343	0.390	0.678	0.775	0.774	0.853	0.538	0.475	0.252	0.759	0.761	0.647	0.297	0.373	0.585	0.602	0.649	0.505	0.688	0.829	0.781	0.860	0.757	0.145	0.397	0.125	0.003	0.494	0.078	0.198	0.000	0.056	0.443	0.000	0.000	0.330	0.528	0.358	0.349	0.584	0.257	0.414	0.316	0.000	0.381	0.435	0.239	0.208	0.610	0.586	0.341	0.762	0.472	0.784	0.181	0.351	0.647	0.362	0.756	0.526	0.807	0.634	0.704	0.137	0.065	0.560	0.137	0.562	0.649	0.000	0.373	0.847	0.308	0.395	0.232	0.800	0.656	0.000	0.000
sharpen_1	0.708	0.398	0.398	0.736	0.785	0.706	0.796	0.515	0.433	0.240	0.756	0.704	0.614	0.282	0.402	0.595	0.594	0.671	0.525	0.574	0.848	0.826	0.849	0.732	0.141	0.437	0.074	0.046	0.462	0.081	0.218	0.000	0.054	0.456	0.000	0.000	0.302	0.514	0.366	0.279	0.478	0.249	0.480	0.353	0.059	0.414	0.401	0.461	0.560	0.644	0.530	0.488	0.906	0.448	0.653	0.173	0.357	0.701	0.315	0.764	0.514	0.791	0.585	0.721	0.122	0.067	0.575	0.121	0.676	0.723	0.000	0.397	0.809	0.261	0.411	0.241	0.667	0.701	0.000	0.000
sharpen_2	0.713	0.381	0.405	0.779	0.751	0.783	0.773	0.540	0.525	0.213	0.749	0.725	0.682	0.325	0.418	0.614	0.603	0.575	0.500	0.607	0.824	0.837	0.861	0.747	0.093	0.389	0.129	0.018	0.512	0.089	0.221	0.000	0.065	0.485	0.000	0.000	0.294	0.555	0.338	0.323	0.595	0.286	0.380	0.253	0.000	0.377	0.444	0.339	0.435	0.605	0.520	0.328	0.882	0.521	0.662	0.265	0.364	0.678	0.311	0.758	0.564	0.851	0.587	0.785	0.171	0.053	0.570	0.087	0.545	0.622	0.000	0.433	0.773	0.279	0.411	0.237	0.400	0.702	0.000	0.000
addintensity_-80	0.698	0.566	0.389	0.696	0.722	0.796	0.829	0.413	0.407	0.204	0.686	0.898	0.580	0.312	0.445	0.647	0.541	0.606	0.498	0.463	0.873	0.667	0.883	0.903	0.056	0.511	0.165	0.064	0.541	0.078	0.236	0.000	0.114	0.460	0.000	0.000	0.343	0.563	0.473	0.213	0.533	0.230	0.566	0.172	0.000	0.404	0.678	0.229	0.363	0.372	0.474	0.349	0.371	0.502	0.813	0.312	0.367	0.644	0.264	0.832	0.563	0.759	0.490	0.703	0.116	0.068	0.482	0.129	0.529	0.643	0.000	0.429	0.673	0.330	0.450	0.309	0.471	0.782	0.000	0.400
addintensity_80	0.709	0.527	0.407	0.734	0.767	0.706	0.787	0.566	0.589	0.249	0.707	0.716	0.620	0.340	0.474	0.632	0.585	0.639	0.607	0.590	0.774	0.833	0.907	0.842	0.159	0.490	0.195	0.092	0.569	0.049	0.215	0.000	0.064	0.486	0.000	0.000	0.298	0.486	0.486	0.293	0.410	0.225	0.367	0.395	0.071	0.459	0.526	0.289	0.484	0.673	0.602	0.342	0.436	0.486	0.564	0.309	0.375	0.652	0.333	0.792	0.471	0.784	0.609	0.773	0.129	0.107	0.456	0.083	0.486	0.796	0.000	0.383	0.801	0.344	0.425	0.285	0.667	0.758	0.000	0.278
elementrandomintensity_1	0.627	0.403	0.346	0.806	0.714	0.723	0.574	0.348	0.267	0.113	0.412	0.749	0.472	0.238	0.338	0.639	0.415	0.494	0.290	0.513	0.917	0.523	0.916	0.864	0.247	0.318	0.373	0.000	0.268	0.000	0.240	0.000	0.044	0.647	0.000	0.000	0.392	0.323	0.465	0.296	0.694	0.238	0.857	0.000	0.000	0.389	0.711	0.310	0.000	0.600	0.259	0.365	0.000	0.536	0.188	0.098	0.347	0.742	0.108	0.756	0.628	0.519	0.573	0.905	0.000	0.000	0.667	0.200	0.000	0.862	0.000	0.152	0.000	0.207	0.568	0.233	0.600	0.484	0.000	0.000
multiplyintensity_0p25	0.719	0.594	0.491	0.850	0.816	0.858	0.863	0.482	0.597	0.203	0.714	0.784	0.588	0.346	0.477	0.602	0.658	0.697	0.668	0.545	0.851	0.744	0.897	0.909	0.153	0.487	0.168	0.083	0.669	0.104	0.319	0.000	0.058	0.648	0.000	0.000	0.325	0.566	0.503	0.372	0.666	0.261	0.520	0.500	0.000	0.518	0.714	0.471	0.375	0.788	0.547	0.438	0.655	0.540	0.619	0.264	0.380	0.574	0.335	0.812	0.553	0.714	0.525	0.777	0.154	0.079	0.383	0.329	0.362	0.712	0.000	0.441	0.797	0.403	0.455	0.388	0.667	0.724	0.000	0.152
multiplyintensity_2	0.704	0.530	0.422	0.723	0.817	0.699	0.783	0.564	0.520	0.226	0.651	0.686	0.717	0.310	0.458	0.661	0.529	0.629	0.617	0.583	0.853	0.782	0.920	0.855	0.104	0.441	0.167	0.018	0.523	0.072	0.283	0.000	0.065	0.462	0.000	0.000	0.352	0.505	0.402	0.260	0.530	0.204	0.363	0.296	0.000	0.372	0.559	0.213	0.421	0.452	0.504	0.277	0.404	0.426	0.650	0.279	0.399	0.615	0.312	0.746	0.527	0.877	0.602	0.780	0.142	0.073	0.445	0.087	0.448	0.751	0.000	0.350	0.819	0.345	0.447	0.300	0.651	0.784	0.000	0.300
contrastnormalization_0	0.720	0.531	0.445	0.742	0.743	0.794	0.762	0.504	0.591	0.276	0.689	0.776	0.697	0.368	0.410	0.674	0.558	0.668	0.610	0.577	0.891	0.770	0.896	0.874	0.176	0.466	0.131	0.059	0.631	0.057	0.169	0.000	0.054	0.493	0.075	0.000	0.380	0.546	0.388	0.280	0.479	0.225	0.471	0.241	0.039	0.405	0.675	0.278	0.326	0.551	0.508	0.243	0.634	0.531	0.646	0.354	0.391	0.650	0.257	0.828	0.501	0.750	0.633	0.732	0.132	0.087	0.488	0.068	0.522	0.780	0.000	0.430	0.837	0.330	0.476	0.316	0.421	0.739	0.000	0.247
contrastnormalization_1	0.710	0.483	0.408	0.722	0.715	0.733	0.790	0.524	0.530	0.282	0.761	0.692	0.762	0.291	0.460	0.637	0.566	0.668	0.490	0.567	0.851	0.629	0.913	0.843	0.175	0.431	0.155	0.101	0.653	0.052	0.198	0.000	0.091	0.508	0.154	0.104	0.282	0.575	0.406	0.312	0.522	0.242	0.443	0.299	0.049	0.439	0.664	0.227	0.345	0.521	0.573	0.319	0.700	0.539	0.642	0.371	0.360	0.663	0.304	0.875	0.518	0.814	0.639	0.769	0.097	0.064	0.506	0.149	0.583	0.777	0.000	0.472	0.749	0.375	0.464	0.304	0.286	0.707	0.000	0.177
contrastnormalization_2	0.727	0.467	0.431	0.772	0.803	0.725	0.758	0.511	0.598	0.240	0.577	0.834	0.679	0.403	0.548	0.659	0.619	0.597	0.600	0.607	0.871	0.774	0.902	0.817	0.167	0.438	0.167	0.116	0.664	0.060	0.203	0.000	0.057	0.492	0.082	0.000	0.315	0.485	0.429	0.277	0.486	0.233	0.452	0.302	0.000	0.414	0.603	0.211	0.366	0.560	0.536	0.328	0.562	0.530	0.646	0.344	0.374	0.694	0.228	0.751	0.485	0.832	0.663	0.755	0.094	0.068	0.536	0.093	0.503	0.779	0.000	0.388	0.733	0.320	0.457	0.276	0.529	0.798	0.000	0.325
elastic_1	0.624	0.000	0.345	1.000	1.000	0.750	0.383	0.784	0.149	0.286	0.258	0.733	0.444	0.344	1.000	0.476	0.390	0.331	0.417	1.000	0.708	0.486	1.000	0.935	0.000	0.292	0.000	0.000	0.750	0.023	0.000	0.000	0.000	0.289	0.000	0.000	0.000	0.149	0.000	0.500	0.000	0.372	0.000	0.000	0.000	0.584	0.800	0.248	0.000	0.627	0.342	0.286	1.000	0.800	0.250	0.243	0.179	1.000	0.106	1.000	0.600	0.795	0.442	0.000	0.500	0.000	0.000	0.000	1.000	0.500	0.000	0.100	0.000	0.000	0.000	0.300	0.000	0.727	0.000	0.000
scaled_1p25	0.748	0.522	0.425	0.735	0.799	0.808	0.872	0.555	0.685	0.418	0.722	0.931	0.688	0.456	0.496	0.716	0.675	0.699	0.580	0.655	0.889	0.883	0.927	0.882	0.120	0.641	0.134	0.189	0.620	0.418	0.392	0.000	0.136	0.644	0.311	0.000	0.391	0.570	0.524	0.298	0.549	0.324	0.332	0.360	0.241	0.445	0.794	0.275	0.545	0.587	0.606	0.433	0.873	0.572	0.596	0.424	0.435	0.676	0.305	0.877	0.615	0.854	0.646	0.702	0.146	0.104	0.494	0.217	0.425	0.703	0.383	0.502	0.741	0.458	0.570	0.293	0.500	0.729	0.000	0.209
scaled_0p75	0.615	0.429	0.230	0.714	0.722	0.709	0.789	0.489	0.437	0.089	0.641	0.663	0.587	0.271	0.486	0.583	0.497	0.588	0.420	0.554	0.803	0.810	0.845	0.712	0.060	0.460	0.043	0.000	0.525	0.000	0.134	0.000	0.000	0.494	0.082	0.000	0.193	0.326	0.128	0.146	0.230	0.121	0.058	0.096	0.075	0.258	0.529	0.133	0.379	0.260	0.370	0.326	0.622	0.386	0.546	0.306	0.236	0.772	0.152	0.832	0.445	0.617	0.417	0.660	0.194	0.052	0.293	0.049	0.340	0.564	0.000	0.247	0.598	0.260	0.349	0.179	0.750	0.705	0.000	0.305
scaled_0p5	0.491	0.305	0.122	0.498	0.581	0.606	0.768	0.544	0.211	0.070	0.499	0.426	0.600	0.262	0.278	0.494	0.423	0.569	0.414	0.438	0.650	0.657	0.679	0.672	0.036	0.352	0.000	0.000	0.416	0.000	0.072	0.000	0.000	0.293	0.000	0.000	0.015	0.247	0.000	0.114	0.099	0.020	0.000	0.000	0.000	0.160	0.449	0.187	0.217	0.095	0.176	0.075	0.464	0.409	0.355	0.353	0.143	0.451	0.110	0.897	0.417	0.466	0.187	0.475	0.000	0.000	0.025	0.107	0.482	0.337	0.000	0.153	0.603	0.126	0.219	0.168	0.750	0.514	0.000	0.353
scaled_(1p25, 1p0)	0.741	0.484	0.385	0.704	0.808	0.774	0.843	0.560	0.608	0.312	0.720	0.836	0.688	0.354	0.451	0.638	0.562	0.792	0.565	0.606	0.887	0.815	0.883	0.871	0.118	0.530	0.152	0.214	0.606	0.169	0.278	0.000	0.098	0.595	0.201	0.000	0.360	0.497	0.432	0.309	0.634	0.299	0.490	0.289	0.331	0.365	0.698	0.251	0.592	0.571	0.588	0.424	0.677	0.468	0.625	0.469	0.381	0.678	0.313	0.825	0.541	0.811	0.668	0.736	0.159	0.072	0.382	0.159	0.352	0.713	0.526	0.521	0.799	0.416	0.442	0.276	0.364	0.717	0.000	0.222
scaled_(0p75, 1p0)	0.657	0.480	0.272	0.682	0.765	0.698	0.806	0.459	0.497	0.217	0.653	0.637	0.633	0.311	0.478	0.649	0.570	0.536	0.498	0.546	0.808	0.753	0.869	0.758	0.105	0.561	0.052	0.057	0.533	0.000	0.203	0.000	0.034	0.517	0.000	0.000	0.268	0.439	0.343	0.192	0.414	0.181	0.286	0.271	0.112	0.344	0.574	0.200	0.311	0.464	0.475	0.318	0.560	0.555	0.717	0.372	0.290	0.742	0.271	0.877	0.447	0.628	0.511	0.711	0.107	0.000	0.319	0.089	0.497	0.602	0.000	0.316	0.665	0.254	0.390	0.196	0.714	0.782	0.000	0.330
scaled_(1p0, 1p25)	0.725	0.598	0.466	0.796	0.814	0.782	0.786	0.543	0.594	0.396	0.760	0.758	0.723	0.406	0.472	0.733	0.645	0.595	0.561	0.584	0.871	0.763	0.905	0.858	0.119	0.644	0.138	0.126	0.675	0.189	0.285	0.147	0.090	0.589	0.239	0.000	0.349	0.549	0.510	0.235	0.530	0.233	0.444	0.200	0.108	0.446	0.689	0.333	0.537	0.541	0.609	0.359	0.819	0.585	0.691	0.523	0.373	0.728	0.350	0.920	0.585	0.799	0.608	0.754	0.111	0.047	0.562	0.227	0.552	0.754	0.000	0.520	0.661	0.413	0.517	0.272	0.426	0.788	0.000	0.316
scaled_(1p0, 0p75)	0.679	0.518	0.316	0.775	0.740	0.772	0.780	0.522	0.410	0.175	0.658	0.758	0.638	0.333	0.454	0.616	0.551	0.777	0.488	0.586	0.831	0.805	0.853	0.802	0.114	0.336	0.148	0.004	0.611	0.062	0.195	0.000	0.035	0.474	0.000	0.000	0.247	0.405	0.260	0.234	0.366	0.203	0.502	0.206	0.033	0.316	0.577	0.250	0.214	0.368	0.505	0.283	0.552	0.359	0.558	0.351	0.343	0.666	0.211	0.821	0.393	0.822	0.527	0.670	0.068	0.045	0.499	0.088	0.428	0.679	0.000	0.358	0.698	0.312	0.349	0.324	0.517	0.740	0.000	0.308
translate_(0p1, 0p1)	0.661	0.380	0.263	0.693	0.782	0.754	0.815	0.523	0.487	0.145	0.591	0.630	0.637	0.247	0.434	0.614	0.612	0.590	0.569	0.621	0.842	0.806	0.878	0.827	0.053	0.474	0.071	0.009	0.491	0.000	0.172	0.000	0.042	0.503	0.061	0.000	0.295	0.473	0.248	0.162	0.306	0.182	0.421	0.187	0.099	0.316	0.561	0.259	0.293	0.305	0.495	0.274	0.564	0.472	0.608	0.409	0.270	0.683	0.221	0.877	0.479	0.703	0.531	0.674	0.097	0.000	0.281	0.073	0.439	0.590	0.000	0.323	0.567	0.285	0.330	0.253	0.500	0.783	0.000	0.414
translate_(0p1, -0p1)	0.710	0.462	0.369	0.751	0.803	0.750	0.840	0.515	0.633	0.365	0.655	0.845	0.641	0.329	0.447	0.606	0.593	0.576	0.587	0.614	0.857	0.796	0.904	0.849	0.099	0.606	0.072	0.064	0.651	0.128	0.246	0.091	0.036	0.532	0.175	0.000	0.351	0.549	0.347	0.245	0.435	0.216	0.564	0.224	0.144	0.364	0.603	0.271	0.407	0.524	0.569	0.410	0.560	0.547	0.691	0.353	0.324	0.681	0.272	0.841	0.512	0.790	0.540	0.759	0.095	0.000	0.449	0.107	0.500	0.680	0.000	0.400	0.780	0.300	0.447	0.379	0.444	0.755	0.000	0.375
translate_(-0p1, 0p1)	0.708	0.481	0.349	0.730	0.776	0.830	0.827	0.539	0.609	0.177	0.683	0.765	0.586	0.400	0.538	0.734	0.600	0.690	0.572	0.671	0.873	0.963	0.887	0.850	0.058	0.562	0.153	0.134	0.611	0.125	0.244	0.000	0.100	0.551	0.119	0.000	0.402	0.565	0.387	0.240	0.504	0.214	0.309	0.295	0.211	0.429	0.703	0.314	0.461	0.478	0.523	0.354	0.764	0.489	0.626	0.455	0.357	0.657	0.271	0.880	0.550	0.780	0.549	0.749	0.113	0.151	0.343	0.104	0.612	0.754	0.000	0.464	0.767	0.357	0.430	0.299	0.459	0.753	0.000	0.312
translate_(-0p1, -0p1)	0.742	0.540	0.432	0.786	0.860	0.881	0.834	0.529	0.660	0.409	0.691	0.847	0.772	0.429	0.517	0.747	0.605	0.713	0.555	0.682	0.888	0.932	0.917	0.873	0.151	0.625	0.135	0.224	0.653	0.400	0.282	0.082	0.118	0.620	0.297	0.000	0.418	0.597	0.481	0.279	0.576	0.277	0.373	0.271	0.356	0.467	0.718	0.352	0.568	0.560	0.627	0.477	0.689	0.612	0.635	0.504	0.463	0.662	0.350	0.781	0.614	0.807	0.643	0.788	0.184	0.000	0.431	0.270	0.522	0.755	0.000	0.531	0.814	0.446	0.596	0.331	0.494	0.755	0.000	0.333
translate_(0p1, 0)	0.697	0.434	0.322	0.700	0.817	0.790	0.828	0.468	0.575	0.210	0.660	0.739	0.680	0.232	0.429	0.613	0.582	0.636	0.623	0.592	0.814	0.804	0.916	0.831	0.051	0.528	0.096	0.061	0.545	0.088	0.172	0.000	0.035	0.488	0.061	0.000	0.290	0.445	0.317	0.197	0.388	0.219	0.419	0.209	0.082	0.386	0.566	0.183	0.360	0.365	0.499	0.272	0.541	0.551	0.713	0.333	0.325	0.643	0.271	0.867	0.480	0.694	0.542	0.759	0.100	0.031	0.447	0.117	0.444	0.649	0.000	0.387	0.703	0.286	0.412	0.318	0.750	0.804	0.000	0.353
translate_(-0p1, 0)	0.736	0.560	0.376	0.761	0.845	0.793	0.864	0.507	0.615	0.322	0.688	0.670	0.701	0.373	0.508	0.770	0.564	0.760	0.555	0.654	0.879	0.903	0.900	0.888	0.156	0.613	0.168	0.201	0.628	0.196	0.259	0.000	0.084	0.559	0.187	0.000	0.413	0.537	0.463	0.283	0.567	0.290	0.391	0.254	0.262	0.496	0.685	0.281	0.576	0.576	0.585	0.444	0.624	0.573	0.673	0.457	0.419	0.655	0.304	0.909	0.563	0.788	0.611	0.787	0.171	0.099	0.364	0.136	0.481	0.787	0.000	0.474	0.758	0.403	0.503	0.284	0.460	0.793	0.000	0.364
translate_(0, 0p1)	0.691	0.472	0.358	0.740	0.726	0.754	0.846	0.538	0.532	0.177	0.647	0.690	0.648	0.287	0.430	0.659	0.589	0.667	0.570	0.574	0.813	0.804	0.910	0.824	0.088	0.434	0.065	0.007	0.620	0.067	0.198	0.000	0.066	0.511	0.000	0.000	0.316	0.472	0.355	0.227	0.358	0.207	0.456	0.297	0.035	0.379	0.588	0.248	0.313	0.387	0.551	0.309	0.635	0.483	0.682	0.433	0.368	0.711	0.245	0.864	0.528	0.799	0.526	0.671	0.180	0.089	0.451	0.128	0.555	0.717	0.000	0.412	0.656	0.285	0.379	0.355	0.421	0.779	0.000	0.400
translate_(0, -0p1)	0.732	0.546	0.443	0.766	0.790	0.780	0.848	0.541	0.638	0.412	0.706	0.715	0.727	0.374	0.466	0.661	0.591	0.700	0.588	0.640	0.844	0.885	0.923	0.868	0.125	0.565	0.165	0.068	0.685	0.193	0.199	0.054	0.093	0.576	0.218	0.000	0.395	0.553	0.480	0.278	0.554	0.241	0.404	0.244	0.108	0.452	0.693	0.273	0.535	0.603	0.583	0.388	0.722	0.543	0.723	0.406	0.410	0.669	0.335	0.848	0.593	0.774	0.604	0.731	0.083	0.049	0.502	0.179	0.548	0.767	0.000	0.476	0.740	0.358	0.515	0.311	0.400	0.813	0.000	0.300
rotated_3	0.719	0.579	0.461	0.766	0.726	0.740	0.803	0.525	0.604	0.340	0.710	0.777	0.613	0.339	0.471	0.682	0.604	0.674	0.574	0.624	0.855	0.788	0.892	0.868	0.154	0.550	0.180	0.103	0.668	0.061	0.286	0.061	0.096	0.530	0.087	0.000	0.428	0.541	0.492	0.281	0.550	0.272	0.449	0.310	0.092	0.390	0.674	0.299	0.449	0.482	0.569	0.410	0.682	0.584	0.727	0.436	0.375	0.676	0.330	0.820	0.547	0.815	0.561	0.735	0.124	0.214	0.471	0.166	0.684	0.803	0.000	0.452	0.767	0.354	0.457	0.305	0.500	0.814	0.000	0.286
rotated_5	0.724	0.622	0.448	0.733	0.762	0.783	0.874	0.459	0.608	0.409	0.710	0.818	0.606	0.372	0.545	0.754	0.588	0.702	0.594	0.648	0.870	0.903	0.899	0.867	0.125	0.532	0.176	0.128	0.691	0.106	0.321	0.142	0.085	0.580	0.069	0.000	0.389	0.539	0.460	0.294	0.616	0.309	0.460	0.304	0.248	0.452	0.705	0.300	0.487	0.543	0.568	0.350	0.661	0.599	0.745	0.516	0.410	0.671	0.324	0.912	0.553	0.858	0.577	0.721	0.143	0.163	0.498	0.070	0.592	0.773	0.000	0.526	0.832	0.390	0.462	0.307	0.500	0.800	0.000	0.370
rotated_10	0.736	0.556	0.435	0.785	0.782	0.775	0.905	0.489	0.691	0.399	0.737	0.854	0.757	0.480	0.518	0.729	0.573	0.663	0.614	0.650	0.845	0.845	0.908	0.903	0.143	0.625	0.233	0.228	0.614	0.190	0.383	0.173	0.096	0.578	0.076	0.000	0.383	0.499	0.394	0.272	0.566	0.273	0.509	0.359	0.215	0.429	0.702	0.372	0.529	0.600	0.605	0.346	0.636	0.634	0.696	0.511	0.408	0.724	0.292	0.844	0.580	0.813	0.548	0.722	0.083	0.102	0.544	0.139	0.710	0.723	0.000	0.492	0.748	0.367	0.520	0.331	0.429	0.848	0.000	0.255
rotated_45	0.734	0.649	0.433	0.732	0.683	0.843	0.622	0.472	0.462	0.489	0.852	0.958	1.000	0.344	0.386	0.682	0.381	0.838	0.750	0.755	0.959	0.711	0.913	0.885	0.221	0.313	0.182	0.620	0.479	0.263	0.385	0.242	0.075	0.423	0.296	0.062	0.255	0.620	0.434	0.246	0.592	0.258	0.529	0.087	0.216	0.636	0.680	0.213	0.624	0.613	0.617	0.372	0.722	0.584	0.739	0.482	0.526	0.500	0.404	0.726	0.601	0.829	0.759	0.804	0.258	0.242	0.626	0.279	0.333	0.424	0.000	0.656	0.391	0.320	0.516	0.400	0.188	0.824	0.000	0.267
rotated_60	0.766	0.562	0.426	0.556	0.548	0.529	0.672	0.576	0.000	0.211	0.875	1.000	0.000	0.285	0.356	0.550	0.391	0.832	0.645	0.818	0.927	0.704	0.915	0.835	0.164	0.386	0.105	0.720	0.328	0.187	0.177	0.073	0.080	0.313	0.312	0.214	0.259	0.565	0.340	0.339	0.474	0.182	0.436	0.069	0.185	0.706	0.715	0.435	0.637	0.681	0.578	0.433	0.554	0.615	0.717	0.560	0.488	0.333	0.423	0.770	0.612	0.840	0.594	0.679	0.400	0.198	0.562	0.260	0.000	0.250	0.000	0.500	0.180	0.307	0.428	0.333	0.000	0.691	0.000	0.211
rotated_90	0.713	0.516	0.412	0.591	0.478	0.478	0.759	0.500	0.500	0.014	0.571	0.687	0.000	0.062	0.276	0.381	0.324	0.724	0.619	0.571	0.926	0.759	0.862	0.901	0.051	0.512	0.176	0.250	0.392	0.205	0.430	0.000	0.000	0.341	0.150	0.043	0.129	0.331	0.304	0.107	0.270	0.186	0.426	0.136	0.069	0.556	0.647	0.242	0.535	0.625	0.506	0.287	0.500	0.704	0.647	0.636	0.211	0.167	0.211	0.688	0.652	0.661	0.294	0.487	0.188	0.059	0.529	0.178	0.000	0.130	0.000	0.183	0.144	0.231	0.328	0.000	1.000	0.570	0.000	0.207
flipH	0.711	0.530	0.408	0.779	0.835	0.772	0.883	0.509	0.525	0.263	0.775	0.708	0.736	0.435	0.483	0.704	0.575	0.684	0.601	0.683	0.826	0.752	0.856	0.886	0.076	0.534	0.182	0.084	0.563	0.125	0.192	0.000	0.089	0.525	0.320	0.000	0.265	0.536	0.306	0.308	0.301	0.320	0.286	0.264	0.124	0.404	0.632	0.257	0.553	0.563	0.535	0.340	0.489	0.505	0.669	0.310	0.429	0.645	0.271	0.860	0.511	0.721	0.664	0.647	0.159	0.160	0.397	0.195	0.438	0.574	0.000	0.418	0.748	0.386	0.430	0.159	0.975	0.843	0.000	0.300
flipV	0.729	0.427	0.220	0.717	0.630	0.870	0.638	0.316	0.184	0.138	0.781	0.746	0.500	0.369	0.210	0.484	0.332	0.741	0.545	0.452	1.000	0.857	0.863	0.832	0.065	0.250	0.061	0.348	0.357	0.149	0.380	0.156	0.056	0.331	0.000	0.000	0.332	0.405	0.325	0.147	0.213	0.188	0.379	0.191	0.188	0.379	0.645	0.246	0.298	0.508	0.614	0.304	0.800	0.592	0.612	0.520	0.377	0.353	0.130	0.520	0.609	0.692	0.316	0.770	0.545	0.000	0.512	0.133	0.309	0.346	0.000	0.407	0.338	0.267	0.343	0.153	0.500	0.628	0.000	0.500
dropout	0.687	0.643	0.443	0.831	0.669	0.730	0.755	0.423	0.527	0.248	0.530	0.850	0.606	0.275	0.156	0.497	0.543	0.580	0.500	0.505	0.848	0.750	0.913	0.834	0.103	0.255	0.156	0.000	0.537	0.000	0.186	0.000	0.000	0.571	0.000	0.000	0.610	0.496	0.442	0.415	0.331	0.286	0.636	0.422	0.000	0.468	0.245	0.000	0.000	0.400	0.316	0.246	0.250	0.521	0.306	0.155	0.373	0.605	0.242	0.498	0.523	0.518	0.498	0.792	0.300	0.096	0.845	0.000	0.455	1.000	0.000	0.203	0.667	0.419	0.286	0.215	0.250	0.354	0.000	0.000

transform	person	bicycle	car	motorcycle	airplane	bus	train	truck	boat	traffic light	fire hydrant	stop sign	parking meter	bench	bird	cat	dog	horse	sheep	cow	elephant	bear	zebra	giraffe	backpack	umbrella	handbag	tie	suitcase	frisbee	skis	snowboard	sports ball	kite	baseball bat	baseball glove	skateboard	surfboard	tennis racket	bottle	wine glass	cup	fork	knife	spoon	bowl	banana	apple	sandwich	orange	broccoli	carrot	hot dog	pizza	donut	cake	chair	couch	potted plant	bed	dining table	toilet	tv	laptop	mouse	remote	keyboard	cell phone	microwave	oven	toaster	sink	refrigerator	book	clock	vase	scissors	teddy bear	hair drier	toothbrush
None	0.697	0.506	0.405	0.716	0.763	0.768	0.875	0.486	0.531	0.279	0.708	0.625	0.626	0.473	0.497	0.627	0.669	0.713	0.690	0.613	0.858	0.859	0.860	0.856	0.136	0.640	0.071	0.036	0.651	0.095	0.272	0.152	0.061	0.623	0.229	0.055	0.324	0.311	0.372	0.275	0.349	0.269	0.381	0.243	0.166	0.363	0.587	0.415	0.508	0.397	0.517	0.265	0.585	0.546	0.598	0.420	0.386	0.594	0.407	0.825	0.479	0.742	0.604	0.646	0.085	0.138	0.440	0.125	0.420	0.603	0.000	0.421	0.762	0.317	0.352	0.302	0.544	0.708	0.000	0.252
gaussianblur_1	0.711	0.567	0.436	0.745	0.793	0.724	0.864	0.606	0.621	0.326	0.762	0.622	0.617	0.372	0.507	0.673	0.537	0.702	0.559	0.630	0.818	0.711	0.933	0.844	0.135	0.572	0.133	0.038	0.690	0.084	0.217	0.100	0.080	0.612	0.000	0.000	0.407	0.563	0.471	0.354	0.513	0.230	0.475	0.281	0.251	0.404	0.650	0.144	0.406	0.413	0.534	0.280	0.648	0.556	0.654	0.317	0.398	0.784	0.381	0.831	0.503	0.785	0.606	0.676	0.091	0.137	0.435	0.132	0.536	0.793	0.000	0.378	0.718	0.316	0.432	0.330	0.286	0.860	0.000	0.176
gaussianblur_10	0.686	0.000	0.514	0.000	0.000	0.577	0.400	0.000	0.000	0.200	0.000	0.667	1.000	0.000	0.444	0.500	0.138	0.000	0.000	0.000	1.000	1.000	0.000	0.000	0.000	0.500	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.078	0.000	0.028	0.000	0.000	0.000	0.418	0.625	0.055	0.000	0.290	0.000	0.462	1.000	0.397	0.191	0.240	0.102	0.000	0.000	0.000	0.698	1.000	0.354	0.419	0.070	0.000	0.000	0.000	0.500	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000
gaussianblur_20	0.636	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.667	0.000	0.000	0.385	0.000	1.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000
superpixels_0p1	0.700	0.249	0.306	0.589	0.654	0.680	0.584	0.289	0.127	0.102	0.469	0.663	0.408	0.237	0.698	0.639	0.500	0.663	0.463	0.191	0.766	0.467	1.000	1.000	0.000	0.270	0.000	0.000	0.293	0.000	0.000	0.000	0.000	0.198	0.000	0.000	0.062	0.333	0.182	0.351	0.506	0.177	0.000	0.160	0.000	0.367	0.649	0.233	0.333	0.388	0.347	0.270	0.489	0.654	0.248	0.113	0.267	0.824	0.219	0.850	0.490	0.853	0.348	0.659	0.750	0.131	0.287	0.071	0.222	0.753	0.000	0.210	0.334	0.395	0.555	0.304	0.000	0.594	0.000	0.000
superpixels_0p5	0.628	0.667	0.187	0.775	0.574	0.600	0.511	0.150	0.028	0.028	0.353	0.633	0.205	0.177	0.500	0.625	1.000	0.000	0.000	0.000	0.556	1.000	1.000	0.000	0.000	0.344	0.000	0.000	0.250	0.000	0.000	0.000	0.000	0.160	0.000	0.000	0.000	0.000	0.000	0.188	0.197	0.275	0.000	0.000	0.000	0.111	0.333	0.000	0.000	0.314	0.307	0.402	0.000	0.606	0.293	0.068	0.161	1.000	0.081	1.000	0.314	0.833	0.289	1.000	0.000	0.000	0.625	0.000	1.000	0.273	0.000	0.000	0.401	0.335	0.595	0.000	0.000	0.429	0.000	0.000
superpixels_0p85	0.596	0.000	0.093	1.000	0.750	0.000	0.000	0.113	0.000	0.004	0.222	0.404	0.000	0.000	0.333	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.231	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.071	0.000	0.000	0.000	0.000	0.000	0.167	0.500	0.240	0.000	0.000	0.000	0.000	0.000	0.000	0.000	1.000	0.122	0.115	0.000	0.000	0.444	0.138	0.000	0.000	0.211	0.000	0.000	0.000	0.361	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.500	0.000	0.000
colorspace_25	0.722	0.498	0.450	0.708	0.806	0.738	0.875	0.453	0.566	0.245	0.657	0.760	0.664	0.300	0.430	0.660	0.538	0.725	0.461	0.531	0.867	0.722	0.905	0.830	0.159	0.429	0.084	0.041	0.563	0.050	0.242	0.081	0.050	0.609	0.000	0.000	0.358	0.574	0.363	0.304	0.581	0.207	0.346	0.264	0.195	0.316	0.396	0.173	0.661	0.671	0.299	0.000	1.000	0.598	0.638	0.337	0.361	0.664	0.312	0.778	0.506	0.854	0.650	0.758	0.102	0.128	0.484	0.141	0.614	0.756	0.000	0.353	0.765	0.340	0.480	0.387	0.476	0.782	0.000	0.170
colorspace_50	0.727	0.543	0.453	0.750	0.798	0.711	0.855	0.507	0.602	0.223	0.629	0.623	0.546	0.226	0.467	0.648	0.576	0.732	0.544	0.494	0.862	0.722	0.891	0.834	0.197	0.433	0.054	0.043	0.501	0.051	0.193	0.000	0.066	0.626	0.000	0.000	0.379	0.541	0.397	0.297	0.575	0.199	0.385	0.319	0.205	0.354	0.525	0.188	0.000	0.857	0.278	0.000	0.000	0.580	0.567	0.221	0.372	0.742	0.263	0.725	0.526	0.810	0.632	0.745	0.092	0.000	0.478	0.101	0.632	0.794	0.000	0.394	0.692	0.332	0.447	0.350	0.500	0.717	0.000	0.000
averageblur_5_11	0.723	0.445	0.483	0.784	0.845	0.767	0.814	0.569	0.602	0.224	0.810	0.648	0.694	0.298	0.494	0.556	0.478	0.827	0.418	0.490	0.816	0.696	0.947	0.891	0.104	0.636	0.160	0.000	0.549	0.109	0.333	0.000	0.065	0.483	0.000	0.000	0.354	0.633	0.471	0.373	0.608	0.206	0.411	0.350	0.088	0.349	0.637	0.140	0.437	0.492	0.416	0.294	0.798	0.475	0.731	0.274	0.309	0.701	0.390	0.871	0.461	0.833	0.536	0.599	0.131	0.056	0.476	0.112	0.545	0.595	0.000	0.406	0.839	0.414	0.576	0.379	0.286	0.898	0.000	0.301
medianblur_1	0.686	0.675	0.450	0.794	0.814	0.762	0.752	0.617	0.499	0.254	0.875	0.573	0.890	0.500	0.357	0.624	0.410	0.700	0.505	0.488	0.794	0.724	0.946	0.876	0.152	0.529	0.125	0.000	0.554	0.085	0.251	0.000	0.081	0.490	0.000	0.000	0.328	0.550	0.443	0.302	0.703	0.210	0.417	0.233	0.087	0.430	0.497	0.225	0.356	0.497	0.487	0.242	0.689	0.465	0.545	0.312	0.367	0.682	0.347	0.762	0.497	0.803	0.531	0.800	0.098	0.080	0.594	0.109	0.692	0.727	0.000	0.465	0.694	0.388	0.648	0.337	0.417	0.796	0.000	0.161
sharpen_0	0.711	0.401	0.420	0.799	0.757	0.747	0.822	0.575	0.562	0.274	0.743	0.594	0.656	0.246	0.410	0.610	0.621	0.674	0.531	0.692	0.720	0.795	0.846	0.762	0.134	0.454	0.087	0.037	0.499	0.087	0.218	0.000	0.050	0.418	0.000	0.000	0.370	0.553	0.363	0.284	0.512	0.238	0.356	0.239	0.137	0.341	0.453	0.137	0.222	0.570	0.535	0.255	0.777	0.459	0.589	0.247	0.358	0.601	0.355	0.725	0.585	0.774	0.547	0.748	0.131	0.065	0.506	0.110	0.508	0.691	0.000	0.357	0.703	0.274	0.442	0.244	0.101	0.712	0.000	0.000
sharpen_1	0.719	0.382	0.435	0.710	0.824	0.789	0.812	0.535	0.509	0.261	0.660	0.589	0.606	0.287	0.391	0.619	0.648	0.654	0.495	0.593	0.762	0.711	0.864	0.771	0.052	0.469	0.159	0.000	0.498	0.095	0.279	0.000	0.060	0.570	0.000	0.000	0.341	0.486	0.385	0.303	0.554	0.242	0.346	0.346	0.258	0.354	0.393	0.167	0.406	0.504	0.517	0.289	0.772	0.490	0.622	0.247	0.354	0.614	0.276	0.827	0.583	0.823	0.540	0.744	0.105	0.081	0.496	0.138	0.612	0.681	0.000	0.357	0.657	0.299	0.453	0.284	0.375	0.702	0.000	0.000
sharpen_2	0.711	0.393	0.462	0.755	0.826	0.810	0.760	0.561	0.596	0.266	0.735	0.588	0.667	0.348	0.451	0.633	0.606	0.673	0.568	0.516	0.774	0.776	0.844	0.789	0.177	0.487	0.089	0.038	0.444	0.092	0.291	0.000	0.052	0.637	0.000	0.000	0.353	0.486	0.363	0.310	0.562	0.248	0.377	0.279	0.179	0.355	0.451	0.210	0.352	0.486	0.543	0.262	0.654	0.467	0.698	0.254	0.354	0.638	0.298	0.774	0.575	0.828	0.585	0.726	0.131	0.077	0.511	0.076	0.623	0.661	0.000	0.353	0.708	0.280	0.447	0.246	0.207	0.727	0.000	0.000
addintensity_-80	0.702	0.586	0.389	0.758	0.780	0.797	0.825	0.516	0.590	0.229	0.678	0.695	0.488	0.434	0.464	0.636	0.508	0.599	0.563	0.574	0.895	0.602	0.932	0.912	0.111	0.517	0.118	0.045	0.610	0.087	0.218	0.101	0.082	0.457	0.087	0.000	0.365	0.534	0.421	0.250	0.521	0.194	0.503	0.188	0.108	0.407	0.596	0.206	0.296	0.378	0.555	0.339	0.622	0.482	0.787	0.329	0.391	0.733	0.289	0.876	0.539	0.724	0.482	0.685	0.112	0.100	0.376	0.074	0.581	0.600	0.000	0.372	0.642	0.288	0.425	0.371	0.250	0.791	0.000	0.364
addintensity_80	0.719	0.454	0.419	0.794	0.813	0.733	0.883	0.582	0.550	0.257	0.695	0.573	0.571	0.344	0.479	0.712	0.618	0.732	0.613	0.590	0.807	0.738	0.904	0.800	0.083	0.473	0.088	0.059	0.685	0.064	0.201	0.000	0.058	0.626	0.000	0.000	0.353	0.502	0.435	0.304	0.526	0.217	0.362	0.301	0.162	0.375	0.558	0.291	0.382	0.561	0.558	0.242	0.645	0.488	0.633	0.260	0.407	0.545	0.313	0.791	0.499	0.808	0.656	0.761	0.079	0.099	0.526	0.122	0.571	0.794	0.000	0.351	0.806	0.298	0.437	0.309	0.462	0.790	0.000	0.284
elementrandomintensity_1	0.638	0.562	0.331	0.826	0.729	0.934	0.906	0.373	0.502	0.220	0.590	0.664	0.643	0.134	0.426	0.592	0.529	0.416	0.359	0.422	0.871	0.453	0.951	0.821	0.176	0.354	0.298	0.032	0.340	0.000	0.194	0.000	0.042	0.495	0.059	0.000	0.311	0.350	0.356	0.200	0.459	0.179	0.762	0.114	0.000	0.307	0.783	0.000	0.279	0.769	0.270	0.206	0.435	0.571	0.198	0.119	0.327	0.716	0.161	0.619	0.586	0.909	0.548	0.838	0.000	0.000	0.750	0.058	1.000	1.000	0.000	0.293	1.000	0.128	0.342	0.186	0.000	0.423	0.000	0.000
multiplyintensity_0p25	0.720	0.535	0.487	0.888	0.839	0.793	0.857	0.590	0.545	0.282	0.793	0.757	0.615	0.346	0.445	0.566	0.664	0.668	0.604	0.582	0.897	0.797	0.919	0.902	0.175	0.522	0.066	0.000	0.611	0.094	0.169	0.084	0.049	0.713	0.000	0.000	0.260	0.596	0.453	0.333	0.681	0.221	0.442	0.298	0.173	0.457	0.597	0.000	0.250	0.604	0.541	0.384	0.636	0.566	0.764	0.188	0.365	0.648	0.331	0.693	0.695	0.723	0.501	0.685	0.110	0.085	0.429	0.138	0.441	0.740	0.000	0.443	0.749	0.374	0.460	0.280	0.522	0.803	0.000	0.286
multiplyintensity_2	0.709	0.569	0.421	0.762	0.786	0.717	0.899	0.526	0.527	0.262	0.709	0.635	0.669	0.359	0.401	0.650	0.576	0.655	0.582	0.619	0.869	0.719	0.917	0.814	0.115	0.465	0.128	0.067	0.616	0.054	0.263	0.000	0.030	0.564	0.000	0.000	0.393	0.513	0.472	0.296	0.498	0.197	0.287	0.265	0.209	0.307	0.434	0.185	0.442	0.401	0.488	0.246	0.521	0.373	0.606	0.261	0.379	0.581	0.309	0.857	0.509	0.841	0.603	0.791	0.109	0.124	0.475	0.093	0.577	0.694	0.000	0.412	0.692	0.335	0.436	0.276	0.482	0.744	0.000	0.290
contrastnormalization_0	0.721	0.556	0.436	0.739	0.756	0.745	0.885	0.506	0.595	0.309	0.617	0.643	0.618	0.373	0.438	0.649	0.515	0.651	0.570	0.609	0.895	0.793	0.936	0.880	0.253	0.516	0.117	0.071	0.659	0.057	0.204	0.000	0.024	0.509	0.000	0.000	0.365	0.572	0.414	0.265	0.506	0.216	0.435	0.267	0.284	0.354	0.643	0.156	0.351	0.450	0.543	0.245	0.678	0.522	0.641	0.292	0.379	0.666	0.317	0.862	0.513	0.752	0.609	0.739	0.094	0.109	0.494	0.100	0.609	0.732	0.000	0.431	0.691	0.322	0.480	0.285	0.328	0.789	0.000	0.160
contrastnormalization_1	0.713	0.520	0.436	0.728	0.777	0.687	0.861	0.565	0.550	0.259	0.714	0.692	0.647	0.332	0.474	0.633	0.601	0.605	0.532	0.588	0.886	0.688	0.925	0.856	0.152	0.476	0.112	0.040	0.647	0.062	0.210	0.000	0.070	0.577	0.000	0.000	0.339	0.545	0.417	0.314	0.508	0.209	0.409	0.268	0.295	0.355	0.655	0.121	0.304	0.493	0.569	0.319	0.754	0.524	0.670	0.308	0.337	0.684	0.274	0.765	0.519	0.774	0.609	0.739	0.104	0.127	0.465	0.120	0.474	0.786	0.000	0.413	0.681	0.323	0.472	0.309	0.400	0.784	0.000	0.189
contrastnormalization_2	0.724	0.512	0.434	0.718	0.811	0.761	0.828	0.562	0.598	0.212	0.666	0.716	0.566	0.392	0.463	0.656	0.623	0.690	0.526	0.670	0.861	0.757	0.918	0.821	0.186	0.476	0.124	0.038	0.754	0.071	0.122	0.000	0.056	0.551	0.069	0.000	0.408	0.562	0.407	0.322	0.533	0.212	0.284	0.281	0.266	0.355	0.574	0.169	0.333	0.390	0.539	0.305	0.613	0.535	0.641	0.279	0.393	0.729	0.255	0.871	0.488	0.804	0.671	0.633	0.091	0.137	0.537	0.134	0.571	0.712	0.000	0.418	0.632	0.306	0.497	0.281	0.400	0.797	0.000	0.217
elastic_1	0.610	0.000	0.278	1.000	0.000	0.769	0.791	0.562	0.250	0.186	0.402	0.769	0.456	0.191	1.000	0.551	0.629	0.238	0.250	0.400	0.738	0.400	1.000	0.971	0.000	0.358	0.000	0.000	0.000	0.110	0.000	0.000	0.000	0.211	0.000	0.000	0.000	0.237	0.800	0.400	0.000	0.288	0.000	0.000	0.000	0.375	0.500	0.048	0.000	0.475	0.281	0.292	0.000	0.591	0.154	0.190	0.161	0.684	0.090	0.000	0.619	0.678	0.380	1.000	0.333	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.434	0.000	0.530	0.000	0.000
scaled_1p25	0.755	0.488	0.461	0.805	0.853	0.792	0.915	0.505	0.680	0.380	0.753	0.776	0.719	0.366	0.519	0.700	0.700	0.800	0.588	0.672	0.915	0.836	0.923	0.906	0.132	0.597	0.096	0.250	0.725	0.401	0.337	0.000	0.149	0.654	0.298	0.000	0.434	0.554	0.502	0.309	0.554	0.269	0.259	0.363	0.238	0.380	0.789	0.216	0.408	0.513	0.600	0.393	0.722	0.605	0.658	0.488	0.437	0.603	0.317	0.894	0.589	0.831	0.662	0.759	0.147	0.090	0.463	0.155	0.453	0.596	0.000	0.464	0.874	0.477	0.539	0.318	0.571	0.801	0.000	0.207
scaled_0p75	0.611	0.355	0.225	0.666	0.761	0.708	0.848	0.489	0.422	0.124	0.661	0.649	0.632	0.223	0.535	0.619	0.558	0.702	0.449	0.551	0.795	0.759	0.833	0.776	0.037	0.450	0.048	0.040	0.488	0.000	0.208	0.000	0.000	0.433	0.076	0.000	0.219	0.358	0.082	0.172	0.247	0.091	0.184	0.218	0.000	0.213	0.562	0.208	0.327	0.306	0.352	0.254	0.453	0.379	0.650	0.248	0.208	0.645	0.177	0.798	0.437	0.611	0.467	0.652	0.093	0.046	0.351	0.042	0.214	0.608	0.000	0.239	0.776	0.260	0.349	0.220	0.800	0.718	0.000	0.423
scaled_0p5	0.486	0.387	0.130	0.524	0.605	0.558	0.811	0.550	0.235	0.027	0.447	0.417	0.485	0.264	0.312	0.509	0.479	0.542	0.466	0.472	0.618	0.613	0.684	0.682	0.000	0.431	0.000	0.000	0.370	0.000	0.103	0.000	0.000	0.329	0.000	0.000	0.017	0.222	0.000	0.120	0.193	0.039	0.000	0.000	0.000	0.165	0.442	0.171	0.323	0.092	0.200	0.058	0.448	0.400	0.512	0.209	0.108	0.462	0.123	0.806	0.486	0.459	0.284	0.483	0.000	0.055	0.032	0.117	0.320	0.365	0.000	0.153	0.630	0.153	0.175	0.144	0.667	0.532	0.000	0.667
scaled_(1p25, 1p0)	0.749	0.517	0.439	0.697	0.846	0.770	0.868	0.530	0.639	0.341	0.764	0.779	0.625	0.294	0.476	0.705	0.617	0.787	0.521	0.659	0.922	0.869	0.923	0.924	0.270	0.513	0.123	0.119	0.731	0.201	0.310	0.000	0.089	0.624	0.179	0.000	0.327	0.564	0.450	0.311	0.560	0.273	0.342	0.331	0.232	0.374	0.712	0.177	0.424	0.485	0.584	0.356	0.761	0.482	0.721	0.472	0.381	0.630	0.343	0.807	0.538	0.817	0.650	0.713	0.203	0.048	0.471	0.101	0.486	0.717	0.000	0.477	0.841	0.424	0.465	0.231	0.250	0.802	0.000	0.255
scaled_(0p75, 1p0)	0.668	0.475	0.292	0.685	0.783	0.766	0.877	0.526	0.562	0.168	0.805	0.597	0.572	0.300	0.457	0.586	0.546	0.659	0.486	0.534	0.801	0.802	0.823	0.752	0.117	0.536	0.066	0.038	0.555	0.000	0.214	0.000	0.031	0.580	0.067	0.000	0.313	0.444	0.337	0.206	0.438	0.169	0.184	0.164	0.062	0.302	0.608	0.232	0.315	0.354	0.445	0.263	0.587	0.565	0.685	0.317	0.267	0.738	0.247	0.884	0.467	0.695	0.583	0.679	0.119	0.053	0.334	0.064	0.557	0.540	0.000	0.262	0.751	0.238	0.374	0.255	0.600	0.820	0.000	0.286
scaled_(1p0, 1p25)	0.727	0.541	0.445	0.806	0.848	0.693	0.828	0.514	0.645	0.418	0.747	0.709	0.704	0.378	0.449	0.698	0.686	0.609	0.575	0.572	0.845	0.815	0.912	0.884	0.097	0.637	0.129	0.118	0.619	0.201	0.271	0.098	0.090	0.614	0.185	0.000	0.423	0.592	0.392	0.282	0.592	0.194	0.303	0.299	0.098	0.436	0.663	0.275	0.409	0.489	0.598	0.318	0.694	0.612	0.698	0.423	0.400	0.674	0.329	0.896	0.603	0.877	0.583	0.705	0.109	0.046	0.495	0.220	0.670	0.801	0.000	0.450	0.693	0.356	0.465	0.274	0.333	0.819	0.000	0.200
scaled_(1p0, 0p75)	0.676	0.482	0.355	0.707	0.710	0.726	0.877	0.458	0.472	0.186	0.747	0.730	0.625	0.317	0.478	0.635	0.591	0.734	0.513	0.601	0.861	0.849	0.859	0.801	0.133	0.358	0.122	0.067	0.601	0.070	0.220	0.000	0.034	0.529	0.081	0.000	0.285	0.462	0.297	0.249	0.419	0.180	0.299	0.276	0.092	0.291	0.583	0.212	0.366	0.400	0.480	0.311	0.545	0.379	0.695	0.269	0.322	0.626	0.232	0.777	0.426	0.780	0.552	0.676	0.096	0.071	0.451	0.052	0.265	0.682	0.000	0.343	0.737	0.270	0.413	0.347	0.647	0.783	0.000	0.236
translate_(0p1, 0p1)	0.664	0.423	0.286	0.664	0.729	0.714	0.945	0.468	0.529	0.165	0.770	0.619	0.662	0.281	0.484	0.583	0.591	0.659	0.478	0.616	0.832	0.758	0.880	0.862	0.054	0.545	0.032	0.040	0.529	0.000	0.226	0.000	0.035	0.508	0.000	0.000	0.304	0.477	0.180	0.164	0.360	0.151	0.312	0.219	0.145	0.286	0.593	0.166	0.357	0.318	0.422	0.275	0.574	0.480	0.661	0.334	0.268	0.670	0.191	0.818	0.529	0.706	0.579	0.626	0.091	0.045	0.311	0.060	0.477	0.666	0.000	0.287	0.787	0.266	0.314	0.288	1.000	0.739	0.000	0.353
translate_(0p1, -0p1)	0.711	0.469	0.386	0.773	0.791	0.738	0.895	0.563	0.619	0.312	0.741	0.735	0.598	0.352	0.492	0.637	0.602	0.687	0.482	0.620	0.857	0.788	0.906	0.909	0.190	0.650	0.062	0.042	0.542	0.155	0.257	0.000	0.035	0.601	0.179	0.000	0.406	0.503	0.335	0.274	0.450	0.204	0.404	0.296	0.169	0.355	0.651	0.130	0.505	0.480	0.547	0.300	0.640	0.546	0.687	0.329	0.330	0.682	0.290	0.801	0.533	0.797	0.647	0.774	0.180	0.080	0.426	0.113	0.491	0.662	0.000	0.498	0.760	0.296	0.426	0.260	0.750	0.781	0.000	0.429
translate_(-0p1, 0p1)	0.718	0.451	0.332	0.759	0.707	0.791	0.904	0.494	0.622	0.209	0.676	0.781	0.657	0.299	0.536	0.685	0.612	0.732	0.614	0.644	0.854	0.827	0.908	0.855	0.036	0.491	0.171	0.184	0.657	0.118	0.260	0.000	0.084	0.623	0.068	0.000	0.470	0.567	0.314	0.263	0.477	0.177	0.162	0.285	0.199	0.358	0.627	0.248	0.401	0.445	0.551	0.301	0.720	0.483	0.831	0.388	0.308	0.608	0.316	0.879	0.580	0.780	0.573	0.713	0.105	0.049	0.447	0.082	0.570	0.671	0.000	0.424	0.745	0.364	0.396	0.243	1.000	0.721	0.000	0.324
translate_(-0p1, -0p1)	0.754	0.529	0.429	0.771	0.794	0.830	0.863	0.496	0.655	0.410	0.714	0.834	0.832	0.371	0.515	0.744	0.636	0.762	0.590	0.680	0.898	0.833	0.937	0.877	0.221	0.622	0.131	0.244	0.675	0.469	0.296	0.083	0.142	0.651	0.308	0.000	0.455	0.628	0.463	0.309	0.592	0.225	0.284	0.321	0.253	0.404	0.741	0.231	0.465	0.549	0.636	0.383	0.800	0.604	0.712	0.426	0.420	0.551	0.361	0.817	0.594	0.798	0.697	0.754	0.204	0.072	0.529	0.185	0.429	0.747	0.000	0.525	0.707	0.418	0.573	0.329	0.500	0.810	0.000	0.218
translate_(0p1, 0)	0.693	0.445	0.316	0.690	0.742	0.711	0.924	0.491	0.584	0.203	0.740	0.585	0.553	0.334	0.436	0.572	0.548	0.671	0.451	0.640	0.881	0.806	0.909	0.876	0.061	0.536	0.065	0.078	0.554	0.000	0.243	0.000	0.032	0.592	0.063	0.000	0.345	0.493	0.343	0.220	0.426	0.186	0.406	0.213	0.210	0.342	0.618	0.167	0.313	0.314	0.492	0.259	0.598	0.601	0.642	0.245	0.325	0.688	0.253	0.821	0.480	0.694	0.631	0.624	0.107	0.048	0.391	0.093	0.462	0.677	0.000	0.311	0.755	0.263	0.388	0.316	0.333	0.820	0.000	0.351
translate_(-0p1, 0)	0.741	0.482	0.406	0.789	0.767	0.791	0.841	0.483	0.596	0.277	0.736	0.670	0.608	0.346	0.508	0.746	0.594	0.763	0.563	0.661	0.866	0.865	0.896	0.866	0.180	0.552	0.164	0.188	0.631	0.161	0.269	0.000	0.068	0.627	0.146	0.000	0.435	0.566	0.415	0.357	0.585	0.247	0.237	0.382	0.227	0.417	0.697	0.203	0.419	0.436	0.597	0.388	0.738	0.569	0.715	0.402	0.382	0.623	0.369	0.861	0.583	0.824	0.634	0.787	0.210	0.051	0.488	0.145	0.438	0.704	0.000	0.435	0.715	0.387	0.498	0.270	0.333	0.754	0.000	0.261
translate_(0, 0p1)	0.693	0.469	0.342	0.724	0.709	0.755	0.903	0.466	0.520	0.192	0.715	0.742	0.686	0.295	0.456	0.630	0.635	0.716	0.550	0.637	0.827	0.832	0.899	0.823	0.079	0.449	0.069	0.036	0.671	0.066	0.246	0.000	0.030	0.556	0.000	0.000	0.332	0.481	0.330	0.248	0.370	0.178	0.302	0.312	0.180	0.331	0.612	0.224	0.360	0.392	0.512	0.315	0.607	0.539	0.693	0.364	0.349	0.622	0.277	0.915	0.531	0.805	0.552	0.669	0.089	0.065	0.446	0.110	0.417	0.705	0.000	0.369	0.686	0.274	0.363	0.269	0.571	0.795	0.000	0.242
translate_(0, -0p1)	0.729	0.579	0.450	0.777	0.793	0.763	0.861	0.495	0.616	0.400	0.710	0.703	0.780	0.334	0.512	0.728	0.654	0.735	0.546	0.641	0.859	0.865	0.924	0.903	0.192	0.573	0.091	0.074	0.708	0.206	0.219	0.096	0.089	0.642	0.170	0.000	0.454	0.552	0.414	0.323	0.567	0.242	0.312	0.294	0.186	0.392	0.707	0.176	0.530	0.588	0.589	0.314	0.782	0.524	0.696	0.401	0.394	0.625	0.373	0.836	0.540	0.818	0.646	0.726	0.160	0.079	0.524	0.125	0.632	0.687	0.000	0.540	0.688	0.346	0.500	0.328	0.273	0.812	0.000	0.160
rotated_3	0.726	0.519	0.442	0.753	0.749	0.743	0.861	0.527	0.609	0.333	0.694	0.658	0.591	0.401	0.504	0.736	0.568	0.681	0.543	0.634	0.865	0.772	0.899	0.876	0.098	0.572	0.123	0.105	0.709	0.067	0.217	0.106	0.083	0.624	0.000	0.000	0.465	0.573	0.492	0.304	0.524	0.236	0.324	0.335	0.207	0.376	0.649	0.239	0.307	0.445	0.547	0.312	0.755	0.564	0.676	0.453	0.366	0.684	0.308	0.890	0.537	0.819	0.582	0.718	0.177	0.179	0.491	0.161	0.401	0.703	0.000	0.428	0.705	0.358	0.444	0.323	0.444	0.851	0.000	0.209
rotated_5	0.728	0.573	0.456	0.776	0.758	0.758	0.900	0.540	0.649	0.322	0.711	0.660	0.623	0.386	0.516	0.746	0.608	0.687	0.560	0.690	0.858	0.806	0.898	0.853	0.099	0.556	0.149	0.117	0.705	0.128	0.344	0.170	0.082	0.576	0.072	0.000	0.414	0.551	0.433	0.283	0.628	0.250	0.409	0.230	0.163	0.402	0.719	0.208	0.426	0.458	0.579	0.288	0.588	0.537	0.699	0.454	0.362	0.686	0.378	0.878	0.584	0.807	0.584	0.695	0.151	0.114	0.502	0.167	0.633	0.719	0.000	0.494	0.901	0.313	0.423	0.331	0.280	0.808	0.000	0.221
rotated_10	0.739	0.602	0.441	0.786	0.759	0.736	0.904	0.548	0.669	0.358	0.772	0.660	0.771	0.337	0.474	0.714	0.591	0.707	0.559	0.627	0.861	0.818	0.901	0.868	0.088	0.540	0.068	0.248	0.760	0.180	0.356	0.265	0.087	0.675	0.000	0.000	0.375	0.531	0.393	0.289	0.561	0.230	0.351	0.261	0.184	0.377	0.721	0.283	0.412	0.499	0.595	0.292	0.668	0.649	0.654	0.473	0.385	0.710	0.296	0.890	0.576	0.859	0.557	0.731	0.100	0.088	0.521	0.179	0.709	0.818	0.000	0.556	0.860	0.353	0.487	0.371	0.625	0.864	0.000	0.205
rotated_45	0.715	0.524	0.437	0.660	0.690	0.762	1.000	0.434	1.000	0.348	0.910	0.739	0.500	0.351	0.387	0.689	0.508	0.801	0.660	0.732	0.930	0.649	0.930	0.900	0.109	0.461	0.322	0.363	0.676	0.298	0.370	0.310	0.062	0.559	0.399	0.000	0.214	0.585	0.445	0.254	0.548	0.239	0.416	0.136	0.154	0.521	0.706	0.323	0.547	0.548	0.567	0.311	0.699	0.613	0.615	0.432	0.424	0.679	0.277	0.689	0.602	0.866	0.660	0.759	0.308	0.211	0.639	0.287	0.400	0.529	0.000	0.580	0.903	0.364	0.477	0.421	0.105	0.856	0.000	0.179
rotated_60	0.749	0.567	0.463	0.625	0.583	0.920	1.000	0.411	0.889	0.154	0.909	0.896	0.000	0.394	0.368	0.648	0.542	0.837	0.545	0.694	0.956	0.673	0.898	0.917	0.235	0.455	0.138	0.224	0.430	0.359	0.291	0.154	0.062	0.464	0.393	0.000	0.185	0.524	0.401	0.181	0.643	0.191	0.500	0.100	0.131	0.495	0.693	0.214	0.500	0.544	0.542	0.349	0.515	0.664	0.529	0.553	0.408	0.667	0.279	0.810	0.652	0.808	0.485	0.632	0.273	0.323	0.390	0.314	0.000	0.280	0.000	0.712	0.357	0.254	0.383	0.250	0.000	0.688	0.000	0.226
rotated_90	0.731	0.466	0.194	0.526	0.583	0.746	0.774	0.293	0.000	0.012	0.714	0.750	0.000	0.066	0.236	0.471	0.310	0.857	0.583	0.684	0.818	0.830	0.864	0.910	0.060	0.591	0.050	0.000	0.384	0.168	0.172	0.000	0.000	0.409	0.226	0.000	0.180	0.313	0.191	0.223	0.135	0.124	0.203	0.127	0.152	0.484	0.530	0.288	0.406	0.538	0.549	0.282	0.536	0.632	0.578	0.529	0.221	0.333	0.243	0.568	0.609	0.593	0.242	0.578	1.000	0.126	0.462	0.172	0.000	0.250	0.000	0.323	0.260	0.236	0.304	0.200	0.200	0.500	0.000	0.160
flipH	0.709	0.514	0.419	0.736	0.804	0.751	0.896	0.518	0.603	0.259	0.777	0.645	0.758	0.378	0.508	0.700	0.611	0.668	0.574	0.715	0.828	0.770	0.841	0.884	0.111	0.496	0.145	0.070	0.552	0.137	0.167	0.099	0.126	0.554	0.224	0.081	0.332	0.564	0.330	0.299	0.417	0.303	0.266	0.279	0.203	0.400	0.610	0.201	0.479	0.526	0.494	0.380	0.319	0.542	0.663	0.303	0.408	0.550	0.319	0.829	0.583	0.689	0.689	0.648	0.090	0.172	0.488	0.198	0.531	0.597	0.000	0.421	0.760	0.378	0.380	0.246	0.714	0.833	0.000	0.176
flipV	0.725	0.575	0.490	0.839	0.623	0.819	0.623	0.361	0.259	0.122	0.730	0.717	0.387	0.334	0.231	0.524	0.362	0.662	1.000	0.328	1.000	1.000	0.848	0.886	0.125	0.191	0.000	0.245	0.475	0.161	0.406	0.236	0.043	0.397	0.000	0.000	0.157	0.365	0.230	0.150	0.185	0.174	0.377	0.298	0.141	0.305	0.570	0.187	0.308	0.412	0.572	0.316	0.588	0.568	0.646	0.391	0.409	0.316	0.183	0.556	0.732	0.664	0.330	0.609	0.343	0.000	0.407	0.152	0.436	0.638	0.000	0.524	0.480	0.276	0.321	0.168	0.286	0.589	0.000	0.462
dropout	0.667	0.697	0.498	0.740	0.863	0.875	0.933	0.484	0.545	0.306	0.738	0.733	0.682	0.309	0.254	0.573	0.658	0.537	0.478	0.536	0.853	0.632	0.930	0.903	0.088	0.517	0.131	0.038	0.499	0.000	0.360	0.000	0.000	0.478	0.000	0.000	0.397	0.412	0.294	0.375	0.608	0.209	0.800	0.289	0.249	0.358	0.338	0.296	0.887	0.827	0.361	0.194	0.625	0.529	0.273	0.100	0.260	0.648	0.232	0.589	0.531	0.630	0.509	0.893	0.200	0.000	0.738	0.041	0.429	1.000	0.000	0.179	0.774	0.427	0.222	0.233	0.529	0.318	0.000	0.000

transform	person	bicycle	car	motorcycle	airplane	bus	train	truck	boat	traffic light	fire hydrant	stop sign	parking meter	bench	bird	cat	dog	horse	sheep	cow	elephant	bear	zebra	giraffe	backpack	umbrella	handbag	tie	suitcase	frisbee	skis	snowboard	sports ball	kite	baseball bat	baseball glove	skateboard	surfboard	tennis racket	bottle	wine glass	cup	fork	knife	spoon	bowl	banana	apple	sandwich	orange	broccoli	carrot	hot dog	pizza	donut	cake	chair	couch	potted plant	bed	dining table	toilet	tv	laptop	mouse	remote	keyboard	cell phone	microwave	oven	toaster	sink	refrigerator	book	clock	vase	scissors	teddy bear	hair drier	toothbrush
None	0.698	0.507	0.423	0.734	0.770	0.745	0.855	0.491	0.567	0.280	0.752	0.584	0.645	0.472	0.509	0.658	0.659	0.732	0.704	0.637	0.871	0.816	0.842	0.855	0.147	0.644	0.111	0.029	0.665	0.099	0.277	0.164	0.054	0.590	0.294	0.082	0.339	0.305	0.365	0.295	0.359	0.278	0.368	0.228	0.224	0.371	0.611	0.418	0.521	0.400	0.555	0.295	0.474	0.535	0.663	0.476	0.387	0.621	0.409	0.776	0.441	0.704	0.594	0.650	0.092	0.137	0.439	0.143	0.397	0.600	0.000	0.395	0.780	0.332	0.370	0.335	0.581	0.712	0.000	0.210
gaussianblur_1	0.712	0.425	0.467	0.787	0.776	0.736	0.830	0.592	0.669	0.254	0.717	0.634	0.497	0.448	0.495	0.683	0.557	0.737	0.595	0.646	0.854	0.789	0.913	0.857	0.154	0.522	0.182	0.034	0.604	0.071	0.234	0.097	0.081	0.639	0.244	0.000	0.374	0.559	0.386	0.372	0.522	0.269	0.349	0.348	0.197	0.392	0.542	0.223	0.379	0.495	0.546	0.266	0.646	0.580	0.797	0.360	0.390	0.696	0.310	0.889	0.467	0.754	0.551	0.679	0.086	0.104	0.519	0.138	0.519	0.808	0.000	0.378	0.692	0.392	0.411	0.342	0.429	0.741	0.000	0.308
gaussianblur_10	0.624	0.000	0.398	1.000	1.000	0.692	0.545	1.000	0.000	0.333	0.500	0.667	0.500	0.000	0.207	0.065	0.000	0.793	0.000	0.600	1.000	1.000	0.000	1.000	0.000	0.308	0.000	0.000	0.000	0.000	0.000	0.000	0.000	1.000	0.000	0.000	0.000	0.000	0.000	0.140	0.077	0.043	0.000	1.000	0.000	0.333	0.365	0.200	1.000	0.387	0.250	0.840	0.333	0.464	0.390	0.210	0.267	0.000	1.000	1.000	0.275	1.000	0.370	0.690	0.105	0.000	0.000	0.000	0.500	0.000	0.000	0.200	0.000	0.000	1.000	0.400	0.000	0.000	0.000	0.000
gaussianblur_20	0.468	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.500	1.000	0.000	0.000	0.125	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.222	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000
superpixels_0p1	0.723	0.296	0.324	0.720	0.653	0.806	0.612	0.247	0.277	0.127	0.395	0.523	0.112	0.177	0.532	0.737	0.409	0.627	0.326	0.280	0.705	0.515	0.987	1.000	0.000	0.466	0.000	0.000	0.452	0.000	0.000	0.000	0.085	0.307	0.000	0.000	0.000	0.613	0.438	0.310	0.580	0.220	0.667	0.241	0.000	0.385	0.719	0.172	0.419	0.613	0.341	0.267	0.690	0.738	0.279	0.109	0.235	0.680	0.259	0.800	0.536	0.914	0.402	0.694	0.500	0.000	0.386	0.152	0.480	0.544	0.000	0.237	0.370	0.456	0.552	0.210	0.000	0.600	0.000	0.000
superpixels_0p5	0.669	0.423	0.209	0.800	0.537	0.595	0.446	0.201	0.081	0.033	0.265	0.421	0.197	0.135	0.435	0.500	0.222	0.571	0.000	0.143	0.838	0.700	1.000	1.000	0.000	0.290	0.000	0.000	0.417	0.000	0.000	0.000	0.000	0.203	0.000	0.000	0.000	0.000	0.000	0.122	0.000	0.291	0.000	0.000	0.000	0.364	0.516	0.273	0.000	0.364	0.318	0.365	0.000	0.386	0.336	0.062	0.122	0.692	0.087	1.000	0.365	0.889	0.288	0.857	0.000	0.000	0.375	0.000	0.310	0.271	0.000	0.000	0.328	0.514	0.571	0.083	0.000	0.580	0.000	0.000
superpixels_0p85	0.582	0.000	0.062	1.000	0.128	0.000	0.750	0.000	0.000	0.007	0.154	0.396	0.000	0.333	0.286	0.000	0.000	1.000	0.000	0.000	0.000	0.000	1.000	0.000	0.000	0.328	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.162	0.000	0.000	0.000	0.000	0.000	0.167	0.000	0.143	0.000	0.000	0.000	0.000	0.000	0.000	0.000	1.000	0.226	0.308	0.000	0.000	0.000	0.065	0.400	0.000	0.226	0.000	0.000	1.000	0.212	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.333	0.000	0.000	0.000	0.000	0.000	0.000	0.000
colorspace_25	0.729	0.437	0.473	0.753	0.774	0.737	0.891	0.493	0.625	0.267	0.685	0.808	0.649	0.359	0.500	0.663	0.633	0.724	0.443	0.526	0.859	0.847	0.891	0.889	0.175	0.555	0.118	0.036	0.506	0.053	0.253	0.081	0.090	0.483	0.072	0.000	0.370	0.542	0.401	0.302	0.519	0.196	0.341	0.352	0.260	0.296	0.425	0.223	0.604	0.820	0.315	0.000	1.000	0.734	0.659	0.294	0.382	0.673	0.346	0.739	0.505	0.800	0.632	0.732	0.111	0.073	0.552	0.108	0.552	0.765	0.000	0.360	0.812	0.365	0.475	0.345	0.571	0.693	0.000	0.000
colorspace_50	0.736	0.432	0.483	0.735	0.763	0.748	0.805	0.487	0.607	0.244	0.701	0.799	0.619	0.274	0.464	0.665	0.566	0.705	0.508	0.501	0.822	0.647	0.906	0.859	0.204	0.460	0.075	0.041	0.581	0.056	0.222	0.000	0.055	0.496	0.000	0.000	0.366	0.545	0.297	0.275	0.507	0.208	0.402	0.298	0.175	0.346	0.701	0.356	0.417	0.882	0.309	0.000	0.000	0.629	0.568	0.181	0.381	0.698	0.310	0.691	0.517	0.786	0.613	0.720	0.097	0.078	0.533	0.124	0.536	0.774	0.000	0.371	0.718	0.399	0.469	0.321	0.500	0.648	0.000	0.000
averageblur_5_11	0.726	0.504	0.497	0.839	0.845	0.741	0.789	0.578	0.650	0.311	0.745	0.833	0.591	0.357	0.466	0.611	0.483	0.730	0.526	0.563	0.738	0.803	0.926	0.927	0.037	0.608	0.313	0.045	0.624	0.092	0.330	0.000	0.038	0.561	0.072	0.000	0.413	0.638	0.370	0.441	0.510	0.282	0.446	0.300	0.088	0.402	0.570	0.160	0.389	0.553	0.466	0.238	0.608	0.556	0.890	0.350	0.391	0.681	0.415	0.771	0.475	0.753	0.582	0.666	0.178	0.058	0.419	0.126	0.477	0.557	0.000	0.358	0.620	0.392	0.462	0.346	0.375	0.841	0.000	0.165
medianblur_1	0.699	0.545	0.482	0.780	0.741	0.784	0.778	0.607	0.587	0.214	0.832	0.634	0.874	0.401	0.324	0.646	0.374	0.701	0.530	0.547	0.784	0.814	0.914	0.927	0.093	0.476	0.059	0.044	0.577	0.042	0.266	0.000	0.065	0.488	0.000	0.000	0.462	0.572	0.456	0.406	0.579	0.257	0.381	0.246	0.131	0.394	0.480	0.210	0.551	0.458	0.536	0.284	0.673	0.565	0.693	0.378	0.382	0.747	0.329	0.813	0.475	0.824	0.554	0.781	0.103	0.106	0.608	0.122	0.600	0.564	0.000	0.355	0.722	0.360	0.530	0.296	0.450	0.781	0.000	0.235
sharpen_0	0.715	0.428	0.458	0.759	0.773	0.748	0.846	0.500	0.580	0.268	0.735	0.583	0.667	0.389	0.439	0.643	0.595	0.690	0.474	0.555	0.877	0.809	0.876	0.804	0.119	0.432	0.131	0.023	0.445	0.088	0.247	0.000	0.060	0.444	0.079	0.000	0.305	0.531	0.375	0.314	0.501	0.259	0.340	0.357	0.143	0.369	0.524	0.177	0.256	0.588	0.570	0.293	0.703	0.493	0.565	0.211	0.371	0.659	0.360	0.794	0.522	0.797	0.571	0.698	0.149	0.046	0.524	0.104	0.620	0.602	0.000	0.334	0.812	0.328	0.487	0.270	0.500	0.783	0.000	0.000
sharpen_1	0.713	0.470	0.451	0.720	0.758	0.809	0.879	0.493	0.571	0.277	0.710	0.596	0.655	0.442	0.429	0.624	0.601	0.675	0.441	0.613	0.879	0.854	0.887	0.812	0.195	0.508	0.123	0.023	0.438	0.080	0.227	0.000	0.060	0.650	0.072	0.000	0.362	0.537	0.360	0.353	0.572	0.248	0.308	0.402	0.065	0.384	0.472	0.269	0.388	0.583	0.607	0.262	0.683	0.565	0.610	0.267	0.395	0.615	0.427	0.825	0.508	0.793	0.576	0.745	0.104	0.000	0.534	0.095	0.701	0.603	0.000	0.377	0.736	0.344	0.489	0.320	0.500	0.765	0.000	0.320
sharpen_2	0.713	0.386	0.445	0.715	0.785	0.774	0.835	0.535	0.631	0.284	0.743	0.627	0.615	0.420	0.458	0.659	0.617	0.645	0.426	0.502	0.861	0.864	0.881	0.804	0.170	0.506	0.146	0.017	0.485	0.093	0.273	0.000	0.065	0.514	0.089	0.000	0.323	0.525	0.361	0.337	0.586	0.256	0.333	0.308	0.224	0.366	0.553	0.238	0.322	0.539	0.579	0.238	0.475	0.526	0.687	0.247	0.376	0.626	0.354	0.781	0.513	0.839	0.586	0.779	0.109	0.046	0.597	0.099	0.626	0.530	0.000	0.455	0.792	0.346	0.452	0.321	0.500	0.718	0.000	0.375
addintensity_-80	0.719	0.571	0.431	0.797	0.740	0.879	0.748	0.461	0.553	0.210	0.633	0.745	0.643	0.464	0.444	0.570	0.512	0.689	0.606	0.577	0.872	0.616	0.904	0.907	0.139	0.551	0.172	0.063	0.652	0.073	0.290	0.000	0.062	0.599	0.140	0.000	0.370	0.498	0.472	0.252	0.598	0.219	0.393	0.225	0.221	0.408	0.586	0.202	0.329	0.347	0.543	0.473	0.723	0.501	0.736	0.331	0.365	0.759	0.329	0.853	0.546	0.781	0.532	0.675	0.098	0.110	0.486	0.106	0.417	0.621	0.000	0.386	0.690	0.360	0.433	0.341	0.429	0.734	0.000	0.250
addintensity_80	0.715	0.501	0.427	0.739	0.730	0.722	0.866	0.540	0.586	0.316	0.722	0.664	0.650	0.387	0.518	0.723	0.586	0.728	0.594	0.582	0.846	0.750	0.893	0.786	0.186	0.480	0.107	0.057	0.603	0.066	0.235	0.000	0.057	0.586	0.077	0.099	0.423	0.469	0.445	0.311	0.488	0.214	0.335	0.227	0.168	0.365	0.581	0.270	0.395	0.605	0.547	0.215	0.439	0.582	0.757	0.293	0.396	0.629	0.326	0.787	0.514	0.826	0.595	0.738	0.093	0.098	0.512	0.125	0.494	0.820	0.000	0.369	0.777	0.343	0.458	0.307	0.391	0.712	0.667	0.166
elementrandomintensity_1	0.640	0.508	0.279	0.786	0.804	0.797	0.975	0.366	0.463	0.234	0.525	0.719	0.450	0.255	0.263	0.503	0.511	0.506	0.432	0.454	0.871	0.600	0.951	0.848	0.000	0.374	0.299	0.035	0.347	0.000	0.152	0.000	0.000	0.638	0.000	0.000	0.517	0.368	0.382	0.249	0.644	0.294	0.750	0.140	0.312	0.322	0.795	0.153	0.000	0.500	0.292	0.093	0.492	0.452	0.130	0.099	0.290	0.841	0.183	0.778	0.532	0.750	0.639	0.732	0.500	0.000	1.000	0.000	1.000	0.721	0.000	0.435	1.000	0.209	0.315	0.312	0.500	0.416	0.000	0.000
multiplyintensity_0p25	0.729	0.521	0.489	0.829	0.838	0.898	0.826	0.552	0.607	0.322	0.852	0.826	0.667	0.391	0.481	0.614	0.627	0.719	0.651	0.590	0.881	0.854	0.931	0.866	0.190	0.495	0.088	0.042	0.660	0.086	0.261	0.000	0.048	0.639	0.183	0.000	0.382	0.601	0.473	0.358	0.593	0.248	0.400	0.375	0.284	0.408	0.652	0.381	0.334	0.800	0.515	0.307	0.602	0.600	0.783	0.203	0.366	0.597	0.410	0.726	0.600	0.744	0.544	0.766	0.102	0.049	0.527	0.138	0.462	0.754	0.000	0.398	0.742	0.373	0.472	0.383	0.429	0.724	0.000	0.375
multiplyintensity_2	0.714	0.546	0.415	0.700	0.757	0.755	0.839	0.529	0.517	0.242	0.671	0.588	0.743	0.351	0.511	0.649	0.580	0.672	0.588	0.565	0.819	0.794	0.909	0.849	0.185	0.489	0.155	0.119	0.583	0.054	0.174	0.000	0.032	0.534	0.166	0.000	0.344	0.535	0.382	0.293	0.479	0.232	0.332	0.337	0.099	0.357	0.441	0.201	0.458	0.475	0.526	0.221	0.592	0.464	0.667	0.333	0.407	0.678	0.286	0.797	0.515	0.787	0.603	0.773	0.119	0.092	0.508	0.155	0.441	0.622	0.000	0.369	0.566	0.357	0.449	0.289	0.387	0.656	0.000	0.300
contrastnormalization_0	0.727	0.491	0.453	0.779	0.729	0.686	0.834	0.506	0.638	0.281	0.634	0.649	0.643	0.424	0.527	0.629	0.544	0.667	0.622	0.603	0.875	0.793	0.895	0.862	0.201	0.511	0.072	0.074	0.665	0.070	0.220	0.098	0.060	0.495	0.060	0.000	0.361	0.494	0.448	0.305	0.507	0.219	0.357	0.233	0.156	0.365	0.570	0.292	0.348	0.503	0.581	0.240	0.700	0.513	0.753	0.360	0.387	0.653	0.373	0.788	0.479	0.736	0.604	0.748	0.090	0.069	0.562	0.075	0.557	0.595	0.000	0.365	0.671	0.367	0.443	0.328	0.375	0.662	0.000	0.245
contrastnormalization_1	0.718	0.441	0.434	0.815	0.724	0.672	0.856	0.577	0.624	0.229	0.757	0.689	0.639	0.374	0.499	0.693	0.620	0.687	0.605	0.640	0.860	0.701	0.909	0.856	0.243	0.508	0.096	0.074	0.704	0.078	0.169	0.105	0.092	0.546	0.148	0.081	0.318	0.546	0.407	0.302	0.508	0.239	0.347	0.365	0.346	0.354	0.638	0.181	0.455	0.487	0.582	0.270	0.701	0.606	0.710	0.373	0.386	0.711	0.280	0.767	0.487	0.704	0.641	0.715	0.101	0.079	0.575	0.163	0.583	0.793	0.000	0.372	0.573	0.374	0.423	0.250	0.439	0.753	0.000	0.261
contrastnormalization_2	0.730	0.470	0.460	0.759	0.761	0.708	0.854	0.516	0.587	0.296	0.688	0.714	0.596	0.399	0.480	0.650	0.653	0.670	0.607	0.615	0.833	0.747	0.891	0.852	0.230	0.496	0.108	0.035	0.624	0.076	0.208	0.000	0.059	0.473	0.248	0.000	0.382	0.526	0.409	0.329	0.518	0.241	0.315	0.237	0.253	0.405	0.562	0.234	0.293	0.443	0.551	0.312	0.622	0.522	0.692	0.341	0.396	0.705	0.311	0.801	0.474	0.764	0.614	0.721	0.104	0.047	0.544	0.180	0.724	0.835	0.000	0.399	0.674	0.361	0.441	0.316	0.450	0.680	0.000	0.360
elastic_1	0.669	0.000	0.275	1.000	0.000	0.625	0.697	0.463	0.112	0.300	0.637	0.649	1.000	0.444	0.500	0.462	0.684	0.262	0.692	0.667	0.869	0.438	1.000	0.846	0.000	0.416	0.000	0.000	1.000	0.097	0.250	0.000	0.000	0.393	0.000	0.000	0.000	0.284	0.571	0.833	1.000	0.358	0.000	0.333	1.000	0.528	0.464	0.089	0.000	0.512	0.337	0.278	1.000	0.640	0.207	0.101	0.335	1.000	0.093	0.500	0.625	0.765	0.553	0.924	0.667	0.000	0.000	0.333	0.000	0.000	0.000	0.484	0.000	0.000	0.000	0.256	1.000	0.692	0.000	0.000
scaled_1p25	0.759	0.501	0.481	0.747	0.820	0.792	0.890	0.575	0.676	0.356	0.758	0.886	0.748	0.426	0.533	0.764	0.627	0.794	0.640	0.668	0.873	0.836	0.906	0.959	0.203	0.606	0.126	0.238	0.728	0.437	0.384	0.000	0.147	0.659	0.306	0.000	0.411	0.573	0.497	0.345	0.619	0.292	0.358	0.351	0.221	0.406	0.741	0.285	0.518	0.521	0.646	0.413	0.744	0.639	0.740	0.511	0.437	0.622	0.336	0.779	0.588	0.823	0.714	0.739	0.202	0.074	0.548	0.233	0.432	0.680	0.000	0.493	0.746	0.475	0.578	0.321	0.400	0.795	0.000	0.206
scaled_0p75	0.619	0.377	0.223	0.678	0.703	0.665	0.824	0.435	0.361	0.079	0.622	0.670	0.640	0.367	0.537	0.573	0.577	0.701	0.487	0.596	0.786	0.767	0.830	0.760	0.054	0.413	0.056	0.000	0.512	0.000	0.181	0.000	0.000	0.503	0.117	0.000	0.196	0.302	0.129	0.193	0.277	0.105	0.221	0.173	0.032	0.182	0.493	0.261	0.347	0.293	0.357	0.322	0.457	0.403	0.791	0.314	0.264	0.656	0.192	0.777	0.454	0.597	0.481	0.699	0.118	0.038	0.350	0.039	0.340	0.610	0.000	0.201	0.697	0.264	0.319	0.208	0.471	0.658	0.000	0.240
scaled_0p5	0.480	0.310	0.120	0.554	0.547	0.594	0.729	0.481	0.185	0.065	0.456	0.418	0.393	0.320	0.272	0.541	0.447	0.493	0.405	0.448	0.628	0.652	0.687	0.675	0.000	0.474	0.000	0.000	0.385	0.000	0.078	0.000	0.000	0.291	0.000	0.000	0.016	0.210	0.025	0.113	0.103	0.037	0.000	0.000	0.000	0.181	0.474	0.192	0.299	0.106	0.216	0.102	0.349	0.411	0.635	0.324	0.105	0.473	0.119	0.829	0.489	0.402	0.237	0.443	0.000	0.000	0.027	0.080	0.500	0.269	0.000	0.175	0.574	0.152	0.161	0.106	0.588	0.477	0.000	0.400
scaled_(1p25, 1p0)	0.748	0.563	0.412	0.755	0.848	0.812	0.926	0.587	0.617	0.295	0.668	0.727	0.778	0.399	0.534	0.751	0.611	0.813	0.604	0.662	0.879	0.845	0.903	0.914	0.202	0.607	0.144	0.197	0.650	0.224	0.300	0.000	0.103	0.528	0.169	0.068	0.392	0.536	0.435	0.370	0.581	0.264	0.329	0.328	0.192	0.389	0.670	0.277	0.504	0.482	0.606	0.406	0.761	0.473	0.694	0.540	0.426	0.654	0.294	0.787	0.521	0.784	0.669	0.751	0.141	0.082	0.446	0.198	0.419	0.665	0.000	0.491	0.811	0.440	0.477	0.263	0.500	0.757	0.000	0.353
scaled_(0p75, 1p0)	0.668	0.437	0.298	0.719	0.726	0.764	0.834	0.462	0.503	0.155	0.651	0.694	0.627	0.370	0.570	0.583	0.494	0.638	0.524	0.612	0.800	0.791	0.843	0.728	0.050	0.548	0.062	0.058	0.473	0.000	0.133	0.000	0.032	0.532	0.067	0.000	0.270	0.435	0.284	0.243	0.426	0.178	0.270	0.221	0.058	0.292	0.535	0.158	0.372	0.334	0.436	0.268	0.504	0.617	0.821	0.291	0.290	0.660	0.301	0.841	0.474	0.617	0.518	0.747	0.107	0.052	0.444	0.078	0.457	0.588	0.000	0.255	0.707	0.298	0.363	0.262	0.516	0.768	0.000	0.267
scaled_(1p0, 1p25)	0.735	0.550	0.483	0.823	0.827	0.762	0.838	0.543	0.634	0.410	0.766	0.733	0.669	0.538	0.509	0.781	0.579	0.674	0.580	0.577	0.849	0.827	0.905	0.884	0.124	0.647	0.090	0.090	0.669	0.202	0.271	0.096	0.090	0.637	0.168	0.000	0.413	0.534	0.440	0.283	0.531	0.236	0.324	0.236	0.280	0.397	0.680	0.244	0.504	0.549	0.555	0.314	0.730	0.661	0.719	0.450	0.397	0.692	0.319	0.840	0.566	0.781	0.639	0.743	0.094	0.043	0.560	0.194	0.669	0.729	0.000	0.520	0.751	0.344	0.488	0.315	0.441	0.763	0.000	0.207
scaled_(1p0, 0p75)	0.690	0.491	0.325	0.697	0.749	0.792	0.881	0.492	0.445	0.156	0.678	0.716	0.588	0.392	0.497	0.663	0.629	0.751	0.547	0.620	0.824	0.795	0.843	0.817	0.095	0.430	0.045	0.037	0.557	0.057	0.192	0.000	0.034	0.528	0.152	0.000	0.258	0.381	0.307	0.268	0.464	0.205	0.408	0.207	0.151	0.304	0.533	0.312	0.429	0.456	0.465	0.238	0.701	0.385	0.668	0.353	0.349	0.623	0.224	0.733	0.422	0.668	0.547	0.686	0.086	0.074	0.472	0.101	0.370	0.652	0.000	0.334	0.671	0.276	0.391	0.333	0.362	0.743	0.000	0.462
translate_(0p1, 0p1)	0.675	0.351	0.282	0.680	0.730	0.713	0.892	0.474	0.461	0.114	0.683	0.689	0.663	0.368	0.520	0.576	0.535	0.698	0.556	0.618	0.834	0.730	0.856	0.848	0.036	0.455	0.068	0.035	0.555	0.000	0.169	0.000	0.040	0.495	0.166	0.000	0.305	0.394	0.297	0.194	0.327	0.138	0.318	0.221	0.087	0.347	0.528	0.268	0.355	0.317	0.425	0.250	0.581	0.522	0.779	0.325	0.293	0.737	0.168	0.851	0.458	0.672	0.573	0.670	0.085	0.050	0.355	0.067	0.515	0.617	0.000	0.294	0.740	0.311	0.336	0.375	0.667	0.710	0.000	0.286
translate_(0p1, -0p1)	0.721	0.457	0.400	0.757	0.840	0.737	0.917	0.529	0.594	0.290	0.745	0.763	0.612	0.454	0.491	0.622	0.594	0.713	0.611	0.646	0.842	0.792	0.910	0.863	0.099	0.679	0.069	0.069	0.585	0.162	0.215	0.104	0.035	0.594	0.122	0.000	0.351	0.531	0.353	0.304	0.423	0.194	0.408	0.244	0.183	0.409	0.668	0.114	0.530	0.493	0.580	0.292	0.556	0.560	0.739	0.368	0.364	0.741	0.357	0.790	0.531	0.699	0.642	0.683	0.086	0.092	0.436	0.150	0.431	0.625	0.000	0.379	0.777	0.306	0.455	0.408	0.500	0.737	0.000	0.273
translate_(-0p1, 0p1)	0.723	0.394	0.340	0.765	0.757	0.833	0.826	0.554	0.598	0.173	0.700	0.864	0.579	0.364	0.550	0.709	0.606	0.733	0.636	0.639	0.847	0.860	0.887	0.869	0.127	0.427	0.147	0.189	0.660	0.139	0.248	0.000	0.094	0.604	0.114	0.000	0.374	0.560	0.356	0.299	0.540	0.234	0.264	0.312	0.400	0.353	0.621	0.271	0.443	0.450	0.529	0.325	0.720	0.536	0.733	0.443	0.373	0.615	0.268	0.816	0.526	0.756	0.577	0.678	0.082	0.076	0.520	0.159	0.494	0.680	0.000	0.430	0.785	0.382	0.427	0.294	0.571	0.754	0.000	0.375
translate_(-0p1, -0p1)	0.749	0.541	0.458	0.788	0.861	0.822	0.878	0.574	0.604	0.376	0.716	0.816	0.750	0.497	0.551	0.781	0.689	0.755	0.627	0.689	0.874	0.853	0.927	0.863	0.123	0.679	0.160	0.259	0.688	0.404	0.277	0.182	0.150	0.602	0.196	0.065	0.390	0.603	0.540	0.339	0.546	0.263	0.268	0.252	0.357	0.382	0.678	0.267	0.567	0.577	0.633	0.462	0.722	0.647	0.698	0.460	0.470	0.655	0.366	0.848	0.578	0.805	0.678	0.747	0.219	0.018	0.519	0.247	0.396	0.603	0.000	0.519	0.753	0.398	0.591	0.378	0.400	0.773	0.000	0.462
translate_(0p1, 0)	0.695	0.431	0.302	0.756	0.765	0.759	0.892	0.458	0.512	0.164	0.736	0.651	0.661	0.361	0.475	0.608	0.584	0.734	0.568	0.655	0.838	0.793	0.909	0.855	0.103	0.557	0.115	0.074	0.538	0.072	0.184	0.000	0.035	0.559	0.119	0.000	0.301	0.442	0.349	0.238	0.423	0.226	0.435	0.252	0.134	0.350	0.556	0.240	0.413	0.340	0.500	0.236	0.605	0.535	0.741	0.370	0.328	0.746	0.280	0.816	0.467	0.604	0.551	0.734	0.101	0.044	0.451	0.111	0.441	0.661	0.000	0.349	0.707	0.323	0.403	0.379	0.667	0.699	0.000	0.353
translate_(-0p1, 0)	0.740	0.499	0.392	0.783	0.794	0.775	0.933	0.512	0.601	0.258	0.636	0.680	0.699	0.452	0.547	0.754	0.617	0.762	0.621	0.666	0.879	0.872	0.896	0.869	0.203	0.544	0.155	0.249	0.664	0.255	0.202	0.000	0.092	0.578	0.245	0.000	0.397	0.528	0.476	0.347	0.557	0.287	0.318	0.337	0.329	0.437	0.707	0.278	0.456	0.489	0.583	0.341	0.664	0.585	0.832	0.435	0.427	0.723	0.335	0.806	0.573	0.792	0.643	0.761	0.131	0.042	0.539	0.192	0.510	0.653	0.000	0.468	0.739	0.433	0.493	0.310	0.400	0.735	0.000	0.231
translate_(0, 0p1)	0.700	0.453	0.357	0.750	0.736	0.729	0.863	0.476	0.553	0.144	0.772	0.702	0.605	0.325	0.535	0.684	0.615	0.728	0.597	0.597	0.805	0.798	0.900	0.819	0.122	0.415	0.072	0.038	0.577	0.072	0.211	0.000	0.066	0.581	0.170	0.000	0.312	0.452	0.353	0.281	0.461	0.223	0.324	0.337	0.071	0.344	0.516	0.221	0.499	0.406	0.529	0.307	0.676	0.568	0.817	0.382	0.351	0.617	0.248	0.884	0.454	0.765	0.549	0.624	0.085	0.106	0.537	0.104	0.574	0.725	0.000	0.361	0.686	0.349	0.377	0.361	0.600	0.743	0.000	0.375
translate_(0, -0p1)	0.734	0.602	0.477	0.814	0.845	0.753	0.835	0.587	0.615	0.395	0.766	0.716	0.717	0.441	0.588	0.715	0.654	0.720	0.599	0.584	0.850	0.838	0.919	0.878	0.116	0.619	0.059	0.104	0.666	0.212	0.216	0.089	0.093	0.650	0.179	0.000	0.423	0.546	0.456	0.329	0.487	0.256	0.331	0.273	0.234	0.418	0.650	0.234	0.554	0.558	0.585	0.321	0.697	0.623	0.720	0.442	0.405	0.648	0.376	0.782	0.521	0.806	0.629	0.721	0.079	0.072	0.538	0.197	0.550	0.666	0.000	0.438	0.741	0.346	0.497	0.402	0.333	0.803	0.000	0.400
rotated_3	0.731	0.453	0.448	0.758	0.755	0.761	0.862	0.539	0.644	0.288	0.806	0.635	0.463	0.468	0.529	0.725	0.562	0.775	0.554	0.630	0.828	0.864	0.911	0.847	0.125	0.554	0.141	0.117	0.652	0.132	0.241	0.103	0.110	0.603	0.179	0.000	0.419	0.499	0.494	0.310	0.576	0.293	0.327	0.326	0.224	0.409	0.611	0.309	0.454	0.465	0.567	0.327	0.631	0.593	0.752	0.476	0.387	0.691	0.382	0.843	0.546	0.777	0.582	0.779	0.130	0.112	0.602	0.098	0.484	0.776	0.000	0.447	0.747	0.375	0.440	0.341	0.571	0.782	0.000	0.267
rotated_5	0.729	0.543	0.476	0.762	0.763	0.805	0.854	0.568	0.645	0.349	0.814	0.664	0.493	0.453	0.545	0.743	0.579	0.743	0.556	0.679	0.836	0.875	0.894	0.843	0.102	0.546	0.175	0.152	0.602	0.133	0.230	0.100	0.082	0.638	0.134	0.000	0.365	0.515	0.495	0.335	0.592	0.284	0.349	0.369	0.220	0.358	0.676	0.269	0.449	0.462	0.608	0.312	0.585	0.604	0.775	0.457	0.412	0.677	0.390	0.846	0.532	0.755	0.609	0.748	0.125	0.200	0.577	0.131	0.624	0.747	0.000	0.432	0.858	0.371	0.508	0.333	0.429	0.787	0.000	0.250
rotated_10	0.747	0.629	0.458	0.757	0.787	0.807	0.892	0.572	0.688	0.380	0.814	0.772	0.767	0.514	0.508	0.745	0.616	0.743	0.590	0.687	0.889	0.860	0.885	0.871	0.149	0.593	0.146	0.239	0.630	0.190	0.325	0.237	0.119	0.636	0.228	0.000	0.354	0.581	0.390	0.310	0.601	0.240	0.339	0.354	0.218	0.428	0.693	0.309	0.463	0.545	0.589	0.320	0.652	0.630	0.748	0.521	0.397	0.708	0.323	0.794	0.562	0.741	0.584	0.705	0.180	0.171	0.589	0.198	0.635	0.732	0.000	0.497	0.791	0.340	0.469	0.420	0.471	0.850	0.000	0.250
rotated_45	0.737	0.582	0.510	0.696	0.694	0.786	0.953	0.385	0.636	0.279	0.925	0.800	0.545	0.147	0.303	0.681	0.449	0.750	0.653	0.644	0.947	0.790	0.927	0.915	0.322	0.431	0.390	0.338	0.528	0.302	0.350	0.249	0.038	0.512	0.419	0.071	0.255	0.529	0.443	0.260	0.762	0.217	0.524	0.112	0.281	0.491	0.602	0.194	0.542	0.579	0.648	0.349	0.519	0.588	0.758	0.525	0.410	0.685	0.311	0.677	0.561	0.843	0.608	0.679	0.284	0.165	0.521	0.178	0.500	0.600	0.000	0.490	0.809	0.397	0.434	0.545	0.153	0.838	0.000	0.100
rotated_60	0.734	0.618	0.571	0.643	0.615	0.764	0.871	0.379	0.571	0.058	0.737	0.929	0.000	0.159	0.295	0.620	0.474	0.876	0.845	0.769	0.908	0.750	0.899	0.895	0.205	0.361	0.187	0.476	0.597	0.254	0.273	0.175	0.000	0.391	0.297	0.000	0.158	0.500	0.315	0.229	0.502	0.222	0.450	0.139	0.142	0.609	0.603	0.169	0.577	0.669	0.567	0.394	0.535	0.630	0.581	0.532	0.438	0.351	0.382	0.585	0.584	0.839	0.444	0.650	0.324	0.341	0.526	0.292	0.000	0.429	0.000	0.429	0.388	0.259	0.408	0.492	0.064	0.630	0.000	0.144
rotated_90	0.736	0.429	0.379	0.514	0.417	0.761	0.632	0.179	0.400	0.000	0.771	0.730	0.250	0.125	0.256	0.499	0.271	0.836	0.875	0.706	0.872	0.900	0.874	0.913	0.113	0.541	0.117	0.000	0.484	0.184	0.358	0.000	0.000	0.425	0.093	0.000	0.247	0.354	0.239	0.148	0.273	0.082	0.436	0.127	0.139	0.520	0.532	0.188	0.291	0.552	0.581	0.339	0.554	0.638	0.632	0.585	0.227	0.400	0.316	0.418	0.711	0.622	0.325	0.542	0.200	0.123	0.522	0.121	0.000	0.167	0.000	0.429	0.209	0.238	0.323	0.000	0.333	0.527	0.000	0.197
flipH	0.717	0.515	0.435	0.749	0.798	0.803	0.895	0.518	0.512	0.292	0.843	0.686	0.696	0.457	0.516	0.690	0.604	0.697	0.687	0.694	0.827	0.815	0.855	0.852	0.075	0.513	0.173	0.069	0.524	0.179	0.199	0.101	0.135	0.510	0.406	0.085	0.280	0.481	0.303	0.340	0.381	0.333	0.309	0.294	0.207	0.429	0.649	0.222	0.517	0.480	0.536	0.351	0.517	0.542	0.764	0.393	0.414	0.622	0.314	0.876	0.532	0.675	0.658	0.730	0.052	0.184	0.520	0.219	0.635	0.620	0.000	0.402	0.826	0.371	0.475	0.297	0.714	0.827	0.000	0.200
flipV	0.754	0.665	0.395	0.738	0.585	0.832	0.586	0.515	0.174	0.117	0.853	0.660	0.500	0.520	0.214	0.487	0.375	0.732	0.667	0.348	0.984	0.538	0.802	0.824	0.175	0.280	0.123	0.418	0.662	0.196	0.283	0.200	0.083	0.373	0.000	0.063	0.220	0.386	0.285	0.163	0.219	0.185	0.374	0.172	0.158	0.339	0.623	0.277	0.458	0.474	0.544	0.320	0.411	0.651	0.506	0.438	0.467	0.222	0.178	0.695	0.570	0.649	0.343	0.826	0.385	0.118	0.464	0.157	0.378	0.461	0.000	0.280	0.506	0.311	0.335	0.196	0.250	0.628	0.000	0.286
dropout	0.691	0.681	0.463	0.726	0.360	0.872	0.850	0.418	0.614	0.283	0.640	0.800	0.727	0.365	0.394	0.695	0.537	0.577	0.628	0.404	0.929	0.593	0.920	0.882	0.000	0.323	0.076	0.028	0.546	0.000	0.270	0.000	0.000	0.566	0.000	0.000	0.400	0.442	0.486	0.326	0.381	0.244	0.522	0.205	0.244	0.378	0.250	0.297	0.186	0.649	0.398	0.238	0.639	0.441	0.282	0.171	0.350	0.639	0.282	0.672	0.582	0.680	0.639	0.872	0.226	0.000	0.615	0.000	0.667	0.736	0.000	0.351	1.000	0.459	0.276	0.188	0.625	0.306	0.000	0.000

transform	person	bicycle	car	motorcycle	airplane	bus	train	truck	boat	traffic light	fire hydrant	stop sign	parking meter	bench	bird	cat	dog	horse	sheep	cow	elephant	bear	zebra	giraffe	backpack	umbrella	handbag	tie	suitcase	frisbee	skis	snowboard	sports ball	kite	baseball bat	baseball glove	skateboard	surfboard	tennis racket	bottle	wine glass	cup	fork	knife	spoon	bowl	banana	apple	sandwich	orange	broccoli	carrot	hot dog	pizza	donut	cake	chair	couch	potted plant	bed	dining table	toilet	tv	laptop	mouse	remote	keyboard	cell phone	microwave	oven	toaster	sink	refrigerator	book	clock	vase	scissors	teddy bear	hair drier	toothbrush
None	0.689	0.536	0.408	0.735	0.768	0.777	0.876	0.484	0.527	0.281	0.704	0.572	0.623	0.404	0.477	0.682	0.656	0.727	0.748	0.669	0.866	0.847	0.848	0.834	0.131	0.654	0.103	0.043	0.661	0.102	0.259	0.182	0.067	0.619	0.300	0.060	0.359	0.304	0.327	0.286	0.402	0.312	0.359	0.238	0.214	0.358	0.582	0.411	0.458	0.447	0.487	0.276	0.472	0.531	0.589	0.421	0.371	0.568	0.420	0.713	0.419	0.726	0.604	0.628	0.083	0.153	0.443	0.136	0.409	0.614	0.322	0.420	0.722	0.297	0.364	0.303	0.486	0.688	0.000	0.180
gaussianblur_1	0.716	0.511	0.464	0.753	0.744	0.812	0.892	0.518	0.578	0.268	0.726	0.665	0.584	0.382	0.449	0.692	0.513	0.730	0.574	0.577	0.804	0.836	0.919	0.859	0.198	0.536	0.155	0.047	0.600	0.079	0.198	0.000	0.097	0.588	0.176	0.000	0.367	0.482	0.398	0.324	0.553	0.275	0.353	0.347	0.217	0.386	0.562	0.258	0.309	0.520	0.530	0.293	0.647	0.520	0.647	0.387	0.375	0.622	0.325	0.790	0.389	0.790	0.567	0.696	0.112	0.165	0.481	0.142	0.465	0.721	0.000	0.380	0.674	0.375	0.411	0.306	0.258	0.752	0.000	0.251
gaussianblur_10	0.555	0.000	0.399	1.000	0.000	0.647	0.667	0.333	0.000	0.556	0.000	1.000	0.667	0.235	0.156	0.229	0.250	1.000	0.000	1.000	0.696	1.000	0.000	1.000	0.000	0.297	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.051	0.000	0.026	0.000	0.000	0.000	0.301	0.615	0.068	0.000	0.302	0.000	0.404	1.000	0.551	0.247	0.104	0.093	0.000	0.353	1.000	0.479	1.000	0.223	0.441	0.000	0.000	0.000	0.500	0.500	0.000	0.000	0.000	0.000	1.000	1.000	0.000	0.000	0.000	0.000	0.000
gaussianblur_20	0.431	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.429	1.000	0.000	0.000	0.267	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.087	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000
superpixels_0p1	0.717	0.319	0.406	0.765	0.751	0.742	0.747	0.232	0.178	0.110	0.501	0.585	0.691	0.249	0.519	0.623	0.435	0.847	0.615	0.525	0.765	0.762	0.916	1.000	0.000	0.378	0.253	0.000	0.471	0.167	0.000	0.000	0.000	0.254	0.000	0.000	0.343	0.490	0.402	0.214	0.629	0.278	0.802	0.198	0.270	0.445	0.716	0.352	0.476	0.607	0.374	0.283	0.619	0.428	0.332	0.135	0.281	0.740	0.216	0.728	0.411	0.796	0.324	0.579	0.500	0.083	0.395	0.074	0.330	0.577	0.000	0.279	0.399	0.391	0.480	0.241	0.000	0.796	0.000	0.000
superpixels_0p5	0.627	0.506	0.338	0.936	0.584	0.813	0.507	0.177	0.066	0.018	0.323	0.352	0.545	0.228	0.357	0.509	0.309	0.000	0.000	0.286	0.611	0.600	0.778	0.800	0.000	0.215	0.000	0.245	0.332	0.000	0.000	0.000	0.000	0.142	0.000	0.000	0.000	0.000	0.353	0.099	0.295	0.290	0.000	0.000	0.000	0.137	0.630	0.311	0.000	0.674	0.307	0.383	0.800	0.500	0.397	0.071	0.190	0.913	0.114	0.778	0.572	0.737	0.200	0.211	0.000	0.000	0.396	0.000	0.324	0.231	0.000	0.090	0.462	0.428	0.447	0.062	0.000	0.486	0.000	0.000
superpixels_0p85	0.583	0.000	0.164	0.000	0.429	0.000	0.439	0.145	0.000	0.003	0.130	0.219	0.000	0.115	0.093	0.000	0.000	0.000	0.000	0.000	0.000	0.000	1.000	0.000	0.000	0.153	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.198	0.000	0.000	0.000	0.000	1.000	0.061	0.000	0.333	0.000	0.000	0.000	0.000	0.000	0.000	0.000	1.000	0.226	0.000	0.000	0.000	0.267	0.128	0.107	0.000	0.163	0.000	0.000	1.000	0.129	0.000	0.000	0.000	0.500	0.000	0.222	0.000	0.000	0.000	1.000	0.333	0.111	0.000	0.000	0.300	0.000	0.000
colorspace_25	0.727	0.456	0.480	0.742	0.775	0.792	0.886	0.469	0.584	0.236	0.740	0.786	0.658	0.347	0.432	0.659	0.634	0.770	0.580	0.648	0.823	0.784	0.915	0.857	0.162	0.474	0.065	0.000	0.553	0.055	0.214	0.000	0.062	0.438	0.114	0.000	0.401	0.510	0.430	0.291	0.549	0.220	0.367	0.302	0.324	0.317	0.484	0.178	0.515	0.691	0.325	0.000	1.000	0.521	0.658	0.253	0.372	0.662	0.283	0.784	0.461	0.689	0.630	0.729	0.104	0.134	0.487	0.100	0.451	0.700	0.000	0.372	0.736	0.342	0.455	0.278	0.500	0.729	0.000	0.142
colorspace_50	0.737	0.451	0.461	0.774	0.744	0.796	0.863	0.486	0.573	0.261	0.702	0.730	0.648	0.285	0.472	0.695	0.612	0.690	0.570	0.666	0.819	0.672	0.914	0.848	0.171	0.450	0.045	0.000	0.482	0.050	0.207	0.000	0.103	0.487	0.085	0.000	0.387	0.452	0.408	0.281	0.556	0.218	0.338	0.272	0.308	0.361	0.658	0.240	0.625	0.817	0.298	0.000	0.000	0.499	0.747	0.198	0.380	0.693	0.258	0.737	0.447	0.708	0.608	0.742	0.091	0.088	0.473	0.125	0.660	0.729	0.000	0.378	0.778	0.364	0.445	0.296	0.615	0.726	0.000	0.161
averageblur_5_11	0.724	0.456	0.462	0.807	0.826	0.732	0.803	0.520	0.644	0.289	0.662	0.727	0.611	0.355	0.570	0.601	0.527	0.770	0.614	0.622	0.787	0.730	0.902	0.856	0.122	0.645	0.147	0.036	0.567	0.094	0.267	0.000	0.038	0.589	0.000	0.000	0.363	0.613	0.345	0.379	0.665	0.317	0.397	0.275	0.284	0.359	0.655	0.179	0.303	0.517	0.476	0.339	0.642	0.476	0.677	0.304	0.351	0.696	0.357	0.726	0.434	0.804	0.513	0.599	0.269	0.081	0.421	0.139	0.442	0.678	0.000	0.323	0.670	0.333	0.456	0.347	0.267	0.842	0.000	0.290
medianblur_1	0.694	0.657	0.448	0.772	0.809	0.764	0.718	0.543	0.588	0.249	0.716	0.649	0.858	0.424	0.301	0.673	0.446	0.702	0.700	0.491	0.762	0.729	0.955	0.878	0.160	0.502	0.123	0.067	0.532	0.032	0.207	0.000	0.050	0.378	0.000	0.000	0.377	0.480	0.388	0.361	0.589	0.244	0.454	0.250	0.234	0.364	0.497	0.319	0.472	0.610	0.500	0.287	0.572	0.454	0.562	0.303	0.359	0.724	0.397	0.657	0.435	0.733	0.473	0.726	0.165	0.108	0.456	0.077	0.466	0.579	0.000	0.353	0.638	0.297	0.568	0.266	0.333	0.710	0.000	0.188
sharpen_0	0.713	0.394	0.440	0.744	0.782	0.801	0.792	0.480	0.519	0.305	0.721	0.655	0.736	0.309	0.405	0.688	0.613	0.747	0.554	0.669	0.808	0.808	0.889	0.796	0.160	0.481	0.098	0.051	0.508	0.060	0.236	0.000	0.061	0.537	0.176	0.000	0.392	0.458	0.386	0.336	0.543	0.258	0.333	0.377	0.202	0.398	0.538	0.156	0.165	0.528	0.517	0.313	0.746	0.521	0.609	0.209	0.365	0.568	0.377	0.848	0.463	0.820	0.616	0.799	0.127	0.111	0.449	0.129	0.536	0.671	0.000	0.342	0.587	0.305	0.437	0.272	0.353	0.722	0.000	0.000
sharpen_1	0.712	0.477	0.433	0.777	0.856	0.756	0.828	0.443	0.526	0.294	0.666	0.678	0.677	0.365	0.463	0.669	0.595	0.670	0.574	0.681	0.811	0.875	0.887	0.815	0.174	0.499	0.107	0.000	0.499	0.076	0.213	0.000	0.079	0.643	0.208	0.000	0.408	0.511	0.439	0.342	0.546	0.290	0.301	0.358	0.207	0.386	0.554	0.219	0.383	0.493	0.540	0.246	0.721	0.486	0.637	0.292	0.384	0.616	0.363	0.768	0.465	0.785	0.590	0.749	0.169	0.219	0.432	0.092	0.687	0.738	0.000	0.374	0.644	0.318	0.451	0.285	0.327	0.757	0.000	0.194
sharpen_2	0.705	0.371	0.436	0.729	0.802	0.799	0.790	0.445	0.583	0.296	0.678	0.647	0.702	0.360	0.482	0.695	0.587	0.714	0.550	0.624	0.808	0.809	0.882	0.804	0.149	0.510	0.089	0.035	0.528	0.075	0.277	0.000	0.064	0.534	0.090	0.000	0.343	0.452	0.358	0.345	0.602	0.292	0.329	0.246	0.310	0.383	0.523	0.326	0.322	0.546	0.510	0.256	0.653	0.511	0.679	0.242	0.363	0.634	0.323	0.770	0.455	0.828	0.633	0.818	0.124	0.152	0.528	0.116	0.534	0.717	0.000	0.385	0.627	0.304	0.426	0.270	0.421	0.707	0.000	0.370
addintensity_-80	0.700	0.482	0.409	0.795	0.757	0.819	0.822	0.482	0.475	0.287	0.635	0.682	0.529	0.355	0.483	0.619	0.577	0.647	0.660	0.629	0.870	0.716	0.924	0.868	0.189	0.571	0.125	0.026	0.639	0.081	0.171	0.000	0.097	0.567	0.064	0.000	0.343	0.501	0.415	0.254	0.591	0.190	0.300	0.215	0.216	0.387	0.533	0.191	0.276	0.490	0.510	0.360	0.550	0.498	0.667	0.343	0.383	0.719	0.302	0.798	0.453	0.758	0.508	0.679	0.086	0.077	0.408	0.099	0.389	0.620	0.000	0.328	0.601	0.289	0.415	0.236	0.355	0.809	0.000	0.217
addintensity_80	0.717	0.511	0.442	0.785	0.761	0.767	0.825	0.472	0.553	0.319	0.709	0.625	0.691	0.362	0.503	0.691	0.551	0.729	0.645	0.618	0.775	0.821	0.913	0.836	0.149	0.481	0.123	0.093	0.570	0.061	0.175	0.000	0.116	0.536	0.072	0.069	0.410	0.493	0.466	0.321	0.537	0.253	0.353	0.234	0.280	0.363	0.566	0.268	0.410	0.584	0.549	0.273	0.410	0.507	0.626	0.350	0.383	0.499	0.324	0.766	0.403	0.768	0.616	0.764	0.143	0.137	0.474	0.139	0.391	0.767	0.000	0.342	0.694	0.341	0.444	0.290	0.337	0.780	0.000	0.062
elementrandomintensity_1	0.602	0.497	0.380	0.864	0.913	0.790	0.989	0.388	0.392	0.199	0.454	0.687	0.337	0.222	0.384	0.586	0.518	0.559	0.488	0.592	0.920	0.750	0.937	0.806	0.108	0.360	0.129	0.029	0.487	0.043	0.186	0.000	0.000	0.687	0.000	0.000	0.414	0.359	0.409	0.244	0.606	0.257	0.638	0.187	0.278	0.355	0.494	0.031	0.000	0.461	0.296	0.099	0.802	0.394	0.178	0.116	0.276	0.758	0.200	0.730	0.489	0.594	0.510	0.832	0.000	0.000	0.566	0.000	1.000	0.863	0.000	0.236	0.750	0.470	0.372	0.288	0.250	0.492	0.000	0.000
multiplyintensity_0p25	0.736	0.491	0.498	0.866	0.813	0.817	0.898	0.573	0.600	0.279	0.770	0.775	0.774	0.361	0.528	0.574	0.621	0.627	0.618	0.632	0.841	0.887	0.919	0.870	0.151	0.594	0.153	0.055	0.594	0.079	0.218	0.000	0.049	0.577	0.120	0.000	0.359	0.525	0.419	0.323	0.672	0.265	0.519	0.302	0.275	0.427	0.641	0.244	0.294	0.616	0.551	0.330	0.730	0.524	0.642	0.280	0.382	0.613	0.297	0.620	0.543	0.640	0.489	0.744	0.105	0.090	0.492	0.191	0.420	0.735	0.000	0.344	0.659	0.351	0.454	0.296	0.273	0.697	0.000	0.339
multiplyintensity_2	0.702	0.556	0.436	0.773	0.738	0.790	0.810	0.531	0.554	0.268	0.687	0.606	0.685	0.318	0.478	0.674	0.579	0.676	0.597	0.629	0.791	0.802	0.929	0.838	0.171	0.455	0.137	0.030	0.619	0.069	0.162	0.000	0.074	0.548	0.079	0.000	0.392	0.421	0.457	0.265	0.530	0.239	0.410	0.278	0.233	0.348	0.482	0.202	0.427	0.470	0.546	0.284	0.531	0.469	0.549	0.283	0.374	0.548	0.324	0.761	0.449	0.816	0.626	0.766	0.184	0.133	0.488	0.138	0.398	0.626	0.000	0.368	0.730	0.309	0.458	0.313	0.233	0.763	0.000	0.324
contrastnormalization_0	0.724	0.451	0.469	0.753	0.842	0.754	0.838	0.478	0.580	0.304	0.636	0.640	0.637	0.352	0.491	0.728	0.653	0.671	0.586	0.670	0.832	0.790	0.907	0.891	0.173	0.510	0.151	0.090	0.617	0.062	0.212	0.000	0.059	0.523	0.163	0.000	0.441	0.470	0.406	0.318	0.504	0.221	0.316	0.226	0.283	0.381	0.613	0.218	0.219	0.532	0.520	0.280	0.648	0.544	0.658	0.398	0.377	0.674	0.332	0.844	0.427	0.763	0.589	0.722	0.095	0.171	0.489	0.108	0.554	0.661	0.000	0.374	0.630	0.359	0.453	0.255	0.554	0.813	0.000	0.160
contrastnormalization_1	0.718	0.468	0.436	0.774	0.783	0.737	0.826	0.541	0.531	0.268	0.683	0.685	0.667	0.327	0.497	0.710	0.622	0.737	0.601	0.618	0.831	0.678	0.924	0.831	0.217	0.513	0.087	0.060	0.616	0.064	0.180	0.000	0.083	0.526	0.322	0.000	0.390	0.493	0.426	0.305	0.597	0.232	0.300	0.303	0.226	0.376	0.574	0.274	0.336	0.570	0.500	0.283	0.721	0.512	0.589	0.351	0.385	0.642	0.306	0.755	0.428	0.747	0.656	0.733	0.000	0.106	0.485	0.157	0.503	0.720	0.000	0.370	0.596	0.343	0.481	0.261	0.411	0.809	0.000	0.149
contrastnormalization_2	0.721	0.478	0.452	0.817	0.761	0.774	0.871	0.507	0.528	0.301	0.718	0.739	0.620	0.333	0.483	0.719	0.607	0.693	0.587	0.635	0.862	0.756	0.917	0.816	0.197	0.468	0.195	0.092	0.616	0.072	0.200	0.000	0.084	0.565	0.200	0.000	0.399	0.494	0.439	0.271	0.542	0.236	0.292	0.267	0.286	0.354	0.519	0.207	0.240	0.562	0.513	0.302	0.512	0.506	0.641	0.319	0.400	0.610	0.308	0.780	0.414	0.778	0.628	0.741	0.158	0.144	0.510	0.125	0.659	0.818	0.000	0.376	0.587	0.312	0.460	0.264	0.410	0.803	0.000	0.195
elastic_1	0.546	0.000	0.269	0.000	0.000	0.563	1.000	0.596	0.176	0.207	0.282	0.719	0.550	0.181	1.000	0.491	0.304	0.386	0.615	0.364	0.515	0.388	0.778	0.900	0.000	0.349	0.000	0.000	0.000	0.050	0.143	0.000	0.000	0.341	0.000	0.000	0.000	0.179	0.500	0.608	1.000	0.390	0.000	0.000	1.000	0.423	0.714	0.160	0.000	0.443	0.263	0.272	1.000	0.627	0.227	0.100	0.280	1.000	0.108	0.500	0.594	0.721	0.551	1.000	0.000	1.000	0.000	0.000	0.000	0.000	0.000	0.286	0.000	0.000	0.000	0.571	0.000	0.584	0.000	0.000
scaled_1p25	0.752	0.506	0.481	0.753	0.802	0.837	0.929	0.548	0.570	0.379	0.682	0.831	0.726	0.365	0.592	0.784	0.672	0.768	0.653	0.653	0.882	0.775	0.935	0.958	0.185	0.617	0.133	0.250	0.743	0.401	0.350	0.086	0.188	0.601	0.360	0.000	0.448	0.561	0.474	0.328	0.539	0.304	0.342	0.379	0.229	0.338	0.727	0.248	0.442	0.534	0.595	0.458	0.552	0.635	0.587	0.549	0.355	0.564	0.349	0.667	0.505	0.775	0.696	0.703	0.202	0.019	0.476	0.201	0.423	0.640	0.000	0.532	0.650	0.434	0.580	0.210	0.269	0.839	0.000	0.143
scaled_0p75	0.610	0.440	0.217	0.680	0.737	0.725	0.924	0.465	0.409	0.129	0.602	0.639	0.533	0.296	0.502	0.605	0.574	0.669	0.449	0.576	0.769	0.811	0.834	0.810	0.035	0.488	0.035	0.000	0.515	0.000	0.182	0.000	0.000	0.536	0.000	0.000	0.257	0.325	0.071	0.162	0.229	0.092	0.147	0.181	0.043	0.214	0.560	0.161	0.376	0.278	0.347	0.307	0.460	0.450	0.610	0.317	0.246	0.621	0.198	0.709	0.379	0.575	0.452	0.657	0.090	0.062	0.292	0.032	0.199	0.541	0.000	0.161	0.699	0.229	0.326	0.130	0.571	0.710	0.000	0.149
scaled_0p5	0.484	0.348	0.138	0.602	0.557	0.571	0.783	0.439	0.209	0.053	0.466	0.396	0.561	0.282	0.331	0.566	0.415	0.553	0.395	0.476	0.625	0.640	0.684	0.687	0.027	0.369	0.000	0.000	0.444	0.000	0.068	0.000	0.000	0.288	0.000	0.000	0.018	0.252	0.023	0.128	0.115	0.043	0.093	0.000	0.094	0.151	0.467	0.184	0.284	0.143	0.164	0.092	0.326	0.369	0.370	0.342	0.123	0.392	0.132	0.700	0.422	0.396	0.258	0.477	0.000	0.053	0.038	0.085	0.382	0.386	0.000	0.118	0.621	0.124	0.216	0.239	0.750	0.519	0.000	0.353
scaled_(1p25, 1p0)	0.750	0.593	0.423	0.726	0.821	0.814	0.885	0.534	0.573	0.320	0.708	0.644	0.600	0.354	0.514	0.792	0.604	0.772	0.631	0.707	0.901	0.863	0.904	0.946	0.241	0.558	0.178	0.199	0.644	0.200	0.253	0.082	0.118	0.549	0.214	0.000	0.434	0.491	0.406	0.342	0.670	0.273	0.333	0.374	0.302	0.399	0.679	0.223	0.506	0.507	0.611	0.353	0.662	0.470	0.681	0.479	0.362	0.605	0.312	0.707	0.436	0.798	0.654	0.733	0.188	0.162	0.437	0.135	0.451	0.698	0.000	0.454	0.695	0.424	0.462	0.266	0.227	0.772	0.000	0.156
scaled_(0p75, 1p0)	0.660	0.507	0.275	0.692	0.776	0.722	0.871	0.482	0.509	0.144	0.685	0.652	0.727	0.371	0.525	0.677	0.539	0.692	0.506	0.659	0.772	0.784	0.886	0.796	0.059	0.509	0.074	0.087	0.548	0.000	0.187	0.000	0.066	0.514	0.137	0.000	0.302	0.453	0.302	0.226	0.453	0.155	0.269	0.189	0.106	0.315	0.507	0.302	0.308	0.354	0.452	0.305	0.635	0.544	0.627	0.327	0.267	0.616	0.264	0.771	0.396	0.638	0.552	0.692	0.104	0.069	0.393	0.075	0.556	0.612	0.000	0.263	0.652	0.221	0.327	0.245	0.500	0.746	0.000	0.203
scaled_(1p0, 1p25)	0.727	0.529	0.480	0.768	0.823	0.815	0.880	0.535	0.641	0.407	0.693	0.699	0.736	0.421	0.515	0.777	0.636	0.691	0.606	0.670	0.832	0.800	0.928	0.882	0.197	0.586	0.149	0.120	0.710	0.181	0.264	0.086	0.106	0.637	0.253	0.000	0.408	0.554	0.390	0.287	0.537	0.235	0.276	0.325	0.257	0.391	0.681	0.298	0.460	0.473	0.582	0.341	0.553	0.591	0.595	0.391	0.350	0.555	0.366	0.729	0.542	0.737	0.656	0.711	0.074	0.122	0.510	0.188	0.726	0.719	0.000	0.475	0.716	0.351	0.519	0.262	0.211	0.847	0.000	0.240
scaled_(1p0, 0p75)	0.685	0.511	0.347	0.720	0.702	0.785	0.858	0.569	0.482	0.187	0.690	0.622	0.577	0.359	0.465	0.663	0.669	0.764	0.559	0.670	0.825	0.853	0.831	0.815	0.124	0.418	0.077	0.033	0.606	0.074	0.165	0.000	0.067	0.541	0.073	0.058	0.293	0.390	0.287	0.253	0.440	0.186	0.288	0.196	0.183	0.273	0.498	0.200	0.309	0.478	0.430	0.291	0.534	0.426	0.514	0.402	0.339	0.558	0.330	0.686	0.388	0.699	0.527	0.661	0.097	0.087	0.446	0.087	0.210	0.690	0.000	0.339	0.681	0.282	0.378	0.274	0.444	0.703	0.000	0.182
translate_(0p1, 0p1)	0.668	0.316	0.280	0.693	0.744	0.776	0.899	0.465	0.504	0.132	0.771	0.676	0.597	0.292	0.487	0.608	0.613	0.688	0.531	0.615	0.819	0.788	0.880	0.872	0.021	0.489	0.029	0.065	0.575	0.065	0.174	0.000	0.086	0.575	0.116	0.000	0.295	0.397	0.273	0.179	0.291	0.133	0.286	0.244	0.083	0.320	0.516	0.255	0.395	0.319	0.392	0.310	0.614	0.518	0.642	0.328	0.273	0.628	0.216	0.738	0.440	0.664	0.507	0.632	0.090	0.062	0.417	0.033	0.472	0.634	0.000	0.259	0.683	0.296	0.312	0.205	0.385	0.706	0.000	0.214
translate_(0p1, -0p1)	0.708	0.493	0.399	0.720	0.853	0.789	0.901	0.490	0.624	0.327	0.760	0.709	0.611	0.381	0.495	0.689	0.648	0.635	0.589	0.659	0.863	0.800	0.916	0.898	0.141	0.661	0.096	0.098	0.589	0.127	0.202	0.088	0.067	0.597	0.220	0.000	0.388	0.524	0.343	0.261	0.413	0.204	0.362	0.212	0.251	0.372	0.588	0.176	0.457	0.444	0.547	0.308	0.613	0.608	0.672	0.345	0.300	0.568	0.365	0.733	0.416	0.660	0.594	0.700	0.095	0.094	0.387	0.138	0.545	0.687	0.000	0.406	0.598	0.364	0.393	0.328	0.308	0.793	0.000	0.259
translate_(-0p1, 0p1)	0.716	0.484	0.353	0.795	0.801	0.804	0.917	0.536	0.580	0.173	0.709	0.737	0.635	0.324	0.520	0.732	0.593	0.764	0.607	0.668	0.844	0.924	0.885	0.863	0.138	0.508	0.146	0.213	0.720	0.116	0.206	0.000	0.129	0.625	0.068	0.000	0.384	0.502	0.408	0.315	0.539	0.197	0.220	0.313	0.290	0.312	0.565	0.270	0.361	0.443	0.505	0.330	0.717	0.539	0.698	0.477	0.359	0.594	0.302	0.802	0.433	0.789	0.533	0.674	0.155	0.110	0.395	0.126	0.488	0.601	0.000	0.356	0.776	0.413	0.386	0.185	0.309	0.770	0.000	0.195
translate_(-0p1, -0p1)	0.751	0.480	0.444	0.785	0.841	0.827	0.919	0.570	0.617	0.435	0.703	0.827	0.837	0.417	0.572	0.841	0.710	0.761	0.619	0.709	0.884	0.921	0.932	0.898	0.203	0.608	0.183	0.231	0.716	0.409	0.275	0.166	0.161	0.664	0.291	0.065	0.402	0.555	0.459	0.320	0.554	0.277	0.270	0.351	0.351	0.424	0.707	0.290	0.522	0.527	0.610	0.415	0.763	0.624	0.653	0.539	0.408	0.645	0.374	0.804	0.452	0.778	0.689	0.721	0.128	0.067	0.527	0.167	0.549	0.709	0.000	0.486	0.721	0.412	0.554	0.241	0.263	0.782	0.000	0.155
translate_(0p1, 0)	0.687	0.462	0.326	0.744	0.769	0.780	0.886	0.469	0.556	0.199	0.726	0.652	0.585	0.353	0.488	0.651	0.582	0.735	0.544	0.637	0.853	0.827	0.907	0.858	0.078	0.536	0.081	0.065	0.542	0.068	0.208	0.000	0.077	0.579	0.112	0.000	0.338	0.429	0.327	0.216	0.466	0.195	0.386	0.260	0.234	0.328	0.551	0.186	0.431	0.366	0.435	0.282	0.604	0.536	0.715	0.303	0.293	0.608	0.294	0.722	0.384	0.673	0.572	0.693	0.079	0.103	0.375	0.086	0.467	0.670	0.000	0.360	0.639	0.324	0.385	0.230	0.187	0.743	0.000	0.233
translate_(-0p1, 0)	0.731	0.563	0.374	0.808	0.840	0.793	0.881	0.523	0.580	0.316	0.709	0.680	0.641	0.359	0.545	0.801	0.633	0.817	0.608	0.739	0.846	0.913	0.928	0.893	0.201	0.535	0.169	0.206	0.711	0.233	0.203	0.081	0.080	0.603	0.235	0.000	0.445	0.545	0.448	0.380	0.594	0.269	0.307	0.340	0.269	0.374	0.669	0.320	0.517	0.520	0.567	0.351	0.705	0.535	0.751	0.476	0.386	0.631	0.318	0.800	0.429	0.804	0.620	0.749	0.130	0.110	0.417	0.156	0.426	0.756	0.000	0.450	0.709	0.389	0.486	0.196	0.234	0.760	0.000	0.187
translate_(0, 0p1)	0.693	0.427	0.355	0.770	0.772	0.783	0.836	0.503	0.556	0.153	0.759	0.605	0.662	0.323	0.480	0.698	0.576	0.715	0.616	0.631	0.824	0.863	0.905	0.829	0.130	0.424	0.077	0.062	0.606	0.067	0.178	0.000	0.102	0.576	0.127	0.063	0.336	0.504	0.361	0.235	0.438	0.221	0.276	0.272	0.185	0.340	0.504	0.194	0.387	0.440	0.501	0.273	0.594	0.528	0.698	0.397	0.341	0.587	0.308	0.750	0.446	0.730	0.530	0.693	0.159	0.164	0.466	0.099	0.436	0.664	0.000	0.341	0.611	0.327	0.351	0.331	0.345	0.761	0.000	0.203
translate_(0, -0p1)	0.726	0.548	0.473	0.778	0.837	0.810	0.856	0.548	0.623	0.415	0.724	0.726	0.659	0.440	0.550	0.765	0.657	0.694	0.585	0.676	0.845	0.865	0.917	0.889	0.189	0.579	0.146	0.089	0.646	0.184	0.214	0.087	0.112	0.651	0.214	0.053	0.416	0.556	0.406	0.302	0.491	0.249	0.286	0.330	0.422	0.351	0.646	0.212	0.437	0.576	0.603	0.308	0.734	0.595	0.616	0.486	0.411	0.585	0.383	0.796	0.440	0.742	0.610	0.717	0.079	0.100	0.517	0.225	0.595	0.646	0.000	0.440	0.644	0.335	0.500	0.352	0.357	0.760	0.000	0.215
rotated_3	0.724	0.584	0.457	0.793	0.779	0.831	0.889	0.534	0.624	0.287	0.751	0.675	0.652	0.389	0.560	0.740	0.620	0.752	0.588	0.646	0.868	0.784	0.908	0.892	0.171	0.539	0.192	0.138	0.682	0.068	0.268	0.094	0.114	0.650	0.159	0.000	0.429	0.532	0.420	0.295	0.531	0.284	0.328	0.342	0.231	0.389	0.592	0.269	0.375	0.441	0.559	0.325	0.642	0.556	0.642	0.487	0.379	0.605	0.340	0.744	0.449	0.751	0.605	0.746	0.179	0.194	0.472	0.119	0.506	0.670	0.000	0.361	0.668	0.328	0.443	0.229	0.278	0.790	0.000	0.174
rotated_5	0.720	0.614	0.451	0.782	0.844	0.702	0.850	0.522	0.677	0.369	0.752	0.685	0.646	0.378	0.536	0.734	0.613	0.729	0.591	0.654	0.810	0.804	0.908	0.898	0.157	0.532	0.169	0.132	0.648	0.142	0.309	0.259	0.103	0.660	0.199	0.000	0.379	0.512	0.446	0.313	0.587	0.272	0.303	0.347	0.266	0.376	0.641	0.275	0.331	0.540	0.550	0.342	0.586	0.579	0.659	0.485	0.380	0.557	0.384	0.760	0.490	0.730	0.565	0.748	0.172	0.175	0.525	0.162	0.640	0.795	0.000	0.371	0.741	0.338	0.443	0.297	0.410	0.774	0.000	0.209
rotated_10	0.732	0.614	0.443	0.768	0.801	0.778	0.878	0.554	0.634	0.408	0.731	0.644	0.753	0.332	0.554	0.774	0.645	0.732	0.591	0.723	0.840	0.772	0.899	0.879	0.204	0.574	0.131	0.146	0.697	0.181	0.376	0.216	0.117	0.584	0.144	0.059	0.376	0.573	0.457	0.296	0.559	0.289	0.358	0.363	0.337	0.388	0.711	0.238	0.482	0.483	0.572	0.333	0.632	0.595	0.716	0.512	0.374	0.716	0.342	0.749	0.533	0.788	0.571	0.675	0.191	0.150	0.569	0.174	0.604	0.757	0.000	0.469	0.721	0.389	0.480	0.374	0.412	0.818	0.000	0.155
rotated_45	0.720	0.566	0.491	0.635	0.724	0.763	0.896	0.302	0.648	0.383	0.854	0.821	1.000	0.291	0.447	0.716	0.497	0.777	0.602	0.830	0.949	0.783	0.921	0.918	0.160	0.307	0.305	0.356	0.599	0.261	0.379	0.193	0.106	0.477	0.316	0.177	0.299	0.556	0.408	0.306	0.682	0.228	0.498	0.121	0.171	0.540	0.622	0.278	0.451	0.527	0.590	0.366	0.669	0.540	0.572	0.471	0.324	0.599	0.148	0.633	0.436	0.894	0.481	0.686	0.230	0.170	0.522	0.173	0.000	0.684	0.000	0.439	0.768	0.337	0.401	0.309	0.103	0.819	0.000	0.074
rotated_60	0.735	0.485	0.529	0.515	0.583	0.696	0.792	0.258	0.455	0.147	0.933	0.994	0.000	0.356	0.319	0.605	0.390	0.955	0.838	0.724	0.960	0.736	0.900	0.872	0.173	0.313	0.139	0.397	0.506	0.301	0.287	0.072	0.070	0.431	0.395	0.104	0.253	0.555	0.393	0.297	0.576	0.162	0.521	0.116	0.132	0.463	0.606	0.238	0.527	0.597	0.581	0.399	0.488	0.564	0.563	0.425	0.296	0.477	0.290	0.526	0.495	0.803	0.360	0.652	0.436	0.191	0.540	0.169	0.000	0.429	0.000	0.346	0.298	0.268	0.387	0.418	0.120	0.745	0.000	0.048
rotated_90	0.715	0.420	0.260	0.615	0.429	0.657	0.705	0.408	0.333	0.089	0.769	0.596	0.400	0.108	0.273	0.472	0.335	1.000	0.621	0.636	0.898	0.675	0.869	0.869	0.133	0.404	0.104	0.211	0.536	0.261	0.283	0.000	0.000	0.371	0.000	0.069	0.136	0.429	0.234	0.174	0.222	0.144	0.446	0.119	0.203	0.488	0.548	0.343	0.414	0.601	0.532	0.339	0.564	0.717	0.494	0.529	0.264	0.328	0.230	0.303	0.584	0.610	0.278	0.529	0.000	0.131	0.558	0.183	0.000	0.115	0.000	0.161	0.269	0.170	0.321	0.079	0.444	0.668	0.000	0.131
flipH	0.707	0.504	0.444	0.742	0.810	0.819	0.866	0.536	0.505	0.306	0.798	0.635	0.648	0.458	0.498	0.678	0.616	0.657	0.667	0.772	0.838	0.746	0.859	0.874	0.107	0.537	0.125	0.087	0.514	0.122	0.174	0.047	0.138	0.610	0.295	0.066	0.255	0.513	0.327	0.304	0.495	0.322	0.349	0.316	0.229	0.394	0.663	0.256	0.566	0.540	0.495	0.388	0.461	0.533	0.621	0.353	0.410	0.541	0.302	0.786	0.487	0.644	0.674	0.653	0.166	0.184	0.450	0.151	0.402	0.654	0.000	0.397	0.694	0.373	0.426	0.204	0.620	0.773	0.000	0.167
flipV	0.710	0.650	0.314	0.620	0.621	0.803	0.629	0.407	0.276	0.124	0.770	0.672	0.615	0.312	0.208	0.425	0.343	0.635	1.000	0.675	1.000	0.500	0.803	0.801	0.104	0.271	0.032	0.199	0.474	0.237	0.547	0.370	0.097	0.392	0.000	0.000	0.276	0.404	0.341	0.115	0.267	0.175	0.375	0.228	0.264	0.341	0.600	0.159	0.405	0.522	0.512	0.418	0.611	0.591	0.716	0.508	0.339	0.569	0.165	0.643	0.562	0.603	0.377	0.602	0.375	0.206	0.439	0.159	0.399	0.493	0.000	0.377	0.442	0.269	0.348	0.172	0.145	0.601	0.000	0.270
dropout	0.643	0.527	0.449	0.782	0.989	0.768	0.867	0.409	0.503	0.259	0.435	0.658	0.409	0.253	0.303	0.495	0.498	0.701	0.517	0.606	0.882	0.679	0.910	0.852	0.078	0.334	0.083	0.082	0.557	0.084	0.195	0.000	0.000	0.620	0.000	0.000	0.343	0.408	0.465	0.337	0.588	0.226	0.472	0.297	0.259	0.348	0.527	0.273	0.364	0.576	0.390	0.284	0.784	0.522	0.273	0.210	0.333	0.661	0.227	0.664	0.485	0.531	0.558	0.829	0.194	0.093	0.561	0.000	0.444	0.753	0.000	0.295	0.540	0.360	0.353	0.216	0.250	0.480	0.000	0.000

transform	person	bicycle	car	motorcycle	airplane	bus	train	truck	boat	traffic light	fire hydrant	stop sign	parking meter	bench	bird	cat	dog	horse	sheep	cow	elephant	bear	zebra	giraffe	backpack	umbrella	handbag	tie	suitcase	frisbee	skis	snowboard	sports ball	kite	baseball bat	baseball glove	skateboard	surfboard	tennis racket	bottle	wine glass	cup	fork	knife	spoon	bowl	banana	apple	sandwich	orange	broccoli	carrot	hot dog	pizza	donut	cake	chair	couch	potted plant	bed	dining table	toilet	tv	laptop	mouse	remote	keyboard	cell phone	microwave	oven	toaster	sink	refrigerator	book	clock	vase	scissors	teddy bear	hair drier	toothbrush
None	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000
gaussianblur_1	0.019	0.003	0.036	0.050	-0.030	-0.027	-0.040	0.050	0.015	0.053	0.017	0.109	-0.089	-0.149	0.053	0.021	-0.102	-0.047	-0.107	-0.007	-0.018	-0.066	0.053	0.017	-0.030	-0.055	0.092	0.051	-0.001	-0.041	-0.087	-0.107	0.001	-0.001	-0.247	-0.058	0.081	0.172	0.086	0.056	0.156	-0.045	-0.009	-0.010	-0.228	0.074	0.056	-0.116	-0.255	0.125	0.020	0.028	0.018	-0.006	-0.034	-0.060	-0.000	0.103	-0.087	0.073	0.061	0.068	0.008	0.068	0.080	-0.026	0.065	-0.018	-0.017	0.108	-0.229	-0.083	0.012	0.082	0.097	0.001	0.038	0.098	0.000	0.031
gaussianblur_10	0.034	-0.525	0.002	-0.720	-0.779	-0.045	-0.365	-0.486	-0.531	0.228	-0.057	0.154	-0.356	-0.418	0.508	-0.432	-0.416	-0.085	-0.649	-0.105	-0.089	-0.816	-0.872	0.142	-0.140	-0.403	-0.097	-0.040	-0.656	-0.109	-0.306	-0.107	-0.066	-0.579	-0.247	-0.058	-0.315	-0.307	-0.392	-0.163	-0.238	-0.198	-0.422	-0.226	-0.228	0.027	0.224	-0.308	-0.540	-0.190	0.471	0.195	0.234	0.061	-0.412	-0.022	-0.132	-0.628	-0.395	0.246	-0.005	0.256	-0.364	0.072	0.030	-0.141	-0.464	-0.157	-0.216	-0.607	-0.229	-0.443	-0.295	-0.324	-0.387	-0.312	-0.562	-0.718	0.000	0.770
gaussianblur_20	-0.178	-0.525	-0.414	-0.720	-0.779	-0.745	-0.852	-0.486	-0.531	-0.272	-0.723	-0.596	-0.689	-0.418	-0.492	-0.655	-0.624	-0.751	-0.649	-0.605	-0.867	-0.816	-0.872	-0.858	-0.140	-0.585	-0.097	-0.040	-0.656	-0.109	-0.306	-0.107	-0.066	-0.579	-0.247	-0.058	-0.315	-0.307	-0.392	-0.266	-0.353	-0.298	-0.422	-0.226	-0.228	-0.390	0.412	-0.386	-0.540	-0.262	-0.529	-0.305	-0.566	-0.550	-0.626	-0.438	-0.382	-0.628	-0.395	-0.754	-0.466	-0.744	-0.562	-0.642	-0.095	-0.141	-0.464	-0.157	-0.466	-0.607	-0.229	-0.443	-0.795	-0.324	-0.387	-0.312	-0.562	-0.718	0.000	-0.230
superpixels_0p1	-0.024	0.278	-0.153	-0.024	0.004	0.005	-0.214	-0.186	-0.393	-0.216	-0.409	0.045	-0.537	-0.124	-0.049	0.008	-0.200	0.087	-0.170	-0.280	-0.144	-0.166	0.122	0.142	-0.140	-0.201	-0.097	-0.040	-0.207	0.105	-0.139	-0.107	0.054	-0.258	-0.247	-0.058	-0.161	0.693	-0.046	-0.036	0.033	-0.061	-0.422	-0.026	-0.228	-0.011	0.202	-0.286	0.038	0.146	-0.175	-0.016	-0.021	0.037	-0.348	-0.289	-0.069	0.372	-0.080	0.135	0.024	0.194	-0.285	0.160	-0.095	-0.141	-0.131	0.013	-0.133	0.048	-0.229	-0.119	-0.345	0.060	0.167	0.013	-0.562	-0.131	0.000	-0.230
superpixels_0p5	-0.087	-0.525	-0.245	-0.083	-0.050	0.022	-0.476	-0.233	-0.485	-0.255	-0.507	-0.168	-0.590	-0.190	-0.150	-0.030	-0.376	-0.323	-0.296	-0.483	-0.049	0.184	-0.277	0.142	-0.140	-0.415	-0.097	-0.040	-0.591	-0.109	-0.306	-0.107	-0.066	-0.290	-0.247	-0.058	-0.259	-0.307	-0.392	-0.149	-0.353	-0.117	-0.422	0.084	-0.228	0.010	0.012	-0.328	-0.540	-0.156	-0.201	0.105	-0.566	0.171	-0.410	-0.381	-0.250	0.372	-0.362	-0.754	-0.171	0.151	-0.352	0.206	-0.095	-0.141	-0.227	-0.157	-0.038	-0.313	-0.229	-0.243	-0.344	0.426	0.309	-0.234	-0.562	-0.364	0.000	-0.230
superpixels_0p85	-0.182	-0.525	-0.303	0.280	-0.643	-0.745	-0.352	-0.343	-0.512	-0.268	-0.615	-0.271	-0.689	-0.418	-0.221	0.345	-0.624	0.249	-0.649	-0.605	-0.867	0.184	0.128	-0.858	-0.140	-0.484	-0.097	-0.040	-0.656	-0.109	-0.306	-0.107	-0.066	-0.437	-0.247	-0.058	-0.315	-0.307	0.008	-0.224	-0.153	-0.157	-0.422	-0.226	-0.228	-0.390	-0.588	-0.428	-0.540	-0.028	-0.129	0.029	-0.566	-0.550	-0.626	-0.391	-0.382	-0.628	-0.306	-0.754	-0.466	-0.744	-0.408	-0.642	-0.095	-0.141	-0.464	-0.157	-0.466	0.393	-0.229	-0.443	0.038	-0.324	-0.387	-0.312	-0.562	-0.318	0.000	-0.230
colorspace_25	0.035	-0.088	0.061	0.030	-0.010	0.008	0.032	0.008	0.105	-0.030	-0.041	0.253	-0.050	-0.157	-0.055	-0.065	-0.093	-0.026	-0.112	-0.108	0.017	-0.069	0.025	0.008	0.014	-0.081	0.048	-0.040	-0.067	-0.072	-0.091	-0.107	-0.032	-0.081	-0.247	-0.058	0.004	0.223	0.065	0.008	0.219	-0.065	0.010	-0.046	-0.178	-0.032	-0.158	-0.190	0.032	0.125	-0.266	-0.305	0.434	0.048	0.030	-0.162	-0.021	0.023	-0.122	0.046	0.051	0.127	-0.056	0.130	0.031	-0.002	-0.067	-0.017	-0.040	0.155	-0.229	-0.038	0.009	0.044	0.100	-0.041	0.238	0.032	0.000	0.010
colorspace_50	0.049	-0.074	0.034	0.043	0.019	-0.002	-0.011	-0.015	0.037	-0.049	-0.049	0.184	0.035	-0.200	-0.039	-0.034	-0.117	-0.068	-0.118	-0.103	0.007	-0.172	0.048	0.008	0.038	-0.119	0.034	0.022	-0.084	-0.061	-0.065	-0.107	-0.020	-0.033	-0.247	-0.058	-0.007	0.295	-0.006	-0.003	0.176	-0.088	0.015	0.036	-0.105	0.005	0.057	-0.014	-0.540	0.572	-0.198	-0.305	0.434	0.055	0.206	-0.228	-0.033	0.112	-0.181	0.032	0.098	-0.008	-0.050	0.054	0.024	-0.141	-0.033	-0.035	0.226	0.249	-0.229	-0.009	-0.085	0.050	0.126	0.008	0.105	-0.042	0.000	-0.230
averageblur_5_11	0.037	-0.063	0.052	0.114	-0.002	0.023	-0.082	0.165	-0.010	0.040	0.005	0.076	-0.214	-0.124	-0.077	-0.198	-0.053	-0.080	-0.235	-0.085	-0.072	-0.061	0.065	0.046	-0.085	-0.034	0.127	0.034	-0.062	0.027	-0.002	-0.107	0.013	-0.038	-0.247	-0.058	0.119	0.299	-0.006	0.129	0.078	-0.098	0.045	0.028	-0.060	0.064	0.070	-0.206	-0.061	0.060	-0.043	0.033	0.127	-0.066	0.099	0.012	-0.043	0.227	-0.095	0.170	0.047	0.090	-0.076	0.058	0.128	-0.141	0.011	0.079	-0.113	0.145	-0.229	0.086	0.050	0.090	0.278	-0.023	-0.228	0.125	0.000	0.123
medianblur_1	0.005	0.161	0.051	0.126	-0.058	0.031	-0.151	0.107	-0.003	-0.049	0.090	0.121	-0.057	0.024	-0.138	-0.044	-0.183	-0.064	-0.170	-0.076	-0.090	-0.061	0.060	0.027	-0.100	-0.077	0.033	0.059	-0.149	-0.027	-0.075	-0.107	0.024	-0.152	-0.247	-0.058	0.107	0.250	0.043	0.102	0.095	-0.063	0.069	0.014	-0.228	0.067	0.003	-0.208	0.070	0.090	0.029	-0.020	0.157	-0.059	-0.088	-0.027	-0.020	0.140	-0.065	0.124	0.091	0.065	-0.074	0.125	0.027	-0.051	0.166	0.026	0.172	0.171	-0.229	-0.061	-0.189	0.088	0.311	-0.056	-0.062	-0.013	0.000	-0.017
sharpen_0	0.005	-0.182	-0.024	-0.042	-0.004	0.028	0.001	0.052	-0.056	-0.020	0.036	0.165	-0.042	-0.121	-0.119	-0.071	-0.022	-0.103	-0.144	0.083	-0.038	-0.035	-0.011	-0.101	0.005	-0.187	0.028	-0.038	-0.162	-0.031	-0.108	-0.107	-0.010	-0.137	-0.247	-0.058	0.015	0.221	-0.034	0.083	0.231	-0.042	-0.008	0.090	-0.228	-0.009	-0.154	-0.189	-0.332	0.181	0.057	0.037	0.196	-0.079	0.158	-0.258	-0.031	0.019	-0.033	0.002	0.060	0.063	-0.000	0.062	0.043	-0.076	0.096	-0.020	0.096	0.042	-0.229	-0.070	0.051	-0.016	0.009	-0.080	0.238	-0.062	0.000	-0.230
sharpen_1	0.014	-0.127	-0.016	0.016	0.005	-0.039	-0.056	0.029	-0.098	-0.032	0.033	0.107	-0.075	-0.136	-0.090	-0.060	-0.030	-0.080	-0.124	-0.031	-0.019	0.010	-0.023	-0.127	0.001	-0.147	-0.023	0.006	-0.194	-0.028	-0.088	-0.107	-0.012	-0.123	-0.247	-0.058	-0.014	0.207	-0.026	0.013	0.125	-0.050	0.058	0.126	-0.169	0.024	-0.187	0.033	0.020	0.216	0.001	0.183	0.340	-0.102	0.027	-0.265	-0.025	0.074	-0.080	0.010	0.048	0.048	-0.048	0.079	0.027	-0.074	0.111	-0.036	0.210	0.116	-0.229	-0.046	0.014	-0.062	0.024	-0.071	0.105	-0.017	0.000	-0.230
sharpen_2	0.019	-0.143	-0.009	0.060	-0.028	0.038	-0.079	0.054	-0.006	-0.058	0.026	0.128	-0.007	-0.093	-0.074	-0.041	-0.021	-0.176	-0.149	0.002	-0.043	0.021	-0.011	-0.111	-0.048	-0.196	0.032	-0.023	-0.144	-0.020	-0.085	-0.107	-0.001	-0.094	-0.247	-0.058	-0.021	0.248	-0.054	0.057	0.242	-0.012	-0.043	0.027	-0.228	-0.012	-0.144	-0.089	-0.105	0.177	-0.009	0.023	0.316	-0.030	0.036	-0.174	-0.018	0.051	-0.084	0.005	0.098	0.107	-0.047	0.142	0.077	-0.088	0.106	-0.070	0.079	0.015	-0.229	-0.010	-0.022	-0.045	0.024	-0.075	-0.162	-0.016	0.000	-0.230
addintensity_-80	0.004	0.042	-0.025	-0.024	-0.057	0.051	-0.024	-0.073	-0.124	-0.068	-0.037	0.301	-0.109	-0.105	-0.047	-0.008	-0.083	-0.146	-0.151	-0.142	0.006	-0.150	0.012	0.044	-0.084	-0.073	0.068	0.023	-0.115	-0.031	-0.070	-0.107	0.047	-0.119	-0.247	-0.058	0.028	0.255	0.081	-0.053	0.179	-0.068	0.144	-0.054	-0.228	0.014	0.090	-0.199	-0.177	-0.056	-0.055	0.044	-0.195	-0.048	0.187	-0.127	-0.015	0.016	-0.131	0.079	0.097	0.015	-0.143	0.061	0.021	-0.073	0.018	-0.027	0.063	0.036	-0.229	-0.014	-0.122	0.006	0.063	-0.003	-0.091	0.064	0.000	0.170
addintensity_80	0.015	0.002	-0.007	0.014	-0.012	-0.039	-0.066	0.080	0.059	-0.022	-0.017	0.120	-0.069	-0.078	-0.018	-0.024	-0.039	-0.112	-0.042	-0.015	-0.093	0.017	0.036	-0.016	0.019	-0.094	0.098	0.051	-0.087	-0.060	-0.091	-0.107	-0.003	-0.094	-0.247	-0.058	-0.018	0.179	0.094	0.027	0.057	-0.073	-0.055	0.169	-0.157	0.070	-0.063	-0.140	-0.056	0.245	0.073	0.038	-0.131	-0.064	-0.062	-0.129	-0.007	0.024	-0.062	0.038	0.005	0.040	-0.025	0.131	0.035	-0.033	-0.008	-0.074	0.019	0.189	-0.229	-0.060	0.006	0.021	0.038	-0.027	0.105	0.040	0.000	0.048
elementrandomintensity_1	-0.067	-0.121	-0.069	0.086	-0.066	-0.022	-0.279	-0.138	-0.263	-0.158	-0.311	0.152	-0.217	-0.180	-0.153	-0.017	-0.209	-0.258	-0.359	-0.091	0.050	-0.294	0.044	0.006	0.106	-0.267	0.276	-0.040	-0.388	-0.109	-0.066	-0.107	-0.022	0.068	-0.247	-0.058	0.077	0.016	0.073	0.030	0.341	-0.061	0.435	-0.226	-0.228	-0.001	0.122	-0.118	-0.540	0.172	-0.270	0.061	-0.566	-0.015	-0.438	-0.341	-0.035	0.115	-0.287	0.002	0.162	-0.225	-0.061	0.263	-0.095	-0.141	0.203	0.043	-0.466	0.255	-0.229	-0.291	-0.795	-0.117	0.182	-0.079	0.038	-0.234	0.000	-0.230
multiplyintensity_0p25	0.024	0.070	0.077	0.130	0.036	0.113	0.010	-0.004	0.067	-0.069	-0.010	0.188	-0.101	-0.072	-0.015	-0.054	0.034	-0.055	0.019	-0.060	-0.016	-0.072	0.025	0.050	0.012	-0.097	0.071	0.043	0.014	-0.005	0.013	-0.107	-0.008	0.069	-0.247	-0.058	0.010	0.259	0.111	0.106	0.312	-0.037	0.097	0.274	-0.228	0.128	0.125	0.042	-0.165	0.360	0.018	0.133	0.089	-0.010	-0.007	-0.175	-0.003	-0.053	-0.060	0.058	0.087	-0.030	-0.109	0.135	0.059	-0.062	-0.080	0.172	-0.104	0.106	-0.229	-0.002	0.002	0.079	0.069	0.076	0.105	0.006	0.000	-0.078
multiplyintensity_2	0.010	0.005	0.008	0.004	0.038	-0.046	-0.070	0.078	-0.011	-0.046	-0.073	0.090	0.028	-0.108	-0.033	0.005	-0.095	-0.122	-0.032	-0.022	-0.014	-0.034	0.048	-0.003	-0.036	-0.143	0.070	-0.022	-0.133	-0.037	-0.024	-0.107	-0.001	-0.117	-0.247	-0.058	0.037	0.198	0.010	-0.006	0.177	-0.095	-0.060	0.070	-0.228	-0.018	-0.029	-0.215	-0.118	0.023	-0.024	-0.028	-0.162	-0.124	0.024	-0.160	0.017	-0.012	-0.083	-0.008	0.060	0.133	-0.031	0.138	0.047	-0.068	-0.019	-0.070	-0.019	0.144	-0.229	-0.093	0.024	0.021	0.060	-0.012	0.090	0.066	0.000	0.070
contrastnormalization_0	0.026	0.006	0.031	0.022	-0.037	0.049	-0.090	0.017	0.060	0.004	-0.035	0.179	0.008	-0.050	-0.082	0.019	-0.066	-0.083	-0.039	-0.027	0.024	-0.046	0.024	0.015	0.035	-0.119	0.034	0.018	-0.025	-0.052	-0.137	-0.107	-0.012	-0.086	-0.171	-0.058	0.065	0.239	-0.004	0.014	0.126	-0.073	0.049	0.015	-0.189	0.015	0.086	-0.150	-0.214	0.123	-0.021	-0.062	0.068	-0.019	0.020	-0.085	0.009	0.023	-0.138	0.074	0.034	0.006	-0.001	0.089	0.037	-0.054	0.025	-0.089	0.056	0.173	-0.229	-0.014	0.041	0.007	0.089	0.004	-0.140	0.021	0.000	0.017
contrastnormalization_1	0.016	-0.041	-0.006	0.002	-0.064	-0.012	-0.062	0.038	-0.001	0.010	0.038	0.096	0.073	-0.127	-0.032	-0.018	-0.058	-0.084	-0.159	-0.038	-0.016	-0.188	0.041	-0.015	0.034	-0.153	0.058	0.061	-0.003	-0.057	-0.109	-0.107	0.025	-0.071	-0.093	0.047	-0.033	0.268	0.014	0.045	0.169	-0.056	0.021	0.073	-0.179	0.049	0.075	-0.201	-0.195	0.093	0.044	0.014	0.134	-0.011	0.016	-0.068	-0.022	0.036	-0.092	0.121	0.052	0.070	0.005	0.127	0.002	-0.077	0.042	-0.007	0.116	0.170	-0.229	0.029	-0.047	0.051	0.077	-0.008	-0.276	-0.012	0.000	-0.053
contrastnormalization_2	0.033	-0.058	0.016	0.052	0.024	-0.020	-0.095	0.025	0.067	-0.031	-0.147	0.238	-0.010	-0.015	0.056	0.004	-0.005	-0.154	-0.049	0.002	0.004	-0.042	0.030	-0.042	0.027	-0.146	0.070	0.076	0.008	-0.049	-0.103	-0.107	-0.009	-0.087	-0.165	-0.058	-0.001	0.178	0.037	0.011	0.133	-0.066	0.029	0.076	-0.228	0.024	0.015	-0.218	-0.174	0.132	0.007	0.024	-0.004	-0.020	0.020	-0.095	-0.008	0.067	-0.167	-0.003	0.018	0.088	0.029	0.112	-0.001	-0.072	0.072	-0.064	0.037	0.172	-0.229	-0.055	-0.063	-0.004	0.070	-0.035	-0.032	0.080	0.000	0.095
elastic_1	-0.070	-0.525	-0.070	0.280	0.221	0.005	-0.469	0.298	-0.382	0.014	-0.465	0.137	-0.245	-0.074	0.508	-0.179	-0.234	-0.420	-0.232	0.395	-0.159	-0.330	0.128	0.077	-0.140	-0.293	-0.097	-0.040	0.094	-0.086	-0.306	-0.107	-0.066	-0.290	-0.247	-0.058	-0.315	-0.158	-0.392	0.234	-0.353	0.074	-0.422	-0.226	-0.228	0.194	0.212	-0.180	-0.540	0.199	-0.187	-0.018	0.434	0.250	-0.376	-0.195	-0.203	0.372	-0.289	0.246	0.134	0.051	-0.192	-0.642	0.405	-0.141	-0.464	-0.157	0.534	-0.107	-0.229	-0.343	-0.795	-0.324	-0.387	-0.012	-0.562	0.009	0.000	-0.230
scaled_1p25	0.054	-0.002	0.011	0.015	0.019	0.063	0.019	0.069	0.154	0.146	-0.001	0.335	-0.001	0.038	0.004	0.061	0.051	-0.052	-0.069	0.050	0.022	0.066	0.055	0.024	-0.020	0.057	0.037	0.148	-0.035	0.309	0.086	-0.107	0.070	0.064	0.064	-0.058	0.076	0.263	0.132	0.032	0.195	0.026	-0.090	0.133	0.013	0.055	0.206	-0.154	0.005	0.158	0.077	0.128	0.306	0.022	-0.030	-0.014	0.053	0.048	-0.091	0.123	0.149	0.110	0.012	0.060	0.051	-0.036	0.030	0.060	-0.042	0.096	0.154	0.059	-0.055	0.135	0.183	-0.019	-0.062	0.011	0.000	-0.021
scaled_0p75	-0.079	-0.096	-0.185	-0.005	-0.057	-0.036	-0.063	0.003	-0.094	-0.183	-0.083	0.067	-0.102	-0.147	-0.006	-0.072	-0.127	-0.163	-0.229	-0.051	-0.064	-0.006	-0.027	-0.146	-0.080	-0.124	-0.054	-0.040	-0.131	-0.109	-0.172	-0.107	-0.066	-0.085	-0.165	-0.058	-0.122	0.019	-0.264	-0.120	-0.123	-0.177	-0.364	-0.130	-0.153	-0.131	-0.059	-0.295	-0.161	-0.168	-0.158	0.021	0.056	-0.165	-0.080	-0.133	-0.146	0.144	-0.243	0.079	-0.021	-0.127	-0.217	0.018	0.099	-0.089	-0.170	-0.108	-0.126	-0.043	-0.229	-0.196	-0.197	-0.064	-0.038	-0.133	0.188	-0.013	0.000	0.074
scaled_0p5	-0.203	-0.219	-0.292	-0.222	-0.198	-0.139	-0.084	0.058	-0.320	-0.201	-0.224	-0.170	-0.089	-0.156	-0.214	-0.161	-0.201	-0.182	-0.235	-0.167	-0.217	-0.160	-0.193	-0.186	-0.105	-0.232	-0.097	-0.040	-0.240	-0.109	-0.234	-0.107	-0.066	-0.286	-0.247	-0.058	-0.301	-0.060	-0.392	-0.152	-0.254	-0.279	-0.422	-0.226	-0.228	-0.230	-0.140	-0.241	-0.322	-0.333	-0.353	-0.230	-0.102	-0.141	-0.271	-0.086	-0.240	-0.176	-0.285	0.143	-0.049	-0.277	-0.447	-0.167	-0.095	-0.141	-0.439	-0.050	0.016	-0.270	-0.229	-0.291	-0.193	-0.197	-0.168	-0.144	0.188	-0.204	0.000	0.123
scaled_(1p25, 1p0)	0.046	-0.041	-0.030	-0.016	0.028	0.029	-0.010	0.074	0.077	0.040	-0.003	0.239	-0.001	-0.063	-0.041	-0.018	-0.063	0.041	-0.084	0.001	0.020	-0.002	0.012	0.013	-0.022	-0.054	0.055	0.174	-0.050	0.060	-0.028	-0.107	0.032	0.016	-0.046	-0.058	0.044	0.190	0.040	0.043	0.281	0.001	0.067	0.063	0.103	-0.024	0.110	-0.178	0.052	0.142	0.059	0.119	0.111	-0.083	-0.001	0.030	-0.001	0.051	-0.082	0.072	0.075	0.067	0.034	0.094	0.064	-0.068	-0.082	0.002	-0.115	0.106	0.297	0.078	0.003	0.093	0.055	-0.035	-0.198	-0.002	0.000	-0.008
scaled_(0p75, 1p0)	-0.037	-0.044	-0.143	-0.038	-0.014	-0.047	-0.046	-0.027	-0.033	-0.054	-0.071	0.040	-0.056	-0.107	-0.013	-0.006	-0.054	-0.216	-0.151	-0.058	-0.059	-0.064	-0.003	-0.100	-0.035	-0.024	-0.045	0.017	-0.123	-0.109	-0.103	-0.107	-0.032	-0.063	-0.247	-0.058	-0.047	0.132	-0.049	-0.074	0.061	-0.117	-0.136	0.045	-0.116	-0.046	-0.014	-0.228	-0.229	0.035	-0.054	0.013	-0.006	0.004	0.091	-0.067	-0.092	0.114	-0.124	0.123	-0.019	-0.116	-0.123	0.069	0.013	-0.141	-0.145	-0.068	0.031	-0.005	-0.229	-0.127	-0.131	-0.070	0.003	-0.116	0.153	0.064	0.000	0.099
scaled_(1p0, 1p25)	0.031	0.073	0.052	0.076	0.034	0.037	-0.066	0.057	0.063	0.125	0.037	0.162	0.034	-0.012	-0.019	0.078	0.021	-0.156	-0.088	-0.021	0.004	-0.054	0.034	-0.000	-0.022	0.059	0.041	0.086	0.019	0.080	-0.021	0.039	0.024	0.009	-0.008	-0.058	0.033	0.242	0.118	-0.031	0.177	-0.066	0.022	-0.027	-0.120	0.056	0.101	-0.095	-0.003	0.113	0.080	0.054	0.253	0.035	0.065	0.084	-0.009	0.101	-0.046	0.166	0.118	0.055	-0.026	0.112	0.016	-0.093	0.098	0.070	0.086	0.147	-0.229	0.077	-0.134	0.090	0.131	-0.040	-0.136	0.070	0.000	0.086
scaled_(1p0, 0p75)	-0.015	-0.007	-0.099	0.056	-0.039	0.027	-0.072	0.036	-0.121	-0.097	-0.065	0.161	-0.051	-0.085	-0.038	-0.040	-0.073	0.025	-0.161	-0.019	-0.036	-0.012	-0.019	-0.057	-0.027	-0.249	0.051	-0.037	-0.045	-0.047	-0.111	-0.107	-0.032	-0.105	-0.247	-0.058	-0.069	0.098	-0.132	-0.033	0.013	-0.095	0.080	-0.020	-0.195	-0.073	-0.011	-0.179	-0.326	-0.060	-0.024	-0.022	-0.014	-0.191	-0.068	-0.088	-0.039	0.039	-0.184	0.068	-0.073	0.078	-0.107	0.028	-0.027	-0.095	0.035	-0.069	-0.039	0.072	-0.229	-0.085	-0.098	-0.011	-0.038	0.012	-0.044	0.022	0.000	0.077
translate_(0p1, 0p1)	-0.033	-0.144	-0.151	-0.027	0.002	0.009	-0.037	0.037	-0.043	-0.127	-0.133	0.034	-0.052	-0.171	-0.058	-0.041	-0.013	-0.161	-0.080	0.016	-0.026	-0.010	0.007	-0.031	-0.088	-0.110	-0.026	-0.032	-0.165	-0.109	-0.134	-0.107	-0.024	-0.076	-0.186	-0.058	-0.020	0.166	-0.144	-0.104	-0.047	-0.116	-0.001	-0.040	-0.129	-0.073	-0.028	-0.169	-0.247	-0.123	-0.034	-0.031	-0.002	-0.078	-0.018	-0.030	-0.112	0.055	-0.174	0.124	0.012	-0.041	-0.103	0.032	0.002	-0.141	-0.183	-0.084	-0.027	-0.017	-0.229	-0.120	-0.228	-0.038	-0.056	-0.059	-0.062	0.065	0.000	0.184
translate_(0p1, -0p1)	0.016	-0.063	-0.046	0.032	0.023	0.005	-0.013	0.029	0.102	0.093	-0.068	0.249	-0.048	-0.089	-0.045	-0.049	-0.031	-0.175	-0.062	0.010	-0.010	-0.020	0.032	-0.010	-0.042	0.022	-0.025	0.023	-0.005	0.019	-0.060	-0.016	-0.031	-0.047	-0.072	-0.058	0.035	0.242	-0.045	-0.021	0.081	-0.082	0.142	-0.003	-0.084	-0.026	0.014	-0.157	-0.132	0.096	0.040	0.105	-0.006	-0.003	0.065	-0.086	-0.059	0.053	-0.123	0.087	0.046	0.046	-0.094	0.117	0.000	-0.141	-0.015	-0.050	0.034	0.073	-0.229	-0.043	-0.016	-0.023	0.060	0.067	-0.117	0.037	0.000	0.145
translate_(-0p1, 0p1)	0.014	-0.043	-0.065	0.011	-0.003	0.084	-0.026	0.053	0.078	-0.095	-0.040	0.169	-0.103	-0.017	0.047	0.079	-0.024	-0.062	-0.077	0.067	0.006	0.146	0.016	-0.009	-0.082	-0.023	0.056	0.094	-0.045	0.016	-0.062	-0.107	0.034	-0.029	-0.128	-0.058	0.087	0.257	-0.005	-0.027	0.151	-0.085	-0.113	0.069	-0.017	0.039	0.115	-0.114	-0.079	0.050	-0.006	0.049	0.198	-0.061	0.000	0.017	-0.025	0.030	-0.124	0.126	0.084	0.036	-0.084	0.107	0.018	0.010	-0.121	-0.053	0.145	0.147	-0.229	0.021	-0.029	0.033	0.043	-0.013	-0.103	0.035	0.000	0.082
translate_(-0p1, -0p1)	0.047	0.015	0.018	0.066	0.081	0.136	-0.018	0.043	0.130	0.138	-0.032	0.250	0.083	0.011	0.025	0.092	-0.019	-0.038	-0.094	0.078	0.021	0.115	0.045	0.014	0.011	0.041	0.038	0.184	-0.003	0.291	-0.024	-0.025	0.052	0.041	0.050	-0.058	0.103	0.290	0.089	0.013	0.223	-0.022	-0.049	0.044	0.128	0.078	0.130	-0.077	0.028	0.132	0.098	0.172	0.123	0.062	0.009	0.065	0.081	0.034	-0.045	0.027	0.148	0.063	0.009	0.146	0.090	-0.141	-0.032	0.113	0.056	0.149	-0.229	0.088	0.019	0.122	0.209	0.019	-0.068	0.037	0.000	0.103
translate_(0p1, 0)	0.003	-0.090	-0.093	-0.020	0.038	0.045	-0.025	-0.018	0.044	-0.062	-0.064	0.143	-0.009	-0.185	-0.062	-0.042	-0.042	-0.116	-0.026	-0.012	-0.053	-0.013	0.045	-0.028	-0.090	-0.056	-0.001	0.020	-0.111	-0.021	-0.134	-0.107	-0.032	-0.091	-0.185	-0.058	-0.025	0.138	-0.075	-0.070	0.034	-0.079	-0.004	-0.017	-0.146	-0.004	-0.023	-0.246	-0.180	-0.063	-0.030	-0.033	-0.025	0.001	0.087	-0.106	-0.058	0.015	-0.124	0.114	0.013	-0.050	-0.092	0.116	0.005	-0.109	-0.017	-0.040	-0.023	0.042	-0.229	-0.056	-0.093	-0.038	0.025	0.006	0.188	0.086	0.000	0.123
translate_(-0p1, 0)	0.041	0.036	-0.039	0.041	0.066	0.048	0.011	0.021	0.085	0.050	-0.036	0.073	0.012	-0.045	0.016	0.115	-0.060	0.008	-0.095	0.049	0.012	0.086	0.028	0.030	0.015	0.029	0.071	0.161	-0.028	0.087	-0.047	-0.107	0.018	-0.020	-0.060	-0.058	0.097	0.230	0.071	0.017	0.214	-0.008	-0.032	0.028	0.034	0.106	0.096	-0.147	0.036	0.148	0.056	0.139	0.057	0.023	0.047	0.018	0.037	0.027	-0.091	0.155	0.097	0.044	-0.023	0.145	0.077	-0.042	-0.100	-0.021	0.015	0.180	-0.229	0.030	-0.037	0.080	0.116	-0.028	-0.102	0.075	0.000	0.133
translate_(0, 0p1)	-0.003	-0.052	-0.056	0.020	-0.054	0.009	-0.006	0.052	0.001	-0.095	-0.077	0.094	-0.041	-0.131	-0.062	0.003	-0.035	-0.084	-0.079	-0.031	-0.054	-0.013	0.039	-0.034	-0.053	-0.150	-0.032	-0.033	-0.036	-0.042	-0.108	-0.107	-0.001	-0.069	-0.247	-0.058	0.001	0.165	-0.037	-0.039	0.005	-0.091	0.033	0.071	-0.193	-0.011	-0.000	-0.180	-0.227	-0.042	0.022	0.004	0.069	-0.067	0.056	-0.005	-0.014	0.084	-0.151	0.110	0.062	0.055	-0.107	0.029	0.085	-0.052	-0.013	-0.029	0.089	0.110	-0.229	-0.032	-0.140	-0.039	-0.008	0.043	-0.141	0.061	0.000	0.170
translate_(0, -0p1)	0.038	0.022	0.028	0.046	0.010	0.035	-0.005	0.055	0.107	0.140	-0.017	0.119	0.038	-0.043	-0.026	0.005	-0.033	-0.052	-0.061	0.035	-0.023	0.069	0.051	0.010	-0.016	-0.020	0.068	0.028	0.029	0.084	-0.107	-0.054	0.026	-0.004	-0.028	-0.058	0.080	0.246	0.088	0.012	0.201	-0.057	-0.018	0.018	-0.120	0.062	0.105	-0.156	-0.005	0.175	0.054	0.084	0.156	-0.008	0.097	-0.032	0.028	0.042	-0.060	0.094	0.127	0.030	-0.030	0.088	-0.012	-0.092	0.038	0.022	0.082	0.161	-0.229	0.033	-0.055	0.035	0.128	-0.001	-0.162	0.095	0.000	0.070
rotated_3	0.024	0.054	0.047	0.046	-0.053	-0.005	-0.050	0.039	0.073	0.068	-0.013	0.181	-0.076	-0.079	-0.020	0.027	-0.020	-0.078	-0.075	0.019	-0.013	-0.029	0.021	0.009	0.014	-0.035	0.083	0.063	0.012	-0.048	-0.021	-0.047	0.030	-0.050	-0.160	-0.058	0.113	0.234	0.100	0.015	0.197	-0.027	0.026	0.084	-0.137	-0.000	0.086	-0.129	-0.091	0.054	0.040	0.105	0.116	0.034	0.101	-0.002	-0.007	0.048	-0.065	0.066	0.081	0.071	-0.072	0.093	0.030	0.074	0.008	0.009	0.218	0.196	-0.229	0.009	-0.028	0.030	0.070	-0.007	-0.062	0.096	0.000	0.056

transform	person	bicycle	car	motorcycle	airplane	bus	train	truck	boat	traffic light	fire hydrant	stop sign	parking meter	bench	bird	cat	dog	horse	sheep	cow	elephant	bear	zebra	giraffe	backpack	umbrella	handbag	tie	suitcase	frisbee	skis	snowboard	sports ball	kite	baseball bat	baseball glove	skateboard	surfboard	tennis racket	bottle	wine glass	cup	fork	knife	spoon	bowl	banana	apple	sandwich	orange	broccoli	carrot	hot dog	pizza	donut	cake	chair	couch	potted plant	bed	dining table	toilet	tv	laptop	mouse	remote	keyboard	cell phone	microwave	oven	toaster	sink	refrigerator	book	clock	vase	scissors	teddy bear	hair drier	toothbrush
None	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000
gaussianblur_1	0.014	0.061	0.030	0.028	0.030	-0.044	-0.012	0.120	0.089	0.047	0.054	-0.003	-0.009	-0.101	0.009	0.047	-0.132	-0.011	-0.130	0.017	-0.040	-0.148	0.073	-0.012	-0.002	-0.068	0.061	0.002	0.038	-0.010	-0.055	-0.052	0.019	-0.011	-0.229	-0.055	0.083	0.252	0.098	0.079	0.164	-0.040	0.095	0.038	0.085	0.041	0.063	-0.271	-0.101	0.015	0.017	0.015	0.063	0.011	0.056	-0.104	0.011	0.190	-0.025	0.006	0.025	0.043	0.002	0.030	0.006	-0.001	-0.006	0.007	0.116	0.190	0.000	-0.043	-0.044	-0.001	0.080	0.029	-0.259	0.152	0.000	-0.075
gaussianblur_10	-0.011	-0.506	0.108	-0.716	-0.763	-0.191	-0.475	-0.486	-0.531	-0.079	-0.708	0.042	0.374	-0.473	-0.053	-0.127	-0.531	-0.713	-0.690	-0.613	0.142	0.141	-0.860	-0.856	-0.136	-0.140	-0.071	-0.036	-0.651	-0.095	-0.272	-0.152	-0.061	-0.623	-0.229	-0.055	-0.324	-0.311	-0.372	-0.197	-0.349	-0.241	-0.381	-0.243	-0.166	0.055	0.038	-0.361	-0.508	-0.107	-0.517	0.197	0.415	-0.149	-0.407	-0.180	-0.285	-0.594	-0.407	-0.825	0.219	0.258	-0.250	-0.227	-0.015	-0.138	-0.440	-0.125	0.080	-0.603	0.000	-0.421	-0.762	-0.317	-0.352	-0.302	-0.544	-0.708	0.000	-0.252
gaussianblur_20	-0.061	-0.506	-0.405	-0.716	-0.763	-0.768	-0.875	-0.486	-0.531	-0.279	-0.708	-0.625	-0.626	-0.473	-0.497	-0.627	-0.669	-0.713	-0.690	-0.613	-0.858	-0.859	-0.860	-0.856	-0.136	-0.640	-0.071	-0.036	-0.651	-0.095	-0.272	-0.152	-0.061	-0.623	-0.229	-0.055	-0.324	-0.311	-0.372	-0.275	-0.349	-0.269	-0.381	-0.243	-0.166	-0.363	0.080	-0.415	-0.508	-0.013	-0.517	0.735	-0.585	-0.546	-0.598	-0.420	-0.386	-0.594	-0.407	-0.825	-0.479	-0.742	-0.604	-0.646	-0.085	-0.138	-0.440	-0.125	-0.420	-0.603	0.000	-0.421	-0.762	-0.317	-0.352	-0.302	-0.544	-0.708	0.000	-0.252
superpixels_0p1	0.003	-0.257	-0.100	-0.127	-0.109	-0.088	-0.291	-0.197	-0.405	-0.177	-0.238	0.038	-0.219	-0.236	0.200	0.012	-0.169	-0.050	-0.227	-0.423	-0.091	-0.392	0.140	0.144	-0.136	-0.370	-0.071	-0.036	-0.358	-0.095	-0.272	-0.152	-0.061	-0.425	-0.229	-0.055	-0.262	0.022	-0.190	0.076	0.158	-0.092	-0.381	-0.083	-0.166	0.004	0.062	-0.182	-0.174	-0.009	-0.170	0.005	-0.096	0.109	-0.350	-0.308	-0.119	0.230	-0.187	0.025	0.011	0.112	-0.256	0.013	0.665	-0.007	-0.154	-0.053	-0.198	0.150	0.000	-0.211	-0.428	0.078	0.203	0.002	-0.544	-0.114	0.000	-0.252
superpixels_0p5	-0.069	0.161	-0.218	0.059	-0.189	-0.168	-0.365	-0.336	-0.504	-0.251	-0.355	0.009	-0.422	-0.296	0.003	-0.002	0.331	-0.713	-0.690	-0.613	-0.302	0.141	0.140	-0.856	-0.136	-0.296	-0.071	-0.036	-0.401	-0.095	-0.272	-0.152	-0.061	-0.464	-0.229	-0.055	-0.324	-0.311	-0.372	-0.088	-0.152	0.006	-0.381	-0.243	-0.166	-0.252	-0.254	-0.415	-0.508	-0.083	-0.210	0.137	-0.585	0.060	-0.305	-0.352	-0.226	0.406	-0.325	0.175	-0.165	0.092	-0.315	0.354	-0.085	-0.138	0.185	-0.125	0.580	-0.330	0.000	-0.421	-0.361	0.018	0.244	-0.302	-0.544	-0.279	0.000	-0.252
superpixels_0p85	-0.101	-0.506	-0.313	0.284	-0.013	-0.768	-0.875	-0.373	-0.531	-0.275	-0.486	-0.221	-0.626	-0.473	-0.164	-0.627	-0.669	-0.713	-0.690	-0.613	-0.858	-0.859	-0.860	-0.856	-0.136	-0.409	-0.071	-0.036	-0.651	-0.095	-0.272	-0.152	-0.061	-0.552	-0.229	-0.055	-0.324	-0.311	-0.372	-0.108	0.151	-0.029	-0.381	-0.243	-0.166	-0.363	-0.587	-0.415	-0.508	0.603	-0.395	-0.149	-0.585	-0.546	-0.153	-0.282	-0.386	-0.594	-0.195	-0.825	-0.479	-0.742	-0.243	-0.646	-0.085	-0.138	-0.440	-0.125	-0.420	-0.603	0.000	-0.421	-0.762	-0.317	-0.352	-0.302	-0.544	-0.208	0.000	-0.252
colorspace_25	0.025	-0.008	0.044	-0.008	0.043	-0.030	0.000	-0.033	0.034	-0.034	-0.051	0.135	0.038	-0.173	-0.067	0.033	-0.131	0.012	-0.229	-0.083	0.010	-0.137	0.045	-0.026	0.023	-0.211	0.013	0.005	-0.089	-0.044	-0.030	-0.071	-0.011	-0.014	-0.229	-0.055	0.034	0.263	-0.010	0.028	0.233	-0.063	-0.034	0.021	0.029	-0.047	-0.191	-0.242	0.153	0.274	-0.218	-0.265	0.415	0.052	0.040	-0.084	-0.025	0.070	-0.094	-0.047	0.027	0.112	0.046	0.112	0.017	-0.010	0.044	0.016	0.194	0.153	0.000	-0.068	0.004	0.023	0.129	0.085	-0.068	0.074	0.000	-0.082
colorspace_50	0.030	0.037	0.048	0.033	0.035	-0.057	-0.020	0.021	0.070	-0.057	-0.079	-0.002	-0.080	-0.246	-0.030	0.021	-0.093	0.019	-0.145	-0.119	0.005	-0.137	0.031	-0.021	0.061	-0.207	-0.017	0.007	-0.150	-0.043	-0.079	-0.152	0.005	0.003	-0.229	-0.055	0.055	0.230	0.025	0.022	0.226	-0.070	0.005	0.076	0.039	-0.010	-0.062	-0.227	-0.508	0.460	-0.239	-0.265	-0.585	0.034	-0.031	-0.200	-0.014	0.148	-0.144	-0.100	0.047	0.069	0.028	0.099	0.007	-0.138	0.038	-0.024	0.211	0.191	0.000	-0.026	-0.070	0.015	0.096	0.048	-0.044	0.009	0.000	-0.252
averageblur_5_11	0.026	-0.061	0.078	0.068	0.082	-0.000	-0.061	0.083	0.070	-0.056	0.102	0.023	0.068	-0.175	-0.004	-0.071	-0.191	0.114	-0.271	-0.123	-0.042	-0.162	0.087	0.035	-0.033	-0.004	0.089	-0.036	-0.102	0.015	0.061	-0.152	0.004	-0.140	-0.229	-0.055	0.029	0.322	0.099	0.098	0.260	-0.064	0.030	0.107	-0.078	-0.014	0.050	-0.275	-0.071	0.095	-0.101	0.029	0.213	-0.071	0.133	-0.146	-0.077	0.107	-0.016	0.046	-0.017	0.092	-0.068	-0.047	0.046	-0.082	0.036	-0.013	0.125	-0.008	0.000	-0.015	0.077	0.097	0.225	0.077	-0.259	0.189	0.000	0.049
medianblur_1	-0.011	0.169	0.044	0.078	0.051	-0.006	-0.123	0.131	-0.032	-0.026	0.167	-0.051	0.264	0.027	-0.140	-0.003	-0.258	-0.013	-0.185	-0.125	-0.063	-0.135	0.086	0.021	0.016	-0.111	0.054	-0.036	-0.097	-0.009	-0.020	-0.152	0.020	-0.134	-0.229	-0.055	0.003	0.239	0.071	0.027	0.354	-0.060	0.036	-0.010	-0.079	0.067	-0.090	-0.190	-0.151	0.099	-0.030	-0.023	0.104	-0.081	-0.053	-0.108	-0.019	0.088	-0.060	-0.063	0.018	0.061	-0.073	0.155	0.013	-0.059	0.154	-0.016	0.272	0.124	0.000	0.045	-0.068	0.071	0.297	0.035	-0.128	0.087	0.000	-0.091
sharpen_0	0.015	-0.105	0.015	0.082	-0.006	-0.021	-0.054	0.088	0.031	-0.005	0.035	-0.030	0.030	-0.227	-0.087	-0.017	-0.048	-0.039	-0.159	0.078	-0.138	-0.064	-0.014	-0.094	-0.002	-0.186	0.016	0.001	-0.152	-0.007	-0.054	-0.152	-0.011	-0.206	-0.229	-0.055	0.045	0.242	-0.009	0.009	0.163	-0.031	-0.025	-0.004	-0.029	-0.022	-0.134	-0.278	-0.285	0.173	0.018	-0.010	0.192	-0.086	-0.009	-0.173	-0.028	0.007	-0.051	-0.100	0.106	0.032	-0.057	0.102	0.046	-0.073	0.065	-0.015	0.088	0.087	0.000	-0.064	-0.059	-0.043	0.090	-0.058	-0.443	0.003	0.000	-0.252
sharpen_1	0.022	-0.124	0.029	-0.006	0.061	0.021	-0.063	0.049	-0.022	-0.018	-0.048	-0.036	-0.021	-0.185	-0.106	-0.007	-0.020	-0.059	-0.195	-0.020	-0.096	-0.147	0.005	-0.085	-0.084	-0.171	0.088	-0.036	-0.153	0.001	0.007	-0.152	-0.001	-0.053	-0.229	-0.055	0.017	0.174	0.013	0.028	0.206	-0.027	-0.035	0.103	0.092	-0.009	-0.194	-0.248	-0.102	0.107	-0.000	0.024	0.187	-0.056	0.024	-0.173	-0.033	0.020	-0.130	0.001	0.104	0.082	-0.064	0.098	0.020	-0.057	0.056	0.013	0.192	0.077	0.000	-0.064	-0.105	-0.019	0.102	-0.018	-0.169	-0.007	0.000	-0.252
sharpen_2	0.015	-0.113	0.056	0.039	0.063	0.042	-0.115	0.075	0.064	-0.013	0.027	-0.037	0.040	-0.125	-0.046	0.007	-0.062	-0.040	-0.122	-0.097	-0.083	-0.083	-0.016	-0.067	0.040	-0.153	0.018	0.002	-0.208	-0.003	0.019	-0.152	-0.009	0.014	-0.229	-0.055	0.029	0.175	-0.009	0.035	0.213	-0.022	-0.004	0.036	0.013	-0.008	-0.136	-0.205	-0.156	0.089	0.026	-0.003	0.069	-0.079	0.100	-0.167	-0.032	0.044	-0.108	-0.052	0.096	0.087	-0.019	0.080	0.046	-0.062	0.071	-0.049	0.203	0.058	0.000	-0.068	-0.054	-0.037	0.096	-0.056	-0.338	0.019	0.000	-0.252
addintensity_-80	0.005	0.080	-0.016	0.042	0.017	0.029	-0.050	0.030	0.059	-0.050	-0.030	0.070	-0.139	-0.038	-0.033	0.009	-0.161	-0.114	-0.126	-0.039	0.037	-0.257	0.072	0.057	-0.025	-0.123	0.047	0.009	-0.042	-0.008	-0.053	-0.050	0.021	-0.166	-0.142	-0.055	0.041	0.223	0.049	-0.025	0.172	-0.075	0.122	-0.055	-0.058	0.044	0.009	-0.209	-0.212	-0.019	0.038	0.074	0.037	-0.064	0.189	-0.092	0.005	0.139	-0.117	0.051	0.060	-0.018	-0.122	0.039	0.027	-0.038	-0.064	-0.051	0.161	-0.003	0.000	-0.049	-0.120	-0.029	0.074	0.069	-0.294	0.083	0.000	0.112
addintensity_80	0.022	-0.052	0.014	0.078	0.050	-0.034	0.007	0.096	0.019	-0.022	-0.013	-0.052	-0.055	-0.129	-0.018	0.085	-0.051	0.019	-0.077	-0.023	-0.050	-0.121	0.045	-0.056	-0.053	-0.167	0.017	0.023	0.034	-0.031	-0.071	-0.152	-0.003	0.003	-0.229	-0.055	0.029	0.191	0.063	0.029	0.178	-0.052	-0.019	0.058	-0.004	0.012	-0.029	-0.124	-0.126	0.163	0.041	-0.023	0.060	-0.058	0.035	-0.160	0.020	-0.049	-0.094	-0.035	0.020	0.067	0.052	0.115	-0.006	-0.039	0.086	-0.003	0.150	0.191	0.000	-0.070	0.044	-0.019	0.085	0.007	-0.083	0.082	0.000	0.032
elementrandomintensity_1	-0.059	0.056	-0.075	0.109	-0.034	0.166	0.031	-0.114	-0.029	-0.059	-0.118	0.039	0.016	-0.339	-0.071	-0.034	-0.139	-0.297	-0.331	-0.192	0.013	-0.405	0.091	-0.035	0.039	-0.285	0.227	-0.004	-0.312	-0.095	-0.078	-0.152	-0.019	-0.128	-0.170	-0.055	-0.013	0.038	-0.016	-0.075	0.110	-0.090	0.381	-0.129	-0.166	-0.057	0.196	-0.415	-0.229	0.372	-0.247	-0.059	-0.150	0.025	-0.400	-0.302	-0.059	0.122	-0.246	-0.206	0.107	0.167	-0.056	0.192	-0.085	-0.138	0.310	-0.067	0.580	0.397	0.000	-0.128	0.238	-0.189	-0.010	-0.116	-0.544	-0.286	0.000	-0.252
multiplyintensity_0p25	0.023	0.029	0.082	0.172	0.076	0.025	-0.019	0.104	0.013	0.002	0.085	0.133	-0.011	-0.127	-0.052	-0.060	-0.004	-0.045	-0.086	-0.031	0.039	-0.062	0.059	0.046	0.038	-0.118	-0.005	-0.036	-0.040	-0.000	-0.103	-0.068	-0.012	0.090	-0.229	-0.055	-0.064	0.284	0.081	0.058	0.332	-0.048	0.061	0.055	0.007	0.094	0.010	-0.415	-0.258	0.207	0.024	0.120	0.051	0.020	0.166	-0.233	-0.022	0.054	-0.076	-0.132	0.216	-0.019	-0.103	0.039	0.025	-0.053	-0.011	0.013	0.021	0.137	0.000	0.022	-0.013	0.057	0.109	-0.021	-0.023	0.095	0.000	0.034
multiplyintensity_2	0.012	0.063	0.016	0.046	0.022	-0.051	0.024	0.040	-0.005	-0.017	0.001	0.010	0.043	-0.113	-0.096	0.023	-0.093	-0.058	-0.108	0.005	0.011	-0.140	0.057	-0.042	-0.021	-0.175	0.057	0.031	-0.036	-0.040	-0.009	-0.152	-0.032	-0.060	-0.229	-0.055	0.068	0.202	0.099	0.021	0.149	-0.072	-0.094	0.022	0.043	-0.056	-0.153	-0.230	-0.066	0.004	-0.029	-0.018	-0.064	-0.173	0.008	-0.160	-0.007	-0.013	-0.098	0.032	0.030	0.099	-0.001	0.145	0.024	-0.015	0.035	-0.032	0.157	0.091	0.000	-0.009	-0.070	0.017	0.085	-0.026	-0.062	0.035	0.000	0.038
contrastnormalization_0	0.024	0.049	0.031	0.022	-0.007	-0.023	0.010	0.020	0.064	0.029	-0.091	0.018	-0.009	-0.099	-0.060	0.022	-0.154	-0.062	-0.120	-0.005	0.037	-0.066	0.076	0.024	0.117	-0.124	0.046	0.035	0.007	-0.038	-0.068	-0.152	-0.037	-0.114	-0.229	-0.055	0.040	0.261	0.042	-0.010	0.157	-0.053	0.054	0.024	0.118	-0.009	0.056	-0.259	-0.156	0.053	0.026	-0.020	0.093	-0.023	0.043	-0.129	-0.008	0.072	-0.089	0.037	0.034	0.010	0.005	0.094	0.009	-0.029	0.054	-0.025	0.189	0.129	0.000	0.010	-0.071	0.005	0.129	-0.017	-0.217	0.081	0.000	-0.091
contrastnormalization_1	0.016	0.014	0.031	0.012	0.014	-0.081	-0.014	0.079	0.018	-0.020	0.006	0.067	0.021	-0.141	-0.024	0.007	-0.068	-0.108	-0.158	-0.026	0.029	-0.171	0.066	-0.000	0.015	-0.164	0.041	0.004	-0.004	-0.033	-0.062	-0.152	0.009	-0.046	-0.229	-0.055	0.015	0.234	0.045	0.039	0.160	-0.061	0.028	0.025	0.129	-0.008	0.068	-0.294	-0.204	0.096	0.052	0.054	0.169	-0.022	0.072	-0.113	-0.049	0.090	-0.133	-0.060	0.041	0.032	0.005	0.093	0.019	-0.011	0.025	-0.005	0.054	0.183	0.000	-0.008	-0.081	0.006	0.121	0.007	-0.144	0.076	0.000	-0.062
contrastnormalization_2	0.028	0.006	0.029	0.002	0.048	-0.007	-0.048	0.076	0.066	-0.067	-0.042	0.091	-0.060	-0.081	-0.035	0.029	-0.045	-0.023	-0.164	0.057	0.004	-0.102	0.058	-0.035	0.050	-0.164	0.053	0.002	0.103	-0.024	-0.150	-0.152	-0.005	-0.072	-0.160	-0.055	0.084	0.250	0.035	0.047	0.184	-0.058	-0.097	0.038	0.100	-0.008	-0.013	-0.247	-0.174	-0.007	0.022	0.040	0.028	-0.010	0.044	-0.142	0.007	0.136	-0.152	0.046	0.009	0.062	0.067	-0.012	0.006	-0.001	0.097	0.009	0.151	0.109	0.000	-0.003	-0.130	-0.011	0.145	-0.021	-0.144	0.089	0.000	-0.034
elastic_1	-0.087	-0.506	-0.128	0.284	-0.763	0.001	-0.085	0.076	-0.281	-0.094	-0.306	0.144	-0.171	-0.281	0.503	-0.076	-0.040	-0.475	-0.440	-0.213	-0.119	-0.459	0.140	0.115	-0.136	-0.282	-0.071	-0.036	-0.651	0.016	-0.272	-0.152	-0.061	-0.412	-0.229	-0.055	-0.324	-0.075	0.428	0.125	-0.349	0.019	-0.381	-0.243	-0.166	0.012	-0.087	-0.368	-0.508	0.078	-0.236	0.027	-0.585	0.045	-0.444	-0.230	-0.225	0.090	-0.317	-0.825	0.140	-0.064	-0.224	0.354	0.248	-0.138	-0.440	-0.125	-0.420	-0.603	0.000	-0.421	-0.762	-0.317	-0.352	0.132	-0.544	-0.178	0.000	-0.252
scaled_1p25	0.058	-0.019	0.056	0.089	0.090	0.024	0.039	0.019	0.148	0.101	0.045	0.151	0.093	-0.107	0.022	0.073	0.031	0.088	-0.102	0.058	0.057	-0.023	0.063	0.050	-0.004	-0.043	0.025	0.214	0.074	0.307	0.065	-0.152	0.088	0.030	0.069	-0.055	0.110	0.243	0.129	0.034	0.206	-0.000	-0.122	0.120	0.071	0.016	0.202	-0.199	-0.099	0.115	0.083	0.128	0.137	0.060	0.060	0.068	0.050	0.009	-0.090	0.069	0.110	0.090	0.058	0.114	0.062	-0.048	0.023	0.030	0.033	-0.007	0.000	0.043	0.112	0.160	0.188	0.016	0.027	0.093	0.000	-0.044
scaled_0p75	-0.085	-0.151	-0.180	-0.050	-0.002	-0.060	-0.027	0.003	-0.109	-0.156	-0.047	0.024	0.006	-0.249	0.037	-0.008	-0.110	-0.011	-0.241	-0.062	-0.063	-0.099	-0.027	-0.080	-0.099	-0.189	-0.024	0.004	-0.164	-0.095	-0.064	-0.152	-0.061	-0.190	-0.153	-0.055	-0.105	0.046	-0.291	-0.104	-0.102	-0.178	-0.197	-0.025	-0.166	-0.150	-0.025	-0.207	-0.181	-0.091	-0.165	-0.011	-0.132	-0.167	0.052	-0.172	-0.179	0.051	-0.230	-0.027	-0.042	-0.131	-0.137	0.007	0.008	-0.092	-0.089	-0.083	-0.206	0.005	0.000	-0.182	0.015	-0.057	-0.002	-0.082	0.256	0.009	0.000	0.171
scaled_0p5	-0.211	-0.119	-0.275	-0.192	-0.159	-0.209	-0.065	0.064	-0.296	-0.253	-0.261	-0.208	-0.142	-0.209	-0.185	-0.118	-0.190	-0.171	-0.223	-0.141	-0.240	-0.246	-0.176	-0.174	-0.136	-0.209	-0.071	-0.036	-0.282	-0.095	-0.169	-0.152	-0.061	-0.294	-0.229	-0.055	-0.307	-0.089	-0.372	-0.155	-0.155	-0.230	-0.381	-0.243	-0.166	-0.198	-0.145	-0.245	-0.185	-0.306	-0.317	-0.207	-0.137	-0.146	-0.086	-0.212	-0.279	-0.132	-0.284	-0.020	0.007	-0.283	-0.321	-0.163	-0.085	-0.083	-0.408	-0.008	-0.100	-0.238	0.000	-0.268	-0.132	-0.164	-0.177	-0.158	0.122	-0.176	0.000	0.415
scaled_(1p25, 1p0)	0.052	0.010	0.033	-0.019	0.083	0.002	-0.007	0.044	0.108	0.062	0.056	0.155	-0.001	-0.179	-0.021	0.078	-0.052	0.074	-0.169	0.046	0.064	0.010	0.063	0.069	0.134	-0.127	0.052	0.083	0.079	0.106	0.038	-0.152	0.028	0.001	-0.050	-0.055	0.003	0.253	0.078	0.036	0.212	0.004	-0.039	0.088	0.066	0.011	0.125	-0.238	-0.083	0.088	0.067	0.091	0.176	-0.064	0.123	0.052	-0.006	0.036	-0.064	-0.019	0.059	0.076	0.046	0.067	0.118	-0.090	0.031	-0.023	0.066	0.114	0.000	0.056	0.079	0.107	0.113	-0.070	-0.294	0.094	0.000	0.004
scaled_(0p75, 1p0)	-0.028	-0.031	-0.113	-0.032	0.020	-0.001	0.001	0.040	0.031	-0.111	0.097	-0.028	-0.054	-0.173	-0.040	-0.041	-0.123	-0.054	-0.204	-0.080	-0.056	-0.057	-0.037	-0.104	-0.019	-0.103	-0.005	0.002	-0.097	-0.095	-0.058	-0.152	-0.030	-0.043	-0.162	-0.055	-0.011	0.133	-0.035	-0.070	0.090	-0.101	-0.196	-0.079	-0.104	-0.061	0.021	-0.183	-0.193	-0.043	-0.072	-0.002	0.002	0.020	0.087	-0.103	-0.120	0.144	-0.160	0.059	-0.012	-0.047	-0.022	0.034	0.034	-0.085	-0.106	-0.061	0.137	-0.063	0.000	-0.159	-0.011	-0.079	0.022	-0.047	0.056	0.112	0.000	0.034
scaled_(1p0, 1p25)	0.030	0.035	0.040	0.090	0.085	-0.075	-0.047	0.028	0.114	0.139	0.039	0.085	0.077	-0.095	-0.048	0.071	0.017	-0.104	-0.115	-0.042	-0.012	-0.044	0.052	0.028	-0.040	-0.003	0.058	0.082	-0.033	0.107	-0.001	-0.054	0.029	-0.009	-0.044	-0.055	0.098	0.280	0.020	0.007	0.243	-0.075	-0.078	0.056	-0.068	0.073	0.076	-0.141	-0.099	0.092	0.081	0.053	0.109	0.066	0.100	0.003	0.013	0.080	-0.077	0.071	0.125	0.135	-0.021	0.060	0.024	-0.092	0.054	0.095	0.250	0.198	0.000	0.030	-0.068	0.039	0.114	-0.028	-0.211	0.111	0.000	-0.052
scaled_(1p0, 0p75)	-0.021	-0.024	-0.050	-0.009	-0.053	-0.041	0.001	-0.028	-0.060	-0.093	0.039	0.105	-0.001	-0.155	-0.020	0.008	-0.078	0.021	-0.176	-0.012	0.003	-0.010	-0.001	-0.055	-0.003	-0.282	0.051	0.031	-0.051	-0.024	-0.052	-0.152	-0.027	-0.094	-0.148	-0.055	-0.040	0.150	-0.075	-0.026	0.070	-0.090	-0.082	0.033	-0.074	-0.072	-0.004	-0.203	-0.142	0.003	-0.037	0.046	-0.040	-0.167	0.097	-0.152	-0.065	0.032	-0.174	-0.048	-0.052	0.038	-0.052	0.030	0.011	-0.067	0.011	-0.073	-0.155	0.079	0.000	-0.077	-0.025	-0.047	0.061	0.045	0.103	0.075	0.000	-0.016
translate_(0p1, 0p1)	-0.033	-0.083	-0.119	-0.053	-0.034	-0.054	0.069	-0.018	-0.002	-0.114	0.063	-0.005	0.035	-0.192	-0.014	-0.044	-0.078	-0.054	-0.212	0.002	-0.026	-0.101	0.020	0.007	-0.082	-0.095	-0.039	0.004	-0.122	-0.095	-0.046	-0.152	-0.026	-0.115	-0.229	-0.055	-0.021	0.166	-0.192	-0.111	0.011	-0.118	-0.069	-0.024	-0.021	-0.077	0.006	-0.249	-0.150	-0.080	-0.095	0.010	-0.011	-0.066	0.063	-0.087	-0.119	0.076	-0.216	-0.008	0.050	-0.036	-0.025	-0.020	0.005	-0.093	-0.129	-0.065	0.056	0.063	0.000	-0.134	0.025	-0.051	-0.038	-0.013	0.456	0.031	0.000	0.101
translate_(0p1, -0p1)	0.014	-0.037	-0.020	0.056	0.028	-0.030	0.019	0.077	0.087	0.033	0.033	0.110	-0.029	-0.121	-0.005	0.011	-0.067	-0.026	-0.208	0.007	-0.000	-0.071	0.046	0.054	0.054	0.010	-0.009	0.006	-0.110	0.060	-0.014	-0.152	-0.026	-0.022	-0.051	-0.055	0.082	0.192	-0.037	-0.001	0.101	-0.065	0.024	0.053	0.003	-0.008	0.064	-0.286	-0.002	0.082	0.030	0.035	0.055	0.000	0.090	-0.091	-0.056	0.088	-0.117	-0.024	0.054	0.056	0.043	0.128	0.095	-0.058	-0.014	-0.012	0.071	0.059	0.000	0.078	-0.002	-0.021	0.075	-0.042	0.206	0.072	0.000	0.177
translate_(-0p1, 0p1)	0.021	-0.055	-0.074	0.043	-0.056	0.023	0.029	0.008	0.091	-0.071	-0.032	0.156	0.031	-0.174	0.039	0.059	-0.057	0.019	-0.075	0.031	-0.004	-0.032	0.048	-0.001	-0.100	-0.149	0.100	0.148	0.006	0.023	-0.012	-0.152	0.023	0.000	-0.161	-0.055	0.146	0.256	-0.059	-0.012	0.128	-0.092	-0.219	0.042	0.033	-0.005	0.040	-0.167	-0.107	0.047	0.034	0.036	0.135	-0.063	0.234	-0.032	-0.078	0.014	-0.090	0.054	0.102	0.039	-0.031	0.068	0.020	-0.090	0.007	-0.043	0.150	0.068	0.000	0.003	-0.017	0.047	0.044	-0.058	0.456	0.013	0.000	0.073
translate_(-0p1, -0p1)	0.057	0.023	0.024	0.054	0.031	0.063	-0.013	0.010	0.123	0.131	0.007	0.209	0.205	-0.101	0.018	0.118	-0.033	0.049	-0.100	0.067	0.040	-0.026	0.077	0.021	0.084	-0.018	0.060	0.208	0.023	0.374	0.024	-0.068	0.081	0.027	0.079	-0.055	0.131	0.317	0.090	0.033	0.244	-0.045	-0.097	0.078	0.086	0.041	0.154	-0.184	-0.043	0.151	0.119	0.118	0.215	0.058	0.114	0.005	0.034	-0.043	-0.046	-0.008	0.116	0.056	0.093	0.108	0.119	-0.066	0.089	0.060	0.008	0.144	0.000	0.104	-0.055	0.101	0.222	0.028	-0.044	0.102	0.000	-0.034
translate_(0p1, 0)	-0.004	-0.061	-0.089	-0.026	-0.021	-0.057	0.048	0.005	0.053	-0.076	0.032	-0.040	-0.073	-0.139	-0.062	-0.055	-0.121	-0.042	-0.238	0.027	0.023	-0.053	0.049	0.021	-0.076	-0.104	-0.006	0.042	-0.097	-0.095	-0.029	-0.152	-0.029	-0.031	-0.166	-0.055	0.021	0.182	-0.029	-0.056	0.077	-0.084	0.025	-0.030	0.043	-0.021	0.031	-0.248	-0.195	-0.083	-0.025	-0.006	0.013	0.055	0.045	-0.175	-0.062	0.094	-0.153	-0.005	0.001	-0.047	0.027	-0.022	0.022	-0.090	-0.049	-0.032	0.041	0.074	0.000	-0.110	-0.006	-0.054	0.036	0.014	-0.211	0.112	0.000	0.099
translate_(-0p1, 0)	0.044	-0.024	0.001	0.073	0.004	0.024	-0.034	-0.003	0.065	-0.002	0.028	0.045	-0.019	-0.126	0.011	0.119	-0.074	0.050	-0.126	0.047	0.009	0.007	0.036	0.010	0.043	-0.087	0.093	0.152	-0.021	0.067	-0.003	-0.152	0.007	0.004	-0.083	-0.055	0.111	0.254	0.043	0.082	0.237	-0.022	-0.144	0.139	0.060	0.054	0.110	-0.212	-0.089	0.039	0.079	0.123	0.153	0.024	0.118	-0.019	-0.005	0.029	-0.037	0.036	0.104	0.082	0.030	0.142	0.125	-0.087	0.048	0.020	0.018	0.100	0.000	0.015	-0.047	0.070	0.146	-0.032	-0.211	0.046	0.000	0.009
translate_(0, 0p1)	-0.004	-0.037	-0.063	0.008	-0.054	-0.013	0.028	-0.021	-0.012	-0.087	0.007	0.118	0.060	-0.178	-0.041	0.004	-0.033	0.003	-0.140	0.024	-0.031	-0.027	0.039	-0.033	-0.057	-0.191	-0.002	-0.000	0.020	-0.028	-0.026	-0.152	-0.031	-0.068	-0.229	-0.055	0.007	0.169	-0.042	-0.027	0.022	-0.092	-0.079	0.069	0.014	-0.032	0.025	-0.191	-0.148	-0.005	-0.005	0.050	0.022	-0.007	0.096	-0.056	-0.037	0.028	-0.129	0.090	0.053	0.063	-0.052	0.023	0.004	-0.073	0.006	-0.014	-0.003	0.102	0.000	-0.052	-0.075	-0.043	0.011	-0.032	0.027	0.086	0.000	-0.010
translate_(0, -0p1)	0.033	0.073	0.044	0.061	0.030	-0.005	-0.014	0.009	0.085	0.121	0.002	0.079	0.154	-0.138	0.015	0.101	-0.015	0.022	-0.144	0.028	0.002	0.006	0.064	0.047	0.055	-0.067	0.020	0.038	0.056	0.111	-0.053	-0.056	0.028	0.018	-0.059	-0.055	0.130	0.241	0.042	0.048	0.218	-0.028	-0.068	0.051	0.019	0.029	0.120	-0.240	0.023	0.191	0.072	0.049	0.197	-0.022	0.099	-0.019	0.008	0.031	-0.033	0.010	0.061	0.076	0.042	0.081	0.075	-0.059	0.084	0.001	0.212	0.084	0.000	0.119	-0.074	0.029	0.148	0.026	-0.272	0.104	0.000	-0.092
rotated_3	0.030	0.013	0.036	0.036	-0.014	-0.025	-0.015	0.041	0.077	0.054	-0.013	0.033	-0.036	-0.072	0.007	0.109	-0.100	-0.032	-0.146	0.020	0.008	-0.087	0.039	0.020	-0.039	-0.067	0.052	0.069	0.057	-0.028	-0.055	-0.045	0.022	0.001	-0.229	-0.055	0.141	0.261	0.120	0.029	0.176	-0.034	-0.057	0.092	0.041	0.013	0.062	-0.176	-0.201	0.048	0.030	0.047	0.170	0.018	0.078	0.032	-0.020	0.090	-0.099	0.065	0.058	0.078	-0.022	0.072	0.092	0.040	0.050	0.036	-0.019	0.100	0.000	0.008	-0.057	0.041	0.092	0.021	-0.100	0.143	0.000	-0.042

transform	person	bicycle	car	motorcycle	airplane	bus	train	truck	boat	traffic light	fire hydrant	stop sign	parking meter	bench	bird	cat	dog	horse	sheep	cow	elephant	bear	zebra	giraffe	backpack	umbrella	handbag	tie	suitcase	frisbee	skis	snowboard	sports ball	kite	baseball bat	baseball glove	skateboard	surfboard	tennis racket	bottle	wine glass	cup	fork	knife	spoon	bowl	banana	apple	sandwich	orange	broccoli	carrot	hot dog	pizza	donut	cake	chair	couch	potted plant	bed	dining table	toilet	tv	laptop	mouse	remote	keyboard	cell phone	microwave	oven	toaster	sink	refrigerator	book	clock	vase	scissors	teddy bear	hair drier	toothbrush
None	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000
gaussianblur_1	0.014	-0.082	0.044	0.054	0.006	-0.009	-0.024	0.101	0.102	-0.026	-0.035	0.051	-0.147	-0.024	-0.014	0.025	-0.102	0.005	-0.109	0.009	-0.017	-0.027	0.072	0.001	0.006	-0.122	0.071	0.005	-0.061	-0.028	-0.043	-0.067	0.028	0.049	-0.050	-0.082	0.035	0.254	0.022	0.077	0.163	-0.009	-0.019	0.120	-0.026	0.021	-0.069	-0.195	-0.142	0.095	-0.009	-0.029	0.172	0.044	0.134	-0.117	0.003	0.075	-0.099	0.114	0.026	0.050	-0.043	0.030	-0.006	-0.033	0.080	-0.005	0.121	0.209	0.000	-0.017	-0.088	0.060	0.041	0.007	-0.152	0.029	0.000	0.097
gaussianblur_10	-0.074	-0.507	-0.026	0.266	0.230	-0.053	-0.309	0.509	-0.567	0.054	-0.252	0.083	-0.145	-0.472	-0.302	-0.594	-0.659	0.061	-0.704	-0.037	0.129	0.184	-0.842	0.145	-0.147	-0.336	-0.111	-0.029	-0.665	-0.099	-0.277	-0.164	-0.054	0.410	-0.294	-0.082	-0.339	-0.305	-0.365	-0.155	-0.282	-0.235	-0.368	0.772	-0.224	-0.037	-0.246	-0.218	0.479	-0.013	-0.305	0.545	-0.141	-0.071	-0.273	-0.266	-0.121	-0.621	0.591	0.224	-0.166	0.296	-0.224	0.040	0.013	-0.137	-0.439	-0.143	0.103	-0.600	0.000	-0.195	-0.780	-0.332	0.630	0.065	-0.581	-0.712	0.000	-0.210
gaussianblur_20	-0.230	-0.507	-0.423	-0.734	-0.770	-0.745	-0.855	-0.491	-0.567	-0.280	-0.752	-0.584	-0.645	-0.472	-0.509	-0.658	-0.659	-0.732	-0.704	-0.637	-0.871	-0.816	-0.842	-0.855	-0.147	-0.644	-0.111	-0.029	-0.665	-0.099	-0.277	-0.164	-0.054	-0.590	-0.294	-0.082	-0.339	-0.305	-0.365	-0.295	-0.359	-0.278	-0.368	-0.228	-0.224	0.129	0.389	-0.418	-0.521	-0.275	-0.555	-0.295	-0.474	-0.535	-0.663	-0.476	-0.387	-0.621	-0.409	-0.776	-0.441	-0.704	-0.372	-0.650	-0.092	-0.137	-0.439	-0.143	-0.397	-0.600	0.000	-0.395	-0.780	-0.332	-0.370	-0.335	-0.581	-0.712	0.000	-0.210
superpixels_0p1	0.025	-0.211	-0.100	-0.014	-0.117	0.061	-0.243	-0.244	-0.290	-0.152	-0.357	-0.061	-0.533	-0.295	0.024	0.079	-0.250	-0.105	-0.378	-0.357	-0.165	-0.301	0.145	0.145	-0.147	-0.178	-0.111	-0.029	-0.213	-0.099	-0.277	-0.164	0.032	-0.283	-0.294	-0.082	-0.339	0.308	0.073	0.015	0.221	-0.058	0.299	0.013	-0.224	0.015	0.108	-0.246	-0.103	0.212	-0.214	-0.028	0.216	0.203	-0.384	-0.367	-0.152	0.059	-0.150	0.024	0.095	0.209	-0.192	0.044	0.408	-0.137	-0.053	0.009	0.083	-0.055	0.000	-0.158	-0.410	0.124	0.181	-0.125	-0.581	-0.111	0.000	-0.210
superpixels_0p5	-0.030	-0.084	-0.214	0.066	-0.233	-0.150	-0.409	-0.290	-0.486	-0.247	-0.487	-0.163	-0.448	-0.337	-0.073	-0.158	-0.436	-0.160	-0.704	-0.494	-0.033	-0.116	0.158	0.145	-0.147	-0.354	-0.111	-0.029	-0.248	-0.099	-0.277	-0.164	-0.054	-0.386	-0.294	-0.082	-0.339	-0.305	-0.365	-0.173	-0.359	0.013	-0.368	-0.228	-0.224	-0.007	-0.095	-0.145	-0.521	-0.037	-0.238	0.070	-0.474	-0.150	-0.326	-0.414	-0.266	0.071	-0.322	0.224	-0.076	0.185	-0.306	0.207	-0.092	-0.137	-0.064	-0.143	-0.087	-0.329	0.000	-0.395	-0.452	0.182	0.201	-0.251	-0.581	-0.132	0.000	-0.210
superpixels_0p85	-0.116	-0.507	-0.361	0.266	-0.642	-0.745	-0.105	-0.491	-0.567	-0.272	-0.598	-0.188	-0.645	-0.139	-0.223	-0.658	-0.659	0.268	-0.704	-0.637	-0.871	-0.816	0.158	-0.855	-0.147	-0.316	-0.111	-0.029	-0.665	-0.099	-0.277	-0.164	-0.054	-0.428	-0.294	-0.082	-0.339	-0.305	-0.365	-0.128	-0.359	-0.135	-0.368	-0.228	-0.224	-0.371	-0.611	-0.418	-0.521	0.600	-0.329	0.013	-0.474	-0.535	-0.663	-0.411	0.013	-0.621	-0.183	-0.776	-0.441	0.296	-0.382	-0.650	-0.092	-0.137	-0.439	-0.143	-0.397	-0.600	0.000	-0.395	-0.446	-0.332	-0.370	-0.335	-0.581	-0.712	0.000	-0.210
colorspace_25	0.031	-0.069	0.050	0.020	0.004	-0.008	0.036	0.002	0.058	-0.013	-0.067	0.224	0.004	-0.113	-0.008	0.005	-0.026	-0.008	-0.262	-0.111	-0.012	0.031	0.049	0.033	0.028	-0.089	0.007	0.007	-0.158	-0.046	-0.024	-0.083	0.037	-0.107	-0.222	-0.082	0.031	0.237	0.036	0.007	0.159	-0.082	-0.027	0.124	0.036	-0.075	-0.186	-0.195	0.083	0.420	-0.240	-0.295	0.526	0.199	-0.004	-0.182	-0.005	0.051	-0.063	-0.036	0.064	0.096	0.038	0.082	0.019	-0.064	0.113	-0.035	0.154	0.166	0.000	-0.034	0.032	0.033	0.105	0.010	-0.009	-0.018	0.000	-0.210
colorspace_50	0.038	-0.075	0.060	0.001	-0.007	0.003	-0.050	-0.004	0.040	-0.036	-0.051	0.215	-0.025	-0.198	-0.044	0.007	-0.092	-0.027	-0.197	-0.135	-0.049	-0.169	0.065	0.004	0.056	-0.184	-0.036	0.012	-0.083	-0.043	-0.055	-0.164	0.002	-0.094	-0.294	-0.082	0.027	0.240	-0.068	-0.020	0.148	-0.071	0.035	0.070	-0.049	-0.025	0.090	-0.062	-0.105	0.482	-0.246	-0.295	-0.474	0.093	-0.094	-0.295	-0.007	0.076	-0.099	-0.084	0.076	0.082	0.019	0.070	0.005	-0.059	0.094	-0.019	0.138	0.174	0.000	-0.023	-0.061	0.067	0.099	-0.013	-0.081	-0.063	0.000	-0.210
averageblur_5_11	0.028	-0.003	0.074	0.105	0.075	-0.004	-0.065	0.087	0.082	0.031	-0.007	0.250	-0.054	-0.115	-0.043	-0.047	-0.175	-0.001	-0.178	-0.074	-0.133	-0.013	0.084	0.072	-0.110	-0.036	0.202	0.016	-0.040	-0.007	0.053	-0.164	-0.016	-0.029	-0.223	-0.082	0.074	0.333	0.005	0.146	0.151	0.004	0.078	0.071	-0.135	0.031	-0.041	-0.258	-0.132	0.152	-0.089	-0.057	0.134	0.021	0.227	-0.126	0.004	0.060	0.006	-0.004	0.034	0.049	-0.012	0.016	0.086	-0.080	-0.020	-0.017	0.080	-0.042	0.000	-0.037	-0.160	0.059	0.092	0.012	-0.206	0.129	0.000	-0.046
medianblur_1	0.001	0.039	0.059	0.046	-0.029	0.039	-0.076	0.116	0.019	-0.066	0.080	0.050	0.229	-0.071	-0.184	-0.012	-0.285	-0.031	-0.175	-0.090	-0.087	-0.003	0.072	0.072	-0.055	-0.168	-0.052	0.015	-0.088	-0.056	-0.011	-0.164	0.011	-0.102	-0.294	-0.082	0.123	0.267	0.091	0.111	0.220	-0.021	0.014	0.018	-0.093	0.023	-0.131	-0.208	0.030	0.058	-0.019	-0.011	0.199	0.030	0.030	-0.098	-0.005	0.125	-0.080	0.038	0.034	0.120	-0.040	0.132	0.012	-0.031	0.169	-0.020	0.203	-0.036	0.000	-0.040	-0.058	0.028	0.160	-0.039	-0.131	0.070	0.000	0.025
sharpen_0	0.017	-0.079	0.034	0.025	0.003	0.003	-0.009	0.009	0.012	-0.011	-0.017	-0.001	0.022	-0.083	-0.069	-0.015	-0.064	-0.042	-0.230	-0.082	0.006	-0.007	0.035	-0.051	-0.028	-0.212	0.020	-0.006	-0.219	-0.011	-0.030	-0.164	0.007	-0.146	-0.215	-0.082	-0.033	0.226	0.010	0.019	0.142	-0.019	-0.027	0.129	-0.081	-0.002	-0.087	-0.241	-0.266	0.188	0.015	-0.002	0.229	-0.043	-0.098	-0.266	-0.016	0.038	-0.049	0.019	0.081	0.093	-0.023	0.048	0.057	-0.091	0.085	-0.039	0.223	0.002	0.000	-0.061	0.032	-0.004	0.117	-0.065	-0.081	0.072	0.000	-0.210
sharpen_1	0.015	-0.037	0.028	-0.014	-0.013	0.064	0.024	0.002	0.004	-0.003	-0.042	0.012	0.011	-0.030	-0.080	-0.035	-0.058	-0.057	-0.263	-0.024	0.008	0.038	0.046	-0.043	0.047	-0.136	0.013	-0.006	-0.226	-0.019	-0.050	-0.164	0.007	0.061	-0.222	-0.082	0.023	0.232	-0.005	0.058	0.213	-0.030	-0.060	0.173	-0.159	0.014	-0.139	-0.149	-0.133	0.183	0.052	-0.033	0.208	0.030	-0.053	-0.209	0.007	-0.006	0.018	0.050	0.067	0.088	-0.018	0.095	0.012	-0.137	0.095	-0.047	0.303	0.004	0.000	-0.017	-0.044	0.012	0.119	-0.015	-0.081	0.053	0.000	0.110
sharpen_2	0.015	-0.121	0.022	-0.019	0.015	0.029	-0.020	0.044	0.064	0.005	-0.009	0.044	-0.030	-0.052	-0.051	0.001	-0.042	-0.087	-0.279	-0.135	-0.010	0.048	0.039	-0.051	0.023	-0.138	0.035	-0.012	-0.180	-0.006	-0.004	-0.164	0.012	-0.076	-0.206	-0.082	-0.016	0.220	-0.003	0.042	0.227	-0.023	-0.034	0.080	-0.000	-0.004	-0.058	-0.180	-0.199	0.139	0.024	-0.057	0.001	-0.009	0.024	-0.230	-0.012	0.004	-0.055	0.005	0.072	0.135	-0.008	0.129	0.018	-0.091	0.158	-0.043	0.228	-0.070	0.000	0.060	0.013	0.013	0.082	-0.013	-0.081	0.007	0.000	0.165
addintensity_-80	0.021	0.064	0.008	0.063	-0.031	0.134	-0.106	-0.031	-0.015	-0.070	-0.119	0.161	-0.002	-0.008	-0.064	-0.088	-0.147	-0.043	-0.098	-0.060	0.002	-0.200	0.063	0.051	-0.008	-0.093	0.061	0.034	-0.013	-0.026	0.013	-0.164	0.008	0.009	-0.154	-0.082	0.031	0.193	0.107	-0.043	0.239	-0.059	0.025	-0.004	-0.003	0.037	-0.026	-0.216	-0.192	-0.053	-0.012	0.179	0.249	-0.035	0.074	-0.145	-0.022	0.138	-0.080	0.078	0.105	0.077	-0.062	0.025	0.006	-0.027	0.047	-0.037	0.019	0.021	0.000	-0.009	-0.090	0.028	0.063	0.006	-0.152	0.022	0.000	0.040
addintensity_80	0.017	-0.006	0.003	0.005	-0.040	-0.023	0.012	0.049	0.019	0.036	-0.030	0.081	0.005	-0.085	0.010	0.064	-0.073	-0.004	-0.110	-0.055	-0.025	-0.066	0.051	-0.069	0.038	-0.164	-0.004	0.028	-0.062	-0.032	-0.042	-0.164	0.003	-0.004	-0.217	0.018	0.084	0.164	0.081	0.016	0.129	-0.064	-0.033	-0.002	-0.056	-0.005	-0.031	-0.148	-0.127	0.205	-0.008	-0.080	-0.035	0.047	0.094	-0.183	0.008	0.007	-0.083	0.012	0.073	0.121	0.002	0.088	0.002	-0.040	0.073	-0.017	0.097	0.220	0.000	-0.026	-0.003	0.011	0.088	-0.028	-0.189	0.000	0.667	-0.045
elementrandomintensity_1	-0.058	0.001	-0.144	0.053	0.034	0.052	0.120	-0.125	-0.104	-0.046	-0.227	0.136	-0.195	-0.217	-0.245	-0.155	-0.148	-0.226	-0.272	-0.183	0.001	-0.216	0.109	-0.008	-0.147	-0.270	0.188	0.006	-0.317	-0.099	-0.125	-0.164	-0.054	0.048	-0.294	-0.082	0.179	0.063	0.018	-0.046	0.285	0.016	0.382	-0.088	0.088	-0.048	0.183	-0.265	-0.521	0.100	-0.263	-0.202	0.017	-0.084	-0.533	-0.377	-0.098	0.220	-0.226	0.002	0.091	0.046	0.045	0.082	0.408	-0.137	0.561	-0.143	0.603	0.121	0.000	0.040	0.220	-0.123	-0.055	-0.022	-0.081	-0.296	0.000	-0.210
multiplyintensity_0p25	0.031	0.015	0.066	0.096	0.068	0.153	-0.029	0.061	0.040	0.042	0.100	0.242	0.022	-0.081	-0.027	-0.044	-0.032	-0.012	-0.053	-0.047	0.011	0.038	0.089	0.011	0.043	-0.149	-0.023	0.013	-0.005	-0.013	-0.016	-0.164	-0.006	0.049	-0.112	-0.082	0.043	0.296	0.109	0.063	0.234	-0.031	0.032	0.147	0.060	0.038	0.041	-0.037	-0.188	0.400	-0.041	0.012	0.128	0.065	0.121	-0.273	-0.022	-0.024	0.001	-0.050	0.159	0.040	-0.050	0.117	0.010	-0.089	0.088	-0.004	0.064	0.155	0.000	0.004	-0.038	0.041	0.102	0.048	-0.152	0.013	0.000	0.165
multiplyintensity_2	0.016	0.040	-0.008	-0.033	-0.013	0.010	-0.016	0.038	-0.050	-0.037	-0.081	0.005	0.099	-0.121	0.002	-0.009	-0.079	-0.060	-0.116	-0.072	-0.052	-0.022	0.067	-0.006	0.038	-0.155	0.044	0.090	-0.081	-0.045	-0.103	-0.164	-0.022	-0.056	-0.129	-0.082	0.006	0.230	0.018	-0.002	0.120	-0.046	-0.035	0.108	-0.124	-0.014	-0.171	-0.217	-0.064	0.075	-0.029	-0.073	0.118	-0.071	0.005	-0.143	0.019	0.056	-0.123	0.022	0.074	0.083	0.009	0.123	0.027	-0.045	0.069	0.012	0.044	0.022	0.000	-0.025	-0.214	0.025	0.079	-0.046	-0.194	-0.056	0.000	0.090
contrastnormalization_0	0.029	-0.016	0.030	0.045	-0.041	-0.059	-0.020	0.015	0.071	0.001	-0.118	0.066	-0.001	-0.048	0.018	-0.029	-0.114	-0.065	-0.083	-0.034	0.004	-0.023	0.054	0.007	0.053	-0.133	-0.039	0.045	0.001	-0.029	-0.057	-0.066	0.006	-0.095	-0.234	-0.082	0.022	0.189	0.084	0.010	0.148	-0.059	-0.010	0.004	-0.068	-0.006	-0.041	-0.126	-0.174	0.102	0.026	-0.054	0.225	-0.022	0.090	-0.116	-0.000	0.031	-0.036	0.013	0.038	0.031	0.010	0.098	-0.002	-0.068	0.123	-0.068	0.160	-0.005	0.000	-0.030	-0.109	0.035	0.073	-0.006	-0.206	-0.049	0.000	0.034
contrastnormalization_1	0.020	-0.065	0.011	0.082	-0.047	-0.073	0.001	0.086	0.057	-0.051	0.005	0.106	-0.006	-0.098	-0.010	0.034	-0.038	-0.045	-0.099	0.003	-0.011	-0.115	0.067	0.001	0.096	-0.136	-0.015	0.045	0.039	-0.020	-0.108	-0.059	0.039	-0.044	-0.146	-0.001	-0.020	0.241	0.042	0.007	0.149	-0.039	-0.021	0.137	0.123	-0.016	0.027	-0.237	-0.066	0.087	0.027	-0.025	0.226	0.070	0.048	-0.103	-0.002	0.090	-0.129	-0.008	0.046	0.000	0.047	0.066	0.009	-0.058	0.136	0.020	0.186	0.193	0.000	-0.023	-0.207	0.041	0.053	-0.085	-0.142	0.041	0.000	0.050
contrastnormalization_2	0.032	-0.036	0.037	0.025	-0.009	-0.037	-0.001	0.025	0.019	0.016	-0.064	0.131	-0.048	-0.073	-0.029	-0.008	-0.006	-0.061	-0.097	-0.021	-0.038	-0.070	0.049	-0.004	0.083	-0.148	-0.003	0.006	-0.041	-0.022	-0.069	-0.164	0.006	-0.117	-0.047	-0.082	0.043	0.221	0.044	0.034	0.159	-0.037	-0.053	0.009	0.030	0.034	-0.050	-0.184	-0.229	0.042	-0.004	0.017	0.147	-0.013	0.029	-0.135	0.008	0.083	-0.098	0.026	0.033	0.060	0.020	0.071	0.013	-0.090	0.105	0.038	0.327	0.236	0.000	0.004	-0.105	0.029	0.071	-0.019	-0.131	-0.032	0.000	0.150
elastic_1	-0.029	-0.507	-0.148	0.266	-0.770	-0.120	-0.158	-0.028	-0.455	0.021	-0.115	0.065	0.355	-0.028	-0.009	-0.196	0.025	-0.470	-0.012	0.030	-0.002	-0.379	0.158	-0.009	-0.147	-0.228	-0.111	-0.029	0.335	-0.002	-0.027	-0.164	-0.054	-0.196	-0.294	-0.082	-0.339	-0.021	0.207	0.538	0.641	0.080	-0.368	0.105	0.776	0.157	-0.147	-0.329	-0.521	0.112	-0.218	-0.016	0.526	0.104	-0.456	-0.375	-0.052	0.379	-0.316	-0.276	0.184	0.061	-0.041	0.274	0.575	-0.137	-0.439	0.191	-0.397	-0.600	0.000	0.089	-0.780	-0.332	-0.370	-0.078	0.419	-0.020	0.000	-0.210
scaled_1p25	0.061	-0.006	0.058	0.014	0.050	0.047	0.035	0.084	0.109	0.077	0.006	0.302	0.103	-0.046	0.024	0.106	-0.031	0.062	-0.064	0.031	0.002	0.020	0.064	0.104	0.055	-0.038	0.015	0.209	0.064	0.338	0.108	-0.164	0.093	0.069	0.011	-0.082	0.072	0.268	0.132	0.050	0.260	0.014	-0.010	0.123	-0.002	0.036	0.130	-0.133	-0.003	0.120	0.091	0.118	0.270	0.104	0.077	0.035	0.049	0.001	-0.073	0.004	0.147	0.119	0.120	0.089	0.110	-0.064	0.109	0.091	0.035	0.080	0.000	0.098	-0.034	0.143	0.208	-0.014	-0.181	0.083	0.000	-0.004
scaled_0p75	-0.080	-0.130	-0.201	-0.056	-0.068	-0.080	-0.031	-0.056	-0.207	-0.201	-0.130	0.087	-0.005	-0.105	0.028	-0.085	-0.081	-0.030	-0.217	-0.040	-0.084	-0.049	-0.012	-0.095	-0.093	-0.232	-0.055	-0.029	-0.153	-0.099	-0.096	-0.164	-0.054	-0.087	-0.177	-0.082	-0.143	-0.003	-0.236	-0.102	-0.082	-0.174	-0.147	-0.055	-0.192	-0.189	-0.118	-0.157	-0.174	-0.107	-0.198	0.027	-0.017	-0.132	0.128	-0.162	-0.123	0.034	-0.217	0.002	0.013	-0.107	-0.113	0.049	0.026	-0.099	-0.089	-0.104	-0.057	0.011	0.000	-0.194	-0.083	-0.068	-0.051	-0.127	-0.110	-0.053	0.000	0.030
scaled_0p5	-0.219	-0.197	-0.303	-0.179	-0.223	-0.151	-0.126	-0.011	-0.383	-0.215	-0.295	-0.166	-0.251	-0.152	-0.237	-0.117	-0.212	-0.239	-0.299	-0.189	-0.243	-0.164	-0.155	-0.180	-0.147	-0.170	-0.111	-0.029	-0.280	-0.099	-0.198	-0.164	-0.054	-0.299	-0.294	-0.082	-0.323	-0.095	-0.340	-0.182	-0.256	-0.241	-0.368	-0.228	-0.224	-0.189	-0.137	-0.226	-0.222	-0.294	-0.339	-0.193	-0.126	-0.124	-0.028	-0.152	-0.282	-0.149	-0.290	0.053	0.048	-0.303	-0.357	-0.207	-0.092	-0.137	-0.411	-0.062	0.103	-0.331	0.000	-0.220	-0.206	-0.180	-0.209	-0.229	0.008	-0.234	0.000	0.190
scaled_(1p25, 1p0)	0.050	0.056	-0.012	0.021	0.078	0.067	0.071	0.095	0.050	0.015	-0.084	0.144	0.133	-0.073	0.026	0.093	-0.047	0.082	-0.101	0.025	0.008	0.029	0.062	0.058	0.055	-0.037	0.033	0.168	-0.014	0.125	0.023	-0.164	0.049	-0.062	-0.125	-0.013	0.054	0.231	0.070	0.076	0.222	-0.014	-0.039	0.100	-0.032	0.019	0.059	-0.141	-0.017	0.082	0.051	0.111	0.286	-0.062	0.031	0.063	0.039	0.033	-0.115	0.012	0.080	0.079	0.075	0.101	0.049	-0.056	0.007	0.056	0.022	0.065	0.000	0.097	0.031	0.108	0.107	-0.071	-0.081	0.045	0.000	0.142
scaled_(0p75, 1p0)	-0.030	-0.070	-0.125	-0.014	-0.044	0.019	-0.021	-0.029	-0.065	-0.125	-0.100	0.110	-0.018	-0.102	0.061	-0.075	-0.164	-0.094	-0.180	-0.025	-0.071	-0.025	0.001	-0.127	-0.098	-0.096	-0.049	0.029	-0.192	-0.099	-0.144	-0.164	-0.021	-0.058	-0.227	-0.082	-0.069	0.130	-0.080	-0.052	0.067	-0.100	-0.098	-0.007	-0.166	-0.078	-0.076	-0.260	-0.149	-0.066	-0.120	-0.026	0.030	0.082	0.158	-0.185	-0.097	0.039	-0.108	0.065	0.033	-0.087	-0.076	0.097	0.015	-0.085	0.005	-0.064	0.059	-0.012	0.000	-0.140	-0.072	-0.034	-0.007	-0.072	-0.065	0.057	0.000	0.056
scaled_(1p0, 1p25)	0.037	0.043	0.060	0.089	0.057	0.017	-0.017	0.052	0.067	0.130	0.014	0.149	0.024	0.066	0.001	0.122	-0.080	-0.058	-0.125	-0.060	-0.021	0.011	0.063	0.028	-0.023	0.003	-0.020	0.061	0.004	0.103	-0.005	-0.068	0.036	0.047	-0.127	-0.082	0.074	0.229	0.076	-0.012	0.172	-0.042	-0.044	0.007	0.056	0.027	0.069	-0.174	-0.018	0.149	-0.000	0.019	0.255	0.125	0.056	-0.026	0.010	0.071	-0.090	0.064	0.125	0.077	0.045	0.093	0.002	-0.094	0.121	0.052	0.272	0.129	0.000	0.126	-0.029	0.012	0.118	-0.020	-0.139	0.051	0.000	-0.004
scaled_(1p0, 0p75)	-0.008	-0.016	-0.098	-0.037	-0.021	0.047	0.027	0.001	-0.123	-0.123	-0.074	0.133	-0.056	-0.080	-0.012	0.005	-0.030	0.019	-0.157	-0.017	-0.046	-0.021	0.001	-0.038	-0.052	-0.214	-0.066	0.008	-0.108	-0.042	-0.085	-0.164	-0.019	-0.062	-0.143	-0.082	-0.081	0.076	-0.057	-0.027	0.105	-0.073	0.040	-0.021	-0.073	-0.066	-0.079	-0.106	-0.093	0.056	-0.091	-0.057	0.227	-0.150	0.005	-0.123	-0.038	0.002	-0.185	-0.043	-0.019	-0.036	-0.047	0.036	-0.006	-0.063	0.033	-0.041	-0.027	0.052	0.000	-0.061	-0.109	-0.056	0.021	-0.002	-0.219	0.032	0.000	0.251
translate_(0p1, 0p1)	-0.023	-0.156	-0.141	-0.054	-0.040	-0.032	0.037	-0.017	-0.106	-0.165	-0.069	0.106	0.019	-0.104	0.011	-0.082	-0.123	-0.034	-0.148	-0.019	-0.037	-0.086	0.014	-0.007	-0.112	-0.189	-0.043	0.006	-0.109	-0.099	-0.108	-0.164	-0.014	-0.095	-0.129	-0.082	-0.034	0.089	-0.067	-0.101	-0.032	-0.141	-0.050	-0.008	-0.137	-0.024	-0.083	-0.150	-0.166	-0.083	-0.131	-0.044	0.107	-0.013	0.116	-0.151	-0.094	0.116	-0.241	0.075	0.017	-0.032	-0.021	0.020	-0.007	-0.087	-0.084	-0.076	0.118	0.017	0.000	-0.101	-0.040	-0.021	-0.034	0.040	0.086	-0.001	0.000	0.075
translate_(0p1, -0p1)	0.023	-0.050	-0.023	0.023	0.070	-0.008	0.062	0.038	0.027	0.010	-0.007	0.179	-0.033	-0.018	-0.017	-0.037	-0.065	-0.019	-0.093	0.009	-0.028	-0.024	0.068	0.007	-0.048	0.034	-0.042	0.040	-0.079	0.063	-0.062	-0.060	-0.018	0.004	-0.172	-0.082	0.012	0.226	-0.011	0.009	0.064	-0.084	0.040	0.016	-0.040	0.039	0.057	-0.304	0.009	0.093	0.025	-0.003	0.081	0.025	0.076	-0.108	-0.023	0.119	-0.052	0.015	0.090	-0.005	0.048	0.034	-0.006	-0.045	-0.003	0.008	0.033	0.025	0.000	-0.015	-0.003	-0.026	0.084	0.073	-0.081	0.025	0.000	0.062
translate_(-0p1, 0p1)	0.025	-0.112	-0.084	0.032	-0.013	0.088	-0.029	0.063	0.030	-0.106	-0.052	0.281	-0.066	-0.108	0.042	0.051	-0.053	0.001	-0.069	0.002	-0.024	0.044	0.045	0.014	-0.021	-0.217	0.037	0.160	-0.005	0.040	-0.029	-0.164	0.041	0.015	-0.180	-0.082	0.035	0.255	-0.008	0.004	0.181	-0.044	-0.104	0.084	0.177	-0.017	0.010	-0.147	-0.079	0.050	-0.026	0.030	0.246	0.000	0.070	-0.034	-0.014	-0.006	-0.141	0.040	0.085	0.052	-0.017	0.029	-0.009	-0.061	0.082	0.017	0.097	0.081	0.000	0.035	0.005	0.050	0.056	-0.040	-0.009	0.042	0.000	0.165
translate_(-0p1, -0p1)	0.051	0.034	0.035	0.054	0.091	0.077	0.024	0.083	0.037	0.097	-0.036	0.232	0.105	0.025	0.042	0.122	0.031	0.023	-0.077	0.052	0.003	0.037	0.086	0.007	-0.024	0.034	0.049	0.230	0.024	0.305	0.000	0.018	0.096	0.012	-0.099	-0.016	0.052	0.298	0.176	0.044	0.186	-0.015	-0.100	0.024	0.133	0.012	0.067	-0.151	0.046	0.177	0.078	0.167	0.248	0.112	0.035	-0.016	0.083	0.034	-0.043	0.072	0.137	0.100	0.084	0.097	0.127	-0.119	0.080	0.104	-0.001	0.003	0.000	0.125	-0.026	0.066	0.220	0.044	-0.181	0.061	0.000	0.251
translate_(0p1, 0)	-0.003	-0.075	-0.121	0.022	-0.005	0.014	0.038	-0.033	-0.055	-0.116	-0.016	0.067	0.016	-0.111	-0.034	-0.050	-0.075	0.002	-0.136	0.018	-0.033	-0.023	0.067	-0.000	-0.044	-0.087	0.004	0.045	-0.126	-0.027	-0.093	-0.164	-0.019	-0.031	-0.175	-0.082	-0.037	0.137	-0.016	-0.057	0.064	-0.053	0.067	0.024	-0.090	-0.020	-0.055	-0.179	-0.108	-0.060	-0.056	-0.058	0.131	-0.001	0.078	-0.106	-0.059	0.125	-0.129	0.040	0.026	-0.100	-0.043	0.084	0.009	-0.093	0.012	-0.031	0.044	0.061	0.000	-0.045	-0.072	-0.009	0.033	0.044	0.086	-0.012	0.000	0.142
translate_(-0p1, 0)	0.042	-0.008	-0.031	0.049	0.024	0.030	0.078	0.021	0.033	-0.021	-0.116	0.097	0.054	-0.020	0.038	0.096	-0.042	0.030	-0.083	0.029	0.008	0.056	0.054	0.014	0.055	-0.100	0.044	0.220	-0.000	0.156	-0.075	-0.164	0.038	-0.012	-0.049	-0.082	0.058	0.223	0.111	0.052	0.198	0.008	-0.049	0.109	0.105	0.066	0.096	-0.140	-0.065	0.089	0.028	0.046	0.190	0.049	0.170	-0.041	0.040	0.102	-0.074	0.030	0.132	0.088	0.049	0.111	0.039	-0.095	0.100	0.050	0.112	0.053	0.000	0.073	-0.041	0.101	0.122	-0.025	-0.181	0.023	0.000	0.020
translate_(0, 0p1)	0.002	-0.054	-0.066	0.017	-0.034	-0.016	0.008	-0.015	-0.014	-0.135	0.020	0.119	-0.040	-0.147	0.027	0.026	-0.044	-0.004	-0.107	-0.040	-0.066	-0.018	0.058	-0.036	-0.026	-0.229	-0.039	0.009	-0.088	-0.027	-0.066	-0.164	0.012	-0.009	-0.124	-0.082	-0.027	0.147	-0.012	-0.013	0.102	-0.055	-0.044	0.108	-0.153	-0.026	-0.095	-0.197	-0.022	0.006	-0.026	0.012	0.202	0.033	0.154	-0.094	-0.036	-0.005	-0.161	0.109	0.013	0.061	-0.045	-0.026	-0.007	-0.031	0.098	-0.039	0.177	0.125	0.000	-0.034	-0.094	0.017	0.007	0.027	0.019	0.032	0.000	0.165
translate_(0, -0p1)	0.036	0.095	0.053	0.081	0.074	0.008	-0.020	0.096	0.048	0.116	0.014	0.133	0.073	-0.031	0.079	0.057	-0.004	-0.012	-0.105	-0.053	-0.021	0.022	0.077	0.023	-0.032	-0.025	-0.052	0.075	0.001	0.113	-0.061	-0.075	0.039	0.060	-0.116	-0.082	0.084	0.241	0.091	0.034	0.128	-0.023	-0.037	0.045	0.011	0.048	0.038	-0.184	0.032	0.157	0.030	0.026	0.223	0.088	0.057	-0.034	0.018	0.027	-0.033	0.006	0.080	0.101	0.035	0.071	-0.013	-0.065	0.099	0.054	0.153	0.066	0.000	0.044	-0.039	0.014	0.127	0.067	-0.247	0.092	0.000	0.190
rotated_3	0.033	-0.054	0.025	0.025	-0.015	0.016	0.007	0.048	0.077	0.009	0.054	0.051	-0.181	-0.004	0.020	0.067	-0.097	0.043	-0.150	-0.007	-0.043	0.048	0.070	-0.008	-0.023	-0.090	0.030	0.088	-0.013	0.033	-0.036	-0.061	0.056	0.013	-0.115	-0.082	0.080	0.194	0.129	0.015	0.217	0.014	-0.040	0.097	0.000	0.039	-0.000	-0.109	-0.067	0.065	0.012	0.033	0.157	0.058	0.089	0.000	0.000	0.070	-0.027	0.067	0.105	0.073	-0.012	0.129	0.038	-0.025	0.163	-0.045	0.087	0.177	0.000	0.053	-0.033	0.043	0.070	0.006	-0.009	0.071	0.000	0.056

transform	person	bicycle	car	motorcycle	airplane	bus	train	truck	boat	traffic light	fire hydrant	stop sign	parking meter	bench	bird	cat	dog	horse	sheep	cow	elephant	bear	zebra	giraffe	backpack	umbrella	handbag	tie	suitcase	frisbee	skis	snowboard	sports ball	kite	baseball bat	baseball glove	skateboard	surfboard	tennis racket	bottle	wine glass	cup	fork	knife	spoon	bowl	banana	apple	sandwich	orange	broccoli	carrot	hot dog	pizza	donut	cake	chair	couch	potted plant	bed	dining table	toilet	tv	laptop	mouse	remote	keyboard	cell phone	microwave	oven	toaster	sink	refrigerator	book	clock	vase	scissors	teddy bear	hair drier	toothbrush
None	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000	0.000
gaussianblur_1	0.028	-0.024	0.057	0.018	-0.024	0.035	0.016	0.034	0.051	-0.013	0.022	0.093	-0.039	-0.022	-0.028	0.010	-0.142	0.003	-0.174	-0.092	-0.062	-0.010	0.071	0.025	0.067	-0.118	0.052	0.004	-0.061	-0.023	-0.061	-0.182	0.030	-0.031	-0.124	-0.060	0.008	0.178	0.071	0.039	0.151	-0.037	-0.006	0.109	0.002	0.028	-0.020	-0.153	-0.149	0.073	0.043	0.017	0.174	-0.010	0.058	-0.034	0.004	0.054	-0.096	0.077	-0.030	0.064	-0.037	0.068	0.029	0.012	0.038	0.005	0.056	0.107	-0.322	-0.040	-0.048	0.078	0.047	0.002	-0.228	0.064	0.000	0.071
gaussianblur_10	-0.134	-0.536	-0.009	0.265	-0.768	-0.130	-0.210	-0.151	-0.527	0.275	-0.704	0.428	0.044	-0.169	-0.321	-0.453	-0.406	0.273	-0.748	0.331	-0.170	0.153	-0.848	0.166	-0.131	-0.357	-0.103	-0.043	-0.661	-0.102	-0.259	-0.182	-0.067	-0.619	-0.300	-0.060	-0.359	-0.304	-0.327	-0.235	-0.402	-0.286	-0.359	-0.238	-0.214	-0.057	0.034	-0.343	-0.458	-0.146	-0.487	0.128	0.528	0.021	-0.343	-0.317	-0.278	-0.568	-0.067	0.287	0.060	0.274	-0.380	-0.186	-0.083	-0.153	-0.443	0.364	0.091	-0.614	-0.322	-0.420	-0.722	0.703	0.636	-0.303	-0.486	-0.688	0.000	-0.180
gaussianblur_20	-0.257	-0.536	-0.408	-0.735	-0.768	-0.777	-0.876	-0.484	-0.527	-0.281	-0.704	-0.572	-0.623	-0.404	-0.477	-0.682	-0.656	-0.727	-0.748	-0.669	-0.866	-0.847	-0.848	-0.834	-0.131	-0.654	-0.103	-0.043	-0.661	-0.102	-0.259	-0.182	-0.067	-0.619	-0.300	-0.060	-0.359	-0.304	-0.327	-0.286	-0.402	-0.312	-0.359	-0.238	-0.214	0.071	0.418	-0.411	-0.458	-0.181	-0.487	-0.276	-0.472	-0.531	-0.589	-0.421	-0.371	-0.568	-0.420	-0.713	-0.419	-0.726	-0.517	-0.628	-0.083	-0.153	-0.443	-0.136	-0.409	-0.614	-0.322	-0.420	-0.722	-0.297	-0.364	-0.303	-0.486	-0.688	0.000	-0.180
superpixels_0p1	0.028	-0.217	-0.002	0.030	-0.018	-0.035	-0.130	-0.253	-0.350	-0.171	-0.203	0.014	0.068	-0.155	0.043	-0.059	-0.220	0.119	-0.132	-0.144	-0.101	-0.085	0.068	0.166	-0.131	-0.276	0.150	-0.043	-0.190	0.064	-0.259	-0.182	-0.067	-0.366	-0.300	-0.060	-0.017	0.186	0.075	-0.072	0.227	-0.035	0.443	-0.040	0.056	0.087	0.134	-0.059	0.018	0.160	-0.112	0.007	0.147	-0.102	-0.257	-0.286	-0.090	0.172	-0.204	0.015	-0.009	0.069	-0.280	-0.049	0.417	-0.071	-0.049	-0.063	-0.080	-0.037	-0.322	-0.141	-0.323	0.094	0.116	-0.063	-0.486	0.108	0.000	-0.180
superpixels_0p5	-0.062	-0.029	-0.070	0.201	-0.184	0.036	-0.369	-0.307	-0.461	-0.262	-0.381	-0.220	-0.077	-0.176	-0.120	-0.172	-0.347	-0.727	-0.748	-0.383	-0.255	-0.247	-0.070	-0.034	-0.131	-0.439	-0.103	0.202	-0.329	-0.102	-0.259	-0.182	-0.067	-0.477	-0.300	-0.060	-0.359	-0.304	0.026	-0.187	-0.108	-0.022	-0.359	-0.238	-0.214	-0.221	0.049	-0.100	-0.458	0.227	-0.180	0.107	0.328	-0.031	-0.192	-0.350	-0.181	0.345	-0.306	0.065	0.153	0.011	-0.404	-0.417	-0.083	-0.153	-0.047	-0.136	-0.085	-0.383	-0.322	-0.330	-0.260	0.131	0.083	-0.242	-0.486	-0.202	0.000	-0.180
superpixels_0p85	-0.105	-0.536	-0.243	-0.735	-0.340	-0.777	-0.438	-0.339	-0.527	-0.278	-0.574	-0.352	-0.623	-0.289	-0.383	-0.682	-0.656	-0.727	-0.748	-0.669	-0.866	-0.847	0.152	-0.834	-0.131	-0.500	-0.103	-0.043	-0.661	-0.102	-0.259	-0.182	-0.067	-0.421	-0.300	-0.060	-0.359	-0.304	0.673	-0.225	-0.402	0.021	-0.359	-0.238	-0.214	-0.358	-0.582	-0.411	-0.458	0.553	-0.261	-0.276	-0.472	-0.531	-0.322	-0.293	-0.264	-0.568	-0.257	-0.713	-0.419	0.274	-0.475	-0.628	-0.083	-0.153	0.057	-0.136	-0.187	-0.614	-0.322	-0.420	0.278	0.037	-0.253	-0.303	-0.486	-0.388	0.000	-0.180
colorspace_25	0.039	-0.080	0.072	0.007	0.007	0.014	0.009	-0.015	0.057	-0.045	0.036	0.214	0.035	-0.057	-0.044	-0.023	-0.022	0.043	-0.168	-0.021	-0.043	-0.063	0.066	0.023	0.032	-0.180	-0.037	-0.043	-0.108	-0.048	-0.045	-0.182	-0.005	-0.181	-0.186	-0.060	0.042	0.206	0.102	0.006	0.147	-0.092	0.008	0.065	0.109	-0.041	-0.098	-0.234	0.057	0.244	-0.162	-0.276	0.528	-0.009	0.069	-0.168	0.001	0.094	-0.137	0.070	0.042	-0.037	0.027	0.101	0.021	-0.019	0.044	-0.036	0.042	0.086	-0.322	-0.048	0.014	0.045	0.091	-0.025	0.014	0.041	0.000	-0.038
colorspace_50	0.048	-0.085	0.053	0.039	-0.024	0.019	-0.013	0.002	0.046	-0.020	-0.002	0.159	0.025	-0.119	-0.005	0.014	-0.044	-0.037	-0.178	-0.003	-0.047	-0.175	0.066	0.014	0.040	-0.204	-0.057	-0.043	-0.179	-0.052	-0.052	-0.182	0.037	-0.132	-0.215	-0.060	0.028	0.148	0.080	-0.005	0.154	-0.094	-0.022	0.034	0.093	0.004	0.076	-0.171	0.167	0.370	-0.189	-0.276	-0.472	-0.032	0.158	-0.223	0.009	0.125	-0.162	0.023	0.027	-0.018	0.004	0.114	0.008	-0.065	0.030	-0.011	0.251	0.115	-0.322	-0.041	0.056	0.067	0.081	-0.007	0.129	0.038	0.000	-0.019
averageblur_5_11	0.036	-0.080	0.054	0.072	0.057	-0.046	-0.073	0.035	0.117	0.008	-0.042	0.156	-0.012	-0.049	0.094	-0.080	-0.129	0.042	-0.134	-0.047	-0.079	-0.116	0.054	0.022	-0.008	-0.009	0.044	-0.007	-0.094	-0.008	0.008	-0.182	-0.029	-0.030	-0.300	-0.060	0.003	0.309	0.018	0.093	0.263	0.005	0.038	0.037	0.069	0.001	0.073	-0.232	-0.155	0.070	-0.011	0.063	0.170	-0.054	0.088	-0.117	-0.020	0.128	-0.064	0.013	0.015	0.077	-0.091	-0.029	0.186	-0.072	-0.022	0.002	0.033	0.064	-0.322	-0.097	-0.052	0.037	0.092	0.044	-0.219	0.153	0.000	0.110
medianblur_1	0.005	0.121	0.040	0.037	0.041	-0.013	-0.158	0.058	0.061	-0.032	0.012	0.078	0.235	0.020	-0.175	-0.009	-0.210	-0.025	-0.048	-0.178	-0.104	-0.118	0.106	0.044	0.030	-0.151	0.021	0.024	-0.130	-0.070	-0.052	-0.182	-0.017	-0.241	-0.300	-0.060	0.017	0.176	0.060	0.075	0.187	-0.069	0.094	0.012	0.020	0.006	-0.084	-0.092	0.014	0.163	0.013	0.011	0.100	-0.076	-0.027	-0.118	-0.012	0.156	-0.023	-0.057	0.016	0.007	-0.131	0.099	0.083	-0.045	0.013	-0.059	0.057	-0.035	-0.322	-0.067	-0.084	0.000	0.203	-0.038	-0.153	0.022	0.000	0.008
sharpen_0	0.024	-0.141	0.033	0.009	0.014	0.024	-0.084	-0.004	-0.008	0.025	0.017	0.083	0.113	-0.095	-0.072	0.006	-0.043	0.019	-0.193	0.001	-0.058	-0.039	0.041	-0.038	0.030	-0.173	-0.005	0.007	-0.154	-0.043	-0.023	-0.182	-0.005	-0.082	-0.124	-0.060	0.033	0.154	0.058	0.051	0.141	-0.054	-0.026	0.139	-0.013	0.041	-0.044	-0.255	-0.294	0.080	0.030	0.037	0.274	-0.010	0.020	-0.212	-0.006	0.000	-0.043	0.135	0.043	0.094	0.013	0.171	0.045	-0.042	0.006	-0.008	0.127	0.057	-0.322	-0.077	-0.135	0.009	0.073	-0.031	-0.133	0.033	0.000	-0.180
sharpen_1	0.024	-0.059	0.025	0.042	0.087	-0.021	-0.048	-0.041	-0.001	0.013	-0.039	0.106	0.054	-0.039	-0.014	-0.012	-0.061	-0.057	-0.174	0.013	-0.055	0.028	0.039	-0.019	0.044	-0.155	0.005	-0.043	-0.162	-0.027	-0.046	-0.182	0.013	0.024	-0.092	-0.060	0.049	0.208	0.112	0.057	0.144	-0.023	-0.058	0.120	-0.008	0.029	-0.028	-0.192	-0.076	0.046	0.054	-0.030	0.249	-0.045	0.048	-0.129	0.012	0.048	-0.057	0.054	0.046	0.058	-0.014	0.121	0.086	0.066	-0.011	-0.044	0.278	0.124	-0.322	-0.046	-0.078	0.021	0.087	-0.018	-0.159	0.069	0.000	0.014
sharpen_2	0.017	-0.165	0.028	-0.006	0.034	0.022	-0.087	-0.039	0.056	0.015	-0.026	0.075	0.079	-0.044	0.005	0.013	-0.069	-0.013	-0.197	-0.044	-0.058	-0.038	0.034	-0.030	0.018	-0.144	-0.013	-0.008	-0.133	-0.027	0.018	-0.182	-0.003	-0.085	-0.210	-0.060	-0.017	0.149	0.030	0.059	0.200	-0.020	-0.030	0.009	0.095	0.025	-0.059	-0.085	-0.136	0.098	0.023	-0.020	0.180	-0.020	0.090	-0.179	-0.008	0.066	-0.097	0.056	0.035	0.102	0.029	0.190	0.041	-0.001	0.085	-0.020	0.125	0.103	-0.322	-0.035	-0.095	0.007	0.062	-0.033	-0.065	0.019	0.000	0.190
addintensity_-80	0.011	-0.054	0.002	0.060	-0.012	0.042	-0.055	-0.003	-0.052	0.006	-0.069	0.111	-0.093	-0.049	0.007	-0.063	-0.079	-0.080	-0.087	-0.039	0.004	-0.131	0.076	0.034	0.059	-0.083	0.022	-0.017	-0.022	-0.022	-0.088	-0.182	0.030	-0.053	-0.236	-0.060	-0.016	0.197	0.088	-0.032	0.188	-0.122	-0.059	-0.022	0.001	0.030	-0.049	-0.221	-0.183	0.043	0.023	0.084	0.078	-0.033	0.078	-0.078	0.012	0.151	-0.118	0.085	0.034	0.032	-0.095	0.051	0.004	-0.076	-0.035	-0.038	-0.020	0.006	-0.322	-0.092	-0.121	-0.007	0.051	-0.067	-0.131	0.121	0.000	0.037
addintensity_80	0.029	-0.025	0.034	0.050	-0.007	-0.011	-0.051	-0.013	0.026	0.038	0.004	0.053	0.068	-0.042	0.027	0.009	-0.104	0.002	-0.103	-0.050	-0.091	-0.026	0.065	0.002	0.019	-0.172	0.020	0.050	-0.091	-0.041	-0.084	-0.182	0.049	-0.083	-0.228	0.008	0.051	0.189	0.139	0.035	0.135	-0.059	-0.006	-0.003	0.066	0.005	-0.016	-0.143	-0.048	0.137	0.062	-0.003	-0.062	-0.023	0.037	-0.071	0.012	-0.069	-0.096	0.053	-0.016	0.042	0.012	0.136	0.061	-0.016	0.031	0.003	-0.018	0.153	-0.322	-0.078	-0.028	0.045	0.080	-0.013	-0.149	0.092	0.000	-0.118
elementrandomintensity_1	-0.087	-0.039	-0.028	0.129	0.145	0.013	0.113	-0.096	-0.135	-0.082	-0.251	0.116	-0.286	-0.182	-0.093	-0.096	-0.138	-0.169	-0.259	-0.076	0.054	-0.097	0.089	-0.028	-0.023	-0.293	0.026	-0.014	-0.174	-0.059	-0.073	-0.182	-0.067	0.068	-0.300	-0.060	0.055	0.055	0.082	-0.042	0.204	-0.055	0.279	-0.050	0.064	-0.002	-0.088	-0.380	-0.458	0.013	-0.191	-0.177	0.329	-0.136	-0.411	-0.305	-0.095	0.190	-0.220	0.016	0.070	-0.133	-0.093	0.204	-0.083	-0.153	0.123	-0.136	0.591	0.249	-0.322	-0.184	0.028	0.173	0.008	-0.015	-0.236	-0.196	0.000	-0.180
multiplyintensity_0p25	0.047	-0.044	0.090	0.131	0.045	0.040	0.022	0.089	0.073	-0.002	0.065	0.203	0.151	-0.043	0.051	-0.108	-0.035	-0.101	-0.129	-0.036	-0.025	0.041	0.071	0.036	0.020	-0.060	0.051	0.012	-0.067	-0.024	-0.041	-0.182	-0.018	-0.043	-0.180	-0.060	0.000	0.221	0.091	0.037	0.269	-0.048	0.160	0.065	0.060	0.069	0.059	-0.168	-0.164	0.169	0.064	0.054	0.258	-0.006	0.053	-0.141	0.011	0.045	-0.124	-0.093	0.123	-0.086	-0.114	0.116	0.022	-0.063	0.049	0.055	0.010	0.121	-0.322	-0.076	-0.063	0.055	0.090	-0.007	-0.213	0.009	0.000	0.159
multiplyintensity_2	0.013	0.020	0.028	0.038	-0.030	0.013	-0.066	0.047	0.027	-0.013	-0.017	0.034	0.062	-0.086	0.002	-0.008	-0.077	-0.051	-0.150	-0.039	-0.075	-0.045	0.081	0.004	0.041	-0.199	0.034	-0.013	-0.042	-0.033	-0.097	-0.182	0.008	-0.071	-0.221	-0.060	0.033	0.117	0.129	-0.021	0.128	-0.073	0.051	0.040	0.019	-0.010	-0.100	-0.209	-0.031	0.023	0.059	0.008	0.059	-0.061	-0.040	-0.138	0.003	-0.020	-0.096	0.048	0.030	0.090	0.023	0.138	0.101	-0.021	0.044	0.001	-0.011	0.012	-0.322	-0.051	0.008	0.012	0.094	0.010	-0.253	0.074	0.000	0.144
contrastnormalization_0	0.036	-0.085	0.061	0.018	0.074	-0.023	-0.038	-0.007	0.053	0.023	-0.069	0.069	0.015	-0.052	0.014	0.046	-0.003	-0.056	-0.162	0.001	-0.034	-0.057	0.059	0.057	0.042	-0.144	0.049	0.047	-0.044	-0.040	-0.047	-0.182	-0.008	-0.097	-0.138	-0.060	0.081	0.167	0.078	0.032	0.102	-0.091	-0.044	-0.011	0.069	0.024	0.031	-0.193	-0.239	0.084	0.033	0.004	0.176	0.013	0.069	-0.023	0.006	0.106	-0.088	0.131	0.007	0.037	-0.014	0.094	0.012	0.017	0.045	-0.029	0.145	0.047	-0.322	-0.046	-0.093	0.063	0.089	-0.049	0.068	0.125	0.000	-0.019
contrastnormalization_1	0.030	-0.068	0.029	0.039	0.015	-0.041	-0.050	0.057	0.004	-0.013	-0.022	0.114	0.044	-0.077	0.020	0.029	-0.034	0.009	-0.147	-0.050	-0.035	-0.169	0.076	-0.003	0.086	-0.140	-0.016	0.017	-0.046	-0.039	-0.079	-0.182	0.016	-0.093	0.022	-0.060	0.030	0.189	0.099	0.019	0.194	-0.080	-0.060	0.065	0.012	0.018	-0.008	-0.137	-0.122	0.123	0.013	0.007	0.249	-0.019	-0.000	-0.070	0.014	0.074	-0.114	0.042	0.008	0.020	0.052	0.105	-0.083	-0.047	0.041	0.020	0.093	0.106	-0.322	-0.050	-0.126	0.046	0.117	-0.043	-0.075	0.120	0.000	-0.031
contrastnormalization_2	0.033	-0.058	0.044	0.082	-0.007	-0.004	-0.005	0.023	0.001	0.020	0.014	0.168	-0.003	-0.071	0.006	0.037	-0.049	-0.034	-0.160	-0.034	-0.004	-0.091	0.069	-0.018	0.067	-0.186	0.093	0.049	-0.045	-0.030	-0.059	-0.182	0.017	-0.055	-0.100	-0.060	0.040	0.191	0.111	-0.014	0.140	-0.076	-0.067	0.030	0.072	-0.004	-0.062	-0.205	-0.218	0.115	0.026	0.026	0.040	-0.025	0.052	-0.102	0.029	0.042	-0.112	0.067	-0.005	0.052	0.024	0.113	0.075	-0.009	0.066	-0.012	0.250	0.204	-0.322	-0.044	-0.135	0.015	0.096	-0.039	-0.076	0.115	0.000	0.015
elastic_1	-0.142	-0.536	-0.139	-0.735	-0.768	-0.214	0.124	0.112	-0.351	-0.074	-0.422	0.147	-0.073	-0.223	0.523	-0.191	-0.352	-0.341	-0.132	-0.305	-0.351	-0.459	-0.070	0.066	-0.131	-0.305	-0.103	-0.043	-0.661	-0.053	-0.116	-0.182	-0.067	-0.278	-0.300	-0.060	-0.359	-0.125	0.173	0.322	0.598	0.078	-0.359	-0.238	0.786	0.066	0.133	-0.251	-0.458	-0.004	-0.224	-0.004	0.528	0.096	-0.362	-0.321	-0.091	0.432	-0.312	-0.213	0.174	-0.005	-0.053	0.372	-0.083	0.847	-0.443	-0.136	-0.409	-0.614	-0.322	-0.134	-0.722	-0.297	-0.364	0.268	-0.486	-0.105	0.000	-0.180
scaled_1p25	0.063	-0.030	0.073	0.018	0.033	0.060	0.053	0.064	0.043	0.098	-0.022	0.260	0.103	-0.039	0.116	0.102	0.016	0.041	-0.095	-0.016	0.016	-0.071	0.087	0.124	0.055	-0.037	0.031	0.207	0.082	0.298	0.091	-0.096	0.121	-0.018	0.060	-0.060	0.088	0.257	0.147	0.042	0.137	-0.009	-0.017	0.142	0.015	-0.020	0.146	-0.164	-0.017	0.087	0.109	0.182	0.080	0.105	-0.002	0.128	-0.016	-0.004	-0.071	-0.047	0.086	0.049	0.093	0.076	0.119	-0.134	0.033	0.065	0.014	0.026	-0.322	0.113	-0.072	0.137	0.215	-0.093	-0.217	0.150	0.000	-0.037
scaled_0p75	-0.078	-0.096	-0.191	-0.055	-0.031	-0.052	0.048	-0.020	-0.118	-0.152	-0.102	0.067	-0.090	-0.108	0.026	-0.077	-0.082	-0.058	-0.298	-0.092	-0.097	-0.036	-0.014	-0.024	-0.095	-0.166	-0.067	-0.043	-0.146	-0.102	-0.077	-0.182	-0.067	-0.084	-0.300	-0.060	-0.102	0.021	-0.257	-0.124	-0.174	-0.220	-0.212	-0.056	-0.172	-0.144	-0.021	-0.250	-0.082	-0.169	-0.140	0.031	-0.012	-0.081	0.020	-0.104	-0.125	0.053	-0.222	-0.005	-0.041	-0.151	-0.151	0.029	0.007	-0.092	-0.152	-0.104	-0.210	-0.073	-0.322	-0.258	-0.023	-0.068	-0.039	-0.173	0.085	0.022	0.000	-0.031
scaled_0p5	-0.205	-0.188	-0.270	-0.133	-0.211	-0.206	-0.093	-0.045	-0.318	-0.228	-0.238	-0.175	-0.062	-0.122	-0.145	-0.116	-0.241	-0.174	-0.352	-0.193	-0.241	-0.206	-0.164	-0.147	-0.104	-0.285	-0.103	-0.043	-0.218	-0.102	-0.191	-0.182	-0.067	-0.331	-0.300	-0.060	-0.341	-0.051	-0.304	-0.158	-0.287	-0.269	-0.266	-0.238	-0.120	-0.207	-0.114	-0.227	-0.174	-0.304	-0.323	-0.184	-0.147	-0.162	-0.220	-0.080	-0.248	-0.176	-0.288	-0.013	0.003	-0.331	-0.345	-0.151	-0.083	-0.101	-0.406	-0.052	-0.027	-0.227	-0.322	-0.301	-0.101	-0.173	-0.148	-0.065	0.264	-0.170	0.000	0.173
scaled_(1p25, 1p0)	0.062	0.057	0.015	-0.009	0.053	0.037	0.008	0.049	0.046	0.039	0.003	0.072	-0.023	-0.050	0.037	0.110	-0.052	0.044	-0.117	0.038	0.035	0.017	0.056	0.112	0.111	-0.096	0.075	0.156	-0.017	0.098	-0.006	-0.100	0.051	-0.070	-0.086	-0.060	0.075	0.188	0.079	0.056	0.267	-0.039	-0.026	0.137	0.088	0.041	0.097	-0.188	0.048	0.060	0.125	0.077	0.190	-0.060	0.092	0.058	-0.009	0.037	-0.108	-0.006	0.016	0.071	0.051	0.105	0.105	0.009	-0.006	-0.001	0.042	0.084	-0.322	0.034	-0.027	0.127	0.098	-0.037	-0.259	0.083	0.000	-0.024
scaled_(0p75, 1p0)	-0.028	-0.029	-0.133	-0.043	0.008	-0.055	-0.005	-0.002	-0.018	-0.137	-0.019	0.080	0.104	-0.033	0.049	-0.005	-0.117	-0.036	-0.241	-0.010	-0.094	-0.063	0.038	-0.038	-0.072	-0.145	-0.029	0.044	-0.113	-0.102	-0.072	-0.182	-0.001	-0.105	-0.163	-0.060	-0.057	0.149	-0.026	-0.060	0.051	-0.157	-0.091	-0.048	-0.108	-0.042	-0.075	-0.109	-0.150	-0.094	-0.034	0.029	0.163	0.014	0.038	-0.094	-0.104	0.048	-0.156	0.057	-0.024	-0.088	-0.052	0.064	0.021	-0.084	-0.050	-0.061	0.147	-0.002	-0.322	-0.157	-0.070	-0.076	-0.037	-0.058	0.014	0.058	0.000	0.023
scaled_(1p0, 1p25)	0.038	-0.007	0.072	0.033	0.054	0.038	0.004	0.050	0.114	0.126	-0.012	0.128	0.113	0.017	0.039	0.095	-0.020	-0.036	-0.141	0.001	-0.034	-0.047	0.080	0.048	0.067	-0.067	0.046	0.077	0.048	0.079	0.005	-0.095	0.039	0.017	-0.047	-0.060	0.048	0.250	0.062	0.001	0.135	-0.077	-0.083	0.088	0.043	0.034	0.099	-0.113	0.002	0.026	0.095	0.065	0.081	0.060	0.006	-0.030	-0.022	-0.013	-0.054	0.016	0.123	0.011	0.052	0.084	-0.009	-0.031	0.066	0.051	0.317	0.105	-0.322	0.055	-0.006	0.054	0.155	-0.041	-0.275	0.158	0.000	0.060
scaled_(1p0, 0p75)	-0.003	-0.025	-0.061	-0.015	-0.066	0.008	-0.018	0.085	-0.045	-0.094	-0.015	0.051	-0.046	-0.045	-0.011	-0.019	0.013	0.036	-0.189	0.001	-0.041	0.006	-0.018	-0.019	-0.006	-0.236	-0.025	-0.010	-0.055	-0.028	-0.094	-0.182	0.001	-0.078	-0.227	-0.002	-0.066	0.086	-0.040	-0.033	0.038	-0.126	-0.072	-0.041	-0.031	-0.084	-0.084	-0.211	-0.149	0.031	-0.057	0.015	0.062	-0.104	-0.075	-0.019	-0.032	-0.010	-0.090	-0.027	-0.032	-0.028	-0.076	0.033	0.014	-0.066	0.003	-0.049	-0.199	0.076	-0.322	-0.081	-0.042	-0.015	0.014	-0.029	-0.042	0.014	0.000	0.002
translate_(0p1, 0p1)	-0.020	-0.219	-0.128	-0.042	-0.024	-0.001	0.023	-0.020	-0.023	-0.149	0.067	0.104	-0.026	-0.112	0.011	-0.074	-0.042	-0.040	-0.217	-0.053	-0.047	-0.058	0.032	0.038	-0.109	-0.165	-0.074	0.022	-0.087	-0.038	-0.085	-0.182	0.020	-0.044	-0.184	-0.060	-0.065	0.093	-0.055	-0.106	-0.111	-0.179	-0.073	0.007	-0.131	-0.037	-0.066	-0.157	-0.063	-0.128	-0.095	0.034	0.142	-0.013	0.053	-0.093	-0.099	0.060	-0.204	0.025	0.021	-0.062	-0.096	0.005	0.007	-0.092	-0.027	-0.104	0.063	0.020	-0.322	-0.160	-0.039	-0.001	-0.052	-0.098	-0.101	0.017	0.000	0.034
translate_(0p1, -0p1)	0.019	-0.042	-0.009	-0.015	0.085	0.012	0.025	0.006	0.097	0.046	0.056	0.137	-0.012	-0.023	0.018	0.007	-0.008	-0.093	-0.159	-0.010	-0.003	-0.047	0.068	0.064	0.010	0.007	-0.006	0.055	-0.072	0.025	-0.057	-0.094	0.000	-0.022	-0.081	-0.060	0.028	0.220	0.015	-0.025	0.011	-0.108	0.003	-0.026	0.037	0.015	0.006	-0.236	-0.002	-0.003	0.060	0.032	0.141	0.078	0.083	-0.076	-0.071	0.000	-0.055	0.020	-0.003	-0.066	-0.010	0.073	0.012	-0.059	-0.056	0.001	0.136	0.073	-0.322	-0.014	-0.124	0.068	0.029	0.024	-0.178	0.105	0.000	0.079
translate_(-0p1, 0p1)	0.028	-0.052	-0.055	0.060	0.033	0.027	0.041	0.052	0.053	-0.108	0.005	0.165	0.012	-0.080	0.043	0.050	-0.063	0.037	-0.141	-0.001	-0.022	0.077	0.037	0.029	0.007	-0.146	0.044	0.170	0.058	0.014	-0.053	-0.182	0.062	0.005	-0.232	-0.060	0.025	0.198	0.081	0.029	0.137	-0.116	-0.139	0.075	0.076	-0.045	-0.017	-0.141	-0.097	-0.004	0.018	0.054	0.244	0.009	0.109	0.056	-0.012	0.026	-0.118	0.088	0.014	0.062	-0.071	0.046	0.073	-0.043	-0.049	-0.011	0.079	-0.012	-0.322	-0.063	0.054	0.116	0.022	-0.118	-0.177	0.082	0.000	0.015
translate_(-0p1, -0p1)	0.063	-0.056	0.036	0.050	0.073	0.049	0.043	0.086	0.090	0.154	-0.001	0.255	0.214	0.013	0.096	0.160	0.054	0.033	-0.129	0.041	0.018	0.074	0.084	0.064	0.073	-0.045	0.081	0.188	0.055	0.307	0.016	-0.016	0.094	0.045	-0.009	0.004	0.042	0.251	0.132	0.034	0.152	-0.035	-0.089	0.114	0.136	0.067	0.126	-0.122	0.064	0.080	0.123	0.139	0.290	0.093	0.063	0.118	0.036	0.077	-0.046	0.090	0.033	0.052	0.085	0.094	0.045	-0.086	0.084	0.030	0.139	0.095	-0.322	0.066	-0.002	0.116	0.190	-0.062	-0.223	0.094	0.000	-0.025
translate_(0p1, 0)	-0.001	-0.074	-0.082	0.009	0.001	0.003	0.010	-0.015	0.029	-0.082	0.022	0.080	-0.038	-0.051	0.012	-0.031	-0.074	0.008	-0.204	-0.032	-0.013	-0.020	0.059	0.023	-0.053	-0.117	-0.022	0.022	-0.119	-0.034	-0.051	-0.182	0.010	-0.040	-0.188	-0.060	-0.021	0.125	-0.000	-0.070	0.064	-0.117	0.026	0.022	0.020	-0.030	-0.031	-0.225	-0.027	-0.081	-0.052	0.006	0.132	0.006	0.126	-0.118	-0.078	0.040	-0.126	0.008	-0.036	-0.054	-0.032	0.065	-0.004	-0.050	-0.069	-0.051	0.058	0.056	-0.322	-0.060	-0.083	0.027	0.021	-0.073	-0.299	0.055	0.000	0.053
translate_(-0p1, 0)	0.042	0.028	-0.034	0.073	0.071	0.015	0.005	0.039	0.053	0.035	0.005	0.108	0.018	-0.045	0.068	0.119	-0.023	0.089	-0.140	0.071	-0.020	0.067	0.080	0.059	0.070	-0.118	0.066	0.163	0.050	0.131	-0.056	-0.101	0.013	-0.017	-0.065	-0.060	0.086	0.242	0.120	0.094	0.192	-0.043	-0.052	0.103	0.054	0.016	0.087	-0.091	0.059	0.072	0.080	0.075	0.232	0.005	0.161	0.055	0.015	0.063	-0.102	0.086	0.009	0.078	0.016	0.121	0.047	-0.043	-0.027	0.019	0.017	0.142	-0.322	0.030	-0.013	0.092	0.122	-0.108	-0.252	0.072	0.000	0.007
translate_(0, 0p1)	0.005	-0.109	-0.052	0.035	0.004	0.006	-0.040	0.018	0.029	-0.128	0.055	0.033	0.039	-0.081	0.004	0.017	-0.080	-0.013	-0.132	-0.037	-0.042	0.016	0.057	-0.005	-0.001	-0.230	-0.026	0.019	-0.056	-0.036	-0.081	-0.182	0.035	-0.043	-0.173	0.003	-0.023	0.200	0.033	-0.051	0.036	-0.091	-0.083	0.034	-0.029	-0.018	-0.078	-0.217	-0.072	-0.008	0.014	-0.003	0.121	-0.003	0.109	-0.024	-0.030	0.019	-0.112	0.037	0.026	0.004	-0.074	0.066	0.076	0.011	0.023	-0.037	0.027	0.050	-0.322	-0.078	-0.111	0.031	-0.013	0.027	-0.141	0.073	0.000	0.023
translate_(0, -0p1)	0.037	0.013	0.065	0.043	0.068	0.033	-0.020	0.063	0.096	0.134	0.019	0.155	0.036	0.036	0.074	0.084	0.001	-0.033	-0.163	0.008	-0.021	0.018	0.069	0.055	0.059	-0.075	0.043	0.046	-0.016	0.081	-0.045	-0.095	0.046	0.031	-0.087	-0.008	0.057	0.252	0.078	0.016	0.088	-0.063	-0.073	0.092	0.207	-0.007	0.064	-0.199	-0.021	0.128	0.117	0.032	0.262	0.064	0.026	0.065	0.040	0.017	-0.037	0.083	0.020	0.016	0.007	0.089	-0.004	-0.053	0.073	0.089	0.186	0.032	-0.322	0.021	-0.078	0.038	0.136	0.048	-0.129	0.071	0.000	0.035
rotated_3	0.035	0.049	0.049	0.058	0.010	0.054	0.013	0.050	0.097	0.006	0.047	0.103	0.029	-0.015	0.084	0.058	-0.036	0.025	-0.159	-0.022	0.002	-0.063	0.060	0.058	0.040	-0.115	0.089	0.095	0.021	-0.035	0.009	-0.088	0.047	0.031	-0.141	-0.060	0.070	0.228	0.092	0.009	0.129	-0.029	-0.031	0.105	0.017	0.032	0.010	-0.142	-0.083	-0.006	0.073	0.049	0.169	0.026	0.053	0.066	0.008	0.037	-0.080	0.031	0.029	0.025	0.001	0.118	0.097	0.041	0.029	-0.018	0.097	0.056	-0.322	-0.058	-0.054	0.031	0.079	-0.075	-0.208	0.101	0.000	-0.005