Breast Cancer Classification and Evaluation#

The Breast Cancer dataset is a well-suited example for demonstrating CyclOps features due to its two distinct classes (binary classification) and complete absence of missing values. This clean and organized structure makes it an ideal starting point for exploring CyclOps Evaluator.

[1]:

import numpy as np
import pandas as pd
from datasets.arrow_dataset import Dataset
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC

from cyclops.data.slicer import SliceSpec
from cyclops.evaluate import evaluator
from cyclops.evaluate.fairness import evaluate_fairness
from cyclops.evaluate.metrics import BinaryAccuracy, create_metric
from cyclops.evaluate.metrics.experimental import BinaryAUROC, BinaryAveragePrecision
from cyclops.evaluate.metrics.experimental.metric_dict import MetricDict
from cyclops.report.plot.classification import ClassificationPlotter

/mnt/data/actions_runners/cyclops-actions-runner-1/_work/cyclops/cyclops/.venv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm

[2]:

# Loading the data
breast_cancer_data = datasets.load_breast_cancer(as_frame=True)
X, y = breast_cancer_data.data, breast_cancer_data.target

Features#

Just taking a quick look at features and their stats…

[3]:

df = breast_cancer_data.frame
df.describe().T

[3]:
count mean std min 25% 50% 75% max
mean radius 569.0 14.127292 3.524049 6.981000 11.700000 13.370000 15.780000 28.11000
mean texture 569.0 19.289649 4.301036 9.710000 16.170000 18.840000 21.800000 39.28000
mean perimeter 569.0 91.969033 24.298981 43.790000 75.170000 86.240000 104.100000 188.50000
mean area 569.0 654.889104 351.914129 143.500000 420.300000 551.100000 782.700000 2501.00000
mean smoothness 569.0 0.096360 0.014064 0.052630 0.086370 0.095870 0.105300 0.16340
mean compactness 569.0 0.104341 0.052813 0.019380 0.064920 0.092630 0.130400 0.34540
mean concavity 569.0 0.088799 0.079720 0.000000 0.029560 0.061540 0.130700 0.42680
mean concave points 569.0 0.048919 0.038803 0.000000 0.020310 0.033500 0.074000 0.20120
mean symmetry 569.0 0.181162 0.027414 0.106000 0.161900 0.179200 0.195700 0.30400
mean fractal dimension 569.0 0.062798 0.007060 0.049960 0.057700 0.061540 0.066120 0.09744
radius error 569.0 0.405172 0.277313 0.111500 0.232400 0.324200 0.478900 2.87300
texture error 569.0 1.216853 0.551648 0.360200 0.833900 1.108000 1.474000 4.88500
perimeter error 569.0 2.866059 2.021855 0.757000 1.606000 2.287000 3.357000 21.98000
area error 569.0 40.337079 45.491006 6.802000 17.850000 24.530000 45.190000 542.20000
smoothness error 569.0 0.007041 0.003003 0.001713 0.005169 0.006380 0.008146 0.03113
compactness error 569.0 0.025478 0.017908 0.002252 0.013080 0.020450 0.032450 0.13540
concavity error 569.0 0.031894 0.030186 0.000000 0.015090 0.025890 0.042050 0.39600
concave points error 569.0 0.011796 0.006170 0.000000 0.007638 0.010930 0.014710 0.05279
symmetry error 569.0 0.020542 0.008266 0.007882 0.015160 0.018730 0.023480 0.07895
fractal dimension error 569.0 0.003795 0.002646 0.000895 0.002248 0.003187 0.004558 0.02984
worst radius 569.0 16.269190 4.833242 7.930000 13.010000 14.970000 18.790000 36.04000
worst texture 569.0 25.677223 6.146258 12.020000 21.080000 25.410000 29.720000 49.54000
worst perimeter 569.0 107.261213 33.602542 50.410000 84.110000 97.660000 125.400000 251.20000
worst area 569.0 880.583128 569.356993 185.200000 515.300000 686.500000 1084.000000 4254.00000
worst smoothness 569.0 0.132369 0.022832 0.071170 0.116600 0.131300 0.146000 0.22260
worst compactness 569.0 0.254265 0.157336 0.027290 0.147200 0.211900 0.339100 1.05800
worst concavity 569.0 0.272188 0.208624 0.000000 0.114500 0.226700 0.382900 1.25200
worst concave points 569.0 0.114606 0.065732 0.000000 0.064930 0.099930 0.161400 0.29100
worst symmetry 569.0 0.290076 0.061867 0.156500 0.250400 0.282200 0.317900 0.66380
worst fractal dimension 569.0 0.083946 0.018061 0.055040 0.071460 0.080040 0.092080 0.20750
target 569.0 0.627417 0.483918 0.000000 0.000000 1.000000 1.000000 1.00000 
[4]:

# Splitting into train and test
X_train, X_test, y_train, y_test = train_test_split(
    X,
    y,
    test_size=0.1,
    random_state=13,
)

# Use SVM classifier for binary classification
svc = SVC(C=10, gamma=0.01, probability=True)
svc.fit(X_train, y_train)

# model predictions
y_pred = svc.predict(X_test)
y_pred_prob = svc.predict_proba(X_test)

Now we can use CyclOps evaluation metrics to evaluate our model’s performance. You can either use each metric individually by calling them, or define a MetricDict object. Here, we show both methods.

Individual Metrics#

In case you need only a single metric, you can create an object of the desired metric and call it on your ground truth and predictions:

[5]:

bin_acc_metric = BinaryAccuracy()
bin_acc_metric(y_test.values, np.float64(y_pred))

[5]:

0.7192982456140351

Using MetricDict#

You may define a collection of metrics in case you need more metrics. It also speeds up the metric calculation.

[6]:

metric_names = [
    "binary_accuracy",
    "binary_precision",
    "binary_recall",
    "binary_f1_score",
    "binary_roc_curve",
]
metrics = [
    create_metric(metric_name, experimental=True) for metric_name in metric_names
]
metric_collection = MetricDict(metrics)
metric_collection(y_test.values, np.float64(y_pred))

[6]:

{'BinaryAccuracy': array(0.71929824, dtype=float32),
 'BinaryPrecision': array(0.7090909, dtype=float32),
 'BinaryRecall': array(1., dtype=float32),
 'BinaryF1Score': array(0.82978725, dtype=float32),
 'BinaryROC': ROCCurve(fpr=array([0.       , 0.8888889, 1.       ], dtype=float32), tpr=array([0., 1., 1.], dtype=float32), thresholds=array([1., 1., 0.]))}

You may reset the metrics collection and add other metrics:

[7]:

metric_collection.reset()
metric_collection.add_metrics(BinaryAveragePrecision(), BinaryAUROC())
metric_collection(y_test.values, np.float64(y_pred))

[7]:

{'BinaryAccuracy': array(0.71929824, dtype=float32),
 'BinaryPrecision': array(0.7090909, dtype=float32),
 'BinaryRecall': array(1., dtype=float32),
 'BinaryF1Score': array(0.82978725, dtype=float32),
 'BinaryROC': ROCCurve(fpr=array([0.       , 0.8888889, 1.       ], dtype=float32), tpr=array([0., 1., 1.], dtype=float32), thresholds=array([1., 1., 0.])),
 'BinaryAveragePrecision': 0.7090909,
 'BinaryAUROC': 0.5555556}

Data Slicing#

In addition to overall metrics, it might be interesting to see how the model performs on certain subpopulation or subsets. We can define these subsets using SliceSpec objects.

[8]:

spec_list = [
    {
        "worst radius": {
            "min_value": 14.0,
            "max_value": 15.0,
            "min_inclusive": True,
            "max_inclusive": False,
        },
    },
    {
        "worst radius": {
            "min_value": 15.0,
            "max_value": 17.0,
            "min_inclusive": True,
            "max_inclusive": False,
        },
    },
    {
        "worst texture": {
            "min_value": 23.1,
            "max_value": 28.7,
            "min_inclusive": True,
            "max_inclusive": False,
        },
    },
]
slice_spec = SliceSpec(spec_list)

Intersectional slicing#

When subpopulation slices are specified using the SliceSpec, sometimes we wish create combinations of intersectional slices. We can use the intersections argument to specify this.

[9]:

slice_spec = SliceSpec(spec_list, intersections=2)
slice_spec

[9]:

SliceSpec(spec_list=[{'worst radius': {'min_value': 14.0, 'max_value': 15.0, 'min_inclusive': True, 'max_inclusive': False}}, {'worst radius': {'min_value': 15.0, 'max_value': 17.0, 'min_inclusive': True, 'max_inclusive': False}}, {'worst texture': {'min_value': 23.1, 'max_value': 28.7, 'min_inclusive': True, 'max_inclusive': False}}, {'worst radius': {'min_value': 14.0, 'max_value': 15.0, 'min_inclusive': True, 'max_inclusive': False}, 'worst texture': {'min_value': 23.1, 'max_value': 28.7, 'min_inclusive': True, 'max_inclusive': False}}, {'worst radius': {'min_value': 15.0, 'max_value': 17.0, 'min_inclusive': True, 'max_inclusive': False}, 'worst texture': {'min_value': 23.1, 'max_value': 28.7, 'min_inclusive': True, 'max_inclusive': False}}], intersections=2, validate=True, include_overall=True, column_names=None)

Preparing Result#

CyclOps Evaluator takes data as a HuggingFace Dataset object, so we combine predictions and features in a dataframe, and create a Dataset object:

[10]:

# Combine result and features for test data
df = pd.concat([X_test, pd.DataFrame(y_test, columns=["target"])], axis=1)
df["preds"] = y_pred
df["preds_prob"] = y_pred_prob[:, 1]

[11]:

# Create Dataset object
breast_cancer_data = Dataset.from_pandas(df)
breast_cancer_sliced_result = evaluator.evaluate(
    dataset=breast_cancer_data,
    metrics=metric_collection,  # type: ignore[list-item]
    target_columns="target",
    prediction_columns="preds_prob",
    slice_spec=slice_spec,
)







Filter -> worst radius:[14.0 - 15.0):   0%|          | 0/57 [00:00<?, ? examples/s]


</pre>






Filter -> worst radius:[14.0 - 15.0):   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> worst radius:[14.0 - 15.0):   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; worst radius:[14.0 - 15.0): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 3770.84 examples/s]


</pre>






Filter -> worst radius:[14.0 - 15.0): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 3770.84 examples/s]


end{sphinxVerbatim}








Filter -> worst radius:[14.0 - 15.0): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 3770.84 examples/s]






























Filter -&gt; worst radius:[15.0 - 17.0):   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> worst radius:[15.0 - 17.0):   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> worst radius:[15.0 - 17.0):   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; worst radius:[15.0 - 17.0): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4768.16 examples/s]


</pre>






Filter -> worst radius:[15.0 - 17.0): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4768.16 examples/s]


end{sphinxVerbatim}








Filter -> worst radius:[15.0 - 17.0): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4768.16 examples/s]






























Filter -&gt; worst texture:[23.1 - 28.7):   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> worst texture:[23.1 - 28.7):   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> worst texture:[23.1 - 28.7):   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; worst texture:[23.1 - 28.7): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4506.09 examples/s]


</pre>






Filter -> worst texture:[23.1 - 28.7): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4506.09 examples/s]


end{sphinxVerbatim}








Filter -> worst texture:[23.1 - 28.7): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4506.09 examples/s]






























Filter -&gt; worst radius:[14.0 - 15.0)&amp;worst texture:[23.1 - 28.7):   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> worst radius:[14.0 - 15.0)&worst texture:[23.1 - 28.7):   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> worst radius:[14.0 - 15.0)&worst texture:[23.1 - 28.7):   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; worst radius:[14.0 - 15.0)&amp;worst texture:[23.1 - 28.7): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4320.35 examples/s]


</pre>






Filter -> worst radius:[14.0 - 15.0)&worst texture:[23.1 - 28.7): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4320.35 examples/s]


end{sphinxVerbatim}








Filter -> worst radius:[14.0 - 15.0)&worst texture:[23.1 - 28.7): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4320.35 examples/s]











/mnt/data/actions_runners/cyclops-actions-runner-1/_work/cyclops/cyclops/cyclops/evaluate/metrics/experimental/functional/roc.py:74: UserWarning:

No negative samples in targets false positive value should be meaningless. Returning an array of 0s instead.




















Filter -&gt; worst radius:[15.0 - 17.0)&amp;worst texture:[23.1 - 28.7):   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> worst radius:[15.0 - 17.0)&worst texture:[23.1 - 28.7):   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> worst radius:[15.0 - 17.0)&worst texture:[23.1 - 28.7):   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; worst radius:[15.0 - 17.0)&amp;worst texture:[23.1 - 28.7): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4171.25 examples/s]


</pre>






Filter -> worst radius:[15.0 - 17.0)&worst texture:[23.1 - 28.7): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4171.25 examples/s]


end{sphinxVerbatim}








Filter -> worst radius:[15.0 - 17.0)&worst texture:[23.1 - 28.7): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4171.25 examples/s]






























Filter -&gt; overall:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> overall:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> overall:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; overall: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5114.90 examples/s]


</pre>






Filter -> overall: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5114.90 examples/s]


end{sphinxVerbatim}








Filter -> overall: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5114.90 examples/s]
















We can visualize the BinaryF1Score and BinaryPrecision for the different slices




[12]:





# Extracting the metric values for all the slices.
slice_metrics = {
    slice_name: {
        metric_name: metric_value
        for metric_name, metric_value in slice_results.items()
        if metric_name in ["BinaryF1Score", "BinaryPrecision"]
    }
    for slice_name, slice_results in breast_cancer_sliced_result[
        "model_for_preds_prob"
    ].items()
}
# Plotting the metric values for all the slices.
plotter = ClassificationPlotter(task_type="binary", class_names=["0", "1"])
plotter.set_template("plotly_white")
slice_metrics_plot = plotter.metrics_comparison_bar(slice_metrics)
slice_metrics_plot.show()














        












                            
                    








Fairness Evaluator#


The Breast Cancer dataset may not be a very good example to apply fairness, but to demonstrate how you can use our fairness evaluator, we apply it to mean texture feature. It’s recommended to use it on features with discrete values. For optimal results, the feature should have less than 50 unique categories.




[13]:





fairness_result = evaluate_fairness(
    dataset=breast_cancer_data,
    metrics="binary_precision",  # type: ignore[list-item]
    groups="mean texture",
    target_columns="target",
    prediction_columns="preds_prob",
)
fairness_result















2024-07-16 16:53:07,812 WARNING cyclops.evaluate.fairness.evaluator - The number of unique values for the group is greater than 50. This may take a long time to compute. Consider binning the values into fewer groups.



















Filter -&gt; mean texture:16.93:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:16.93:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:16.93:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:16.93: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4900.59 examples/s]


</pre>






Filter -> mean texture:16.93: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4900.59 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:16.93: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4900.59 examples/s]






























Filter -&gt; mean texture:13.32:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:13.32:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:13.32:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:13.32: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4870.64 examples/s]


</pre>






Filter -> mean texture:13.32: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4870.64 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:13.32: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4870.64 examples/s]






























Filter -&gt; mean texture:21.41:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:21.41:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:21.41:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:21.41: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5148.82 examples/s]


</pre>






Filter -> mean texture:21.41: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5148.82 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:21.41: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5148.82 examples/s]






























Filter -&gt; mean texture:21.81:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:21.81:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:21.81:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:21.81: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5073.65 examples/s]


</pre>






Filter -> mean texture:21.81: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5073.65 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:21.81: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5073.65 examples/s]











/mnt/data/actions_runners/cyclops-actions-runner-1/_work/cyclops/cyclops/cyclops/evaluate/metrics/experimental/utils/ops.py:530: RuntimeWarning:

invalid value encountered in divide




















Filter -&gt; mean texture:18.89:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:18.89:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:18.89:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:18.89: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4913.99 examples/s]


</pre>






Filter -> mean texture:18.89: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4913.99 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:18.89: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4913.99 examples/s]






























Filter -&gt; mean texture:18.83:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:18.83:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:18.83:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:18.83: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5072.57 examples/s]


</pre>






Filter -> mean texture:18.83: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5072.57 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:18.83: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5072.57 examples/s]






























Filter -&gt; mean texture:15.98:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:15.98:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:15.98:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:15.98: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5123.56 examples/s]


</pre>






Filter -> mean texture:15.98: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5123.56 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:15.98: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5123.56 examples/s]






























Filter -&gt; mean texture:12.84:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:12.84:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:12.84:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:12.84: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5034.44 examples/s]


</pre>






Filter -> mean texture:12.84: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5034.44 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:12.84: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5034.44 examples/s]






























Filter -&gt; mean texture:18.54:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:18.54:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:18.54:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:18.54: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4930.91 examples/s]


</pre>






Filter -> mean texture:18.54: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4930.91 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:18.54: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4930.91 examples/s]






























Filter -&gt; mean texture:14.74:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:14.74:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:14.74:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:14.74: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4972.24 examples/s]


</pre>






Filter -> mean texture:14.74: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4972.24 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:14.74: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4972.24 examples/s]






























Filter -&gt; mean texture:20.7:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:20.7:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:20.7:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:20.7: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4717.72 examples/s]


</pre>






Filter -> mean texture:20.7: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4717.72 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:20.7: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4717.72 examples/s]






























Filter -&gt; mean texture:23.93:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:23.93:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:23.93:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:23.93: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4983.54 examples/s]


</pre>






Filter -> mean texture:23.93: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4983.54 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:23.93: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4983.54 examples/s]






























Filter -&gt; mean texture:14.08:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:14.08:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:14.08:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:14.08: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5029.99 examples/s]


</pre>






Filter -> mean texture:14.08: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5029.99 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:14.08: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5029.99 examples/s]






























Filter -&gt; mean texture:26.47:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:26.47:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:26.47:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:26.47: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4997.71 examples/s]


</pre>






Filter -> mean texture:26.47: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4997.71 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:26.47: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4997.71 examples/s]






























Filter -&gt; mean texture:23.81:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:23.81:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:23.81:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:23.81: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4909.75 examples/s]


</pre>






Filter -> mean texture:23.81: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4909.75 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:23.81: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4909.75 examples/s]






























Filter -&gt; mean texture:10.94:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:10.94:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:10.94:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:10.94: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5072.68 examples/s]


</pre>






Filter -> mean texture:10.94: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5072.68 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:10.94: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5072.68 examples/s]






























Filter -&gt; mean texture:16.67:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:16.67:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:16.67:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:16.67: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5009.96 examples/s]


</pre>






Filter -> mean texture:16.67: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5009.96 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:16.67: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5009.96 examples/s]






























Filter -&gt; mean texture:17.43:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:17.43:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:17.43:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:17.43: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4972.03 examples/s]


</pre>






Filter -> mean texture:17.43: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4972.03 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:17.43: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4972.03 examples/s]






























Filter -&gt; mean texture:15.04:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:15.04:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:15.04:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:15.04: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5096.69 examples/s]


</pre>






Filter -> mean texture:15.04: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5096.69 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:15.04: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5096.69 examples/s]






























Filter -&gt; mean texture:10.38:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:10.38:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:10.38:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:10.38: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5190.29 examples/s]


</pre>






Filter -> mean texture:10.38: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5190.29 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:10.38: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5190.29 examples/s]






























Filter -&gt; mean texture:20.78:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:20.78:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:20.78:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:20.78: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4726.58 examples/s]


</pre>






Filter -> mean texture:20.78: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4726.58 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:20.78: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4726.58 examples/s]






























Filter -&gt; mean texture:20.13:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:20.13:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:20.13:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:20.13: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5132.02 examples/s]


</pre>






Filter -> mean texture:20.13: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5132.02 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:20.13: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5132.02 examples/s]






























Filter -&gt; mean texture:19.51:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:19.51:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:19.51:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:19.51: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5075.05 examples/s]


</pre>






Filter -> mean texture:19.51: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5075.05 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:19.51: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5075.05 examples/s]






























Filter -&gt; mean texture:12.17:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:12.17:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:12.17:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:12.17: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5106.59 examples/s]


</pre>






Filter -> mean texture:12.17: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5106.59 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:12.17: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5106.59 examples/s]






























Filter -&gt; mean texture:16.49:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:16.49:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:16.49:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:16.49: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4948.06 examples/s]


</pre>






Filter -> mean texture:16.49: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4948.06 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:16.49: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4948.06 examples/s]






























Filter -&gt; mean texture:20.82:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:20.82:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:20.82:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:20.82: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5135.22 examples/s]


</pre>






Filter -> mean texture:20.82: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5135.22 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:20.82: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5135.22 examples/s]






























Filter -&gt; mean texture:22.47:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:22.47:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:22.47:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:22.47: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5217.93 examples/s]


</pre>






Filter -> mean texture:22.47: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5217.93 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:22.47: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5217.93 examples/s]






























Filter -&gt; mean texture:20.25:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:20.25:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:20.25:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:20.25: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5150.04 examples/s]


</pre>






Filter -> mean texture:20.25: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5150.04 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:20.25: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5150.04 examples/s]






























Filter -&gt; mean texture:18.03:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:18.03:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:18.03:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:18.03: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5079.36 examples/s]


</pre>






Filter -> mean texture:18.03: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5079.36 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:18.03: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5079.36 examples/s]






























Filter -&gt; mean texture:22.07:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:22.07:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:22.07:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:22.07: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5166.07 examples/s]


</pre>






Filter -> mean texture:22.07: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5166.07 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:22.07: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5166.07 examples/s]






























Filter -&gt; mean texture:14.86:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:14.86:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:14.86:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:14.86: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5309.48 examples/s]


</pre>






Filter -> mean texture:14.86: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5309.48 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:14.86: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5309.48 examples/s]






























Filter -&gt; mean texture:22.91:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:22.91:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:22.91:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:22.91: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4859.45 examples/s]


</pre>






Filter -> mean texture:22.91: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4859.45 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:22.91: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4859.45 examples/s]






























Filter -&gt; mean texture:19.31:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:19.31:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:19.31:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:19.31: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5054.66 examples/s]


</pre>






Filter -> mean texture:19.31: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5054.66 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:19.31: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5054.66 examples/s]






























Filter -&gt; mean texture:16.21:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:16.21:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:16.21:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:16.21: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5234.96 examples/s]


</pre>






Filter -> mean texture:16.21: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5234.96 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:16.21: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5234.96 examples/s]






























Filter -&gt; mean texture:24.68:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:24.68:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:24.68:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:24.68: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5267.25 examples/s]


</pre>






Filter -> mean texture:24.68: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5267.25 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:24.68: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5267.25 examples/s]






























Filter -&gt; mean texture:11.28:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:11.28:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:11.28:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:11.28: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4937.02 examples/s]


</pre>






Filter -> mean texture:11.28: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4937.02 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:11.28: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4937.02 examples/s]






























Filter -&gt; mean texture:14.06:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:14.06:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:14.06:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:14.06: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4986.35 examples/s]


</pre>






Filter -> mean texture:14.06: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4986.35 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:14.06: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4986.35 examples/s]






























Filter -&gt; mean texture:16.62:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:16.62:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:16.62:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:16.62: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5197.40 examples/s]


</pre>






Filter -> mean texture:16.62: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5197.40 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:16.62: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5197.40 examples/s]






























Filter -&gt; mean texture:13.93:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:13.93:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:13.93:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:13.93: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5277.83 examples/s]


</pre>






Filter -> mean texture:13.93: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5277.83 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:13.93: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5277.83 examples/s]






























Filter -&gt; mean texture:19.46:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:19.46:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:19.46:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:19.46: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5279.00 examples/s]


</pre>






Filter -> mean texture:19.46: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5279.00 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:19.46: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5279.00 examples/s]






























Filter -&gt; mean texture:17.21:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:17.21:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:17.21:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:17.21: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5184.55 examples/s]


</pre>






Filter -> mean texture:17.21: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5184.55 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:17.21: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5184.55 examples/s]






























Filter -&gt; mean texture:18.87:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:18.87:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:18.87:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:18.87: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5247.02 examples/s]


</pre>






Filter -> mean texture:18.87: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5247.02 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:18.87: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5247.02 examples/s]






























Filter -&gt; mean texture:19.07:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:19.07:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:19.07:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:19.07: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5210.20 examples/s]


</pre>






Filter -> mean texture:19.07: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5210.20 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:19.07: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5210.20 examples/s]






























Filter -&gt; mean texture:16.41:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:16.41:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:16.41:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:16.41: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5055.73 examples/s]


</pre>






Filter -> mean texture:16.41: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5055.73 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:16.41: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5055.73 examples/s]






























Filter -&gt; mean texture:18.02:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:18.02:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:18.02:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:18.02: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5139.64 examples/s]


</pre>






Filter -> mean texture:18.02: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5139.64 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:18.02: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5139.64 examples/s]






























Filter -&gt; mean texture:18.33:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:18.33:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:18.33:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:18.33: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5094.08 examples/s]


</pre>






Filter -> mean texture:18.33: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5094.08 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:18.33: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5094.08 examples/s]






























Filter -&gt; mean texture:21.28:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:21.28:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:21.28:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:21.28: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 4972.76 examples/s]


</pre>






Filter -> mean texture:21.28: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4972.76 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:21.28: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 4972.76 examples/s]






























Filter -&gt; mean texture:24.21:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:24.21:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:24.21:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:24.21: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5064.40 examples/s]


</pre>






Filter -> mean texture:24.21: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5064.40 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:24.21: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5064.40 examples/s]






























Filter -&gt; mean texture:15.7:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:15.7:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:15.7:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:15.7: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5004.09 examples/s]


</pre>






Filter -> mean texture:15.7: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5004.09 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:15.7: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5004.09 examples/s]






























Filter -&gt; mean texture:13.9:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:13.9:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:13.9:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:13.9: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5281.22 examples/s]


</pre>






Filter -> mean texture:13.9: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5281.22 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:13.9: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5281.22 examples/s]






























Filter -&gt; mean texture:15.05:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:15.05:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:15.05:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:15.05: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5301.24 examples/s]


</pre>






Filter -> mean texture:15.05: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5301.24 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:15.05: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5301.24 examples/s]






























Filter -&gt; mean texture:19.66:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:19.66:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:19.66:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:19.66: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5328.06 examples/s]


</pre>






Filter -> mean texture:19.66: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5328.06 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:19.66: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5328.06 examples/s]






























Filter -&gt; mean texture:25.11:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:25.11:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:25.11:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:25.11: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5279.93 examples/s]


</pre>






Filter -> mean texture:25.11: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5279.93 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:25.11: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5279.93 examples/s]






























Filter -&gt; mean texture:20.22:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:20.22:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:20.22:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:20.22: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5131.47 examples/s]


</pre>






Filter -> mean texture:20.22: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5131.47 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:20.22: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5131.47 examples/s]






























Filter -&gt; mean texture:17.31:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:17.31:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:17.31:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:17.31: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5133.79 examples/s]


</pre>






Filter -> mean texture:17.31: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5133.79 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:17.31: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5133.79 examples/s]






























Filter -&gt; mean texture:28.03:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:28.03:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:28.03:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:28.03: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5071.71 examples/s]


</pre>






Filter -> mean texture:28.03: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5071.71 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:28.03: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5071.71 examples/s]






























Filter -&gt; mean texture:17.94:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> mean texture:17.94:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> mean texture:17.94:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; mean texture:17.94: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5424.53 examples/s]


</pre>






Filter -> mean texture:17.94: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5424.53 examples/s]


end{sphinxVerbatim}








Filter -> mean texture:17.94: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5424.53 examples/s]






























Filter -&gt; overall:   0%|          | 0/57 [00:00&lt;?, ? examples/s]


</pre>






Filter -> overall:   0%|          | 0/57 [00:00<?, ? examples/s]


end{sphinxVerbatim}








Filter -> overall:   0%|          | 0/57 [00:00<?, ? examples/s]
















Filter -&gt; overall: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00&lt;00:00, 5452.61 examples/s]


</pre>






Filter -> overall: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5452.61 examples/s]


end{sphinxVerbatim}








Filter -> overall: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 57/57 [00:00<00:00, 5452.61 examples/s]


















[13]:







{'mean texture:16.93': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:13.32': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:21.41': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:21.81': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:18.89': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:18.83': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:15.98': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:12.84': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:18.54': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:14.74': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:20.7': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:23.93': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:14.08': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:26.47': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:23.81': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:10.94': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:16.67': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:17.43': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:15.04': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:10.38': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:20.78': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:20.13': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:19.51': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:12.17': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:16.49': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:20.82': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:22.47': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:20.25': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:18.03': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:22.07': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:14.86': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:22.91': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:19.31': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:16.21': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:24.68': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:11.28': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:14.06': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:16.62': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:13.93': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:19.46': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:17.21': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:18.87': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:19.07': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:16.41': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:18.02': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:18.33': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:21.28': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:24.21': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:15.7': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:13.9': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:15.05': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:19.66': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:25.11': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:20.22': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:17.31': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'mean texture:28.03': {'Group Size': 1,
  'BinaryPrecision': array(0., dtype=float32),
  'BinaryPrecision Parity': 0.0},
 'mean texture:17.94': {'Group Size': 1,
  'BinaryPrecision': array(1., dtype=float32),
  'BinaryPrecision Parity': 1.037037},
 'overall': {'Group Size': 57,
  'BinaryPrecision': array(0.96428573, dtype=float32),
  'BinaryPrecision Parity': 1.0}}







[ ]: