def colour_histogram_with_filters():
"""Run evaluation of colour histograms with filters"""
rf_model_normal = rf.RF(label='RF with no preprocessing',
preprocessing=[],
features=[colour_histogram(bins=16)])
rf_model_hsv = rf.RF(label='RF with hsv',
preprocessing=[hsv_model],
features=[colour_histogram(bins=16)])
svm_model_normal = svm.SVM(label='SVM with no preprocessing',
preprocessing=[],
features=[colour_histogram(bins=16)])
svm_model_hsv = svm.SVM(label='SVM with hsv',
preprocessing=[hsv_model],
features=[colour_histogram(bins=16)])
run_training_and_tests(
'system_selection_2_colour_hist_preprocessing',
'kaggle',
[rf_model_normal, rf_model_hsv, svm_model_normal, svm_model_hsv],
n_iterations=5,
n_images=10000,
training_split=0.5)
def svm_gamma():
"""Run evaluation of different SVM gamma values"""
svm_auto = svm.SVM(
label = 'SVM with auto-selected gamma',
preprocessing = hsv_saturation_threshold,
features = [haralick],
kernel = 'poly',
degree = 3
)
svm_thousandth = svm.SVM(
label = 'SVM with 0.001 gamma',
preprocessing = hsv_saturation_threshold,
features = [haralick],
kernel = 'poly',
degree = 3,
gamma = 0.001
)
svm_hundredth = svm.SVM(
label = 'SVM with 0.01 gamma',
preprocessing = hsv_saturation_threshold,
features = [haralick],
kernel = 'poly',
degree = 3,
gamma = 0.01
)
svm_tenth = svm.SVM(
label = 'SVM with 0.1 gamma',
preprocessing = hsv_saturation_threshold,
features = [haralick],
kernel = 'poly',
degree = 3,
gamma = 0.1
)
svm_one = svm.SVM(
label = 'SVM with 1 gamma',
preprocessing = hsv_saturation_threshold,
features = [haralick],
kernel = 'poly',
degree = 3,
gamma = 1.0
)
run_training_and_tests(
'system_selection_3_svm_gamma',
'kaggle',
[
svm_auto,
svm_thousandth,
svm_hundredth,
svm_tenth,
svm_one
],
n_iterations = 5, n_images = 10000, training_split = 0.5
)
def rf_max_depth():
"""Run evaluation of different RF max depths"""
rf_10 = rf.RF(
label = 'RF with max depth 10',
preprocessing = hsv_saturation,
features = [greyscale_histogram(bins = 64)],
n_estimators = 100,
max_depth = 10
)
rf_100 = rf.RF(
label = 'RF with max depth 100',
preprocessing = hsv_saturation,
features = [greyscale_histogram(bins = 64)],
n_estimators = 100,
max_depth = 100
)
rf_250 = rf.RF(
label = 'RF with max depth 250',
preprocessing = hsv_saturation,
features = [greyscale_histogram(bins = 64)],
n_estimators = 100,
max_depth = 250
)
rf_1000 = rf.RF(
label = 'RF with max depth 1000',
preprocessing = hsv_saturation,
features = [greyscale_histogram(bins = 64)],
n_estimators = 100,
max_depth = 1000
)
rf_none = rf.RF(
label = 'RF with no max depth',
preprocessing = hsv_saturation,
features = [greyscale_histogram(bins = 64)],
n_estimators = 100,
max_depth = None
)
run_training_and_tests(
'system_selection_3_rf_max_depth',
'kaggle',
[
rf_10,
rf_100,
rf_250,
rf_1000,
rf_none
],
n_iterations = 5, n_images = 10000, training_split = 0.5
)
def svm_kernel():
"""Run evaluation of different SVM kernels"""
svm_rbf = svm.SVM(
label = 'SVM with RBF kernel',
preprocessing = hsv_saturation_threshold,
features = [haralick],
kernel = 'rbf'
)
svm_p1 = svm.SVM(
label = 'SVM with polynomial kernel, degree 1',
preprocessing = hsv_saturation_threshold,
features = [haralick],
kernel = 'poly',
degree = 1
)
svm_p2 = svm.SVM(
label = 'SVM with polynomial kernel, degree 2',
preprocessing = hsv_saturation_threshold,
features = [haralick],
kernel = 'poly',
degree = 2
)
svm_p3 = svm.SVM(
label = 'SVM with polynomial kernel, degree 3',
preprocessing = hsv_saturation_threshold,
features = [haralick],
kernel = 'poly',
degree = 3
)
svm_p5 = svm.SVM(
label = 'SVM with polynomial kernel, degree 5',
preprocessing = hsv_saturation_threshold,
features = [haralick],
kernel = 'poly',
degree = 5
)
run_training_and_tests(
'system_selection_3_svm_kernel',
'kaggle',
[
svm_rbf,
svm_p1,
svm_p2,
svm_p3,
svm_p5
],
n_iterations = 5, n_images = 10000, training_split = 0.5
)
def rf_forest_size():
"""Run evaluation of different RF sizes"""
rf_1 = rf.RF(
label = 'RF with 1 tree',
preprocessing = hsv_saturation,
features = [greyscale_histogram(bins = 64)],
n_estimators = 1
)
rf_10 = rf.RF(
label = 'RF with 10 trees',
preprocessing = hsv_saturation,
features = [greyscale_histogram(bins = 64)],
n_estimators = 10
)
rf_50 = rf.RF(
label = 'RF with 50 trees',
preprocessing = hsv_saturation,
features = [greyscale_histogram(bins = 64)],
n_estimators = 50
)
rf_100 = rf.RF(
label = 'RF with 100 trees',
preprocessing = hsv_saturation,
features = [greyscale_histogram(bins = 64)],
n_estimators = 100
)
rf_250 = rf.RF(
label = 'RF with 250 trees',
preprocessing = hsv_saturation,
features = [greyscale_histogram(bins = 64)],
n_estimators = 250
)
run_training_and_tests(
'system_selection_3_rf_forest_size',
'kaggle',
[
rf_1,
rf_10,
rf_50,
rf_100,
rf_250
],
n_iterations = 5, n_images = 10000, training_split = 0.5
)
def run_experiment():
"""Run experiment one, testing performance on kaggle data"""
optimal_svm = svm.SVM(label='Optimised SVM model',
preprocessing=hsv_saturation_threshold,
features=[haralick],
kernel='poly',
degree=3)
optimal_rf = rf.RF(label='Optimised RF model',
preprocessing=hsv_saturation,
features=[greyscale_histogram(bins=64)],
n_estimators=100,
max_depth=100)
run_training_and_tests('experiment_1_NLM_performance',
'kaggle', [optimal_rf, optimal_svm],
n_iterations=10,
n_training_images=5000,
n_test_images=20000)
def initial_grey_histogram_bins_evaluation():
"""Run evaluation of grey histogram bin sizes"""
rf_model_grey2 = rf.RF(
label='grey 2 bin RF',
preprocessing=[],
features=[greyscale_histogram(bins=2)]
)
rf_model_grey4 = rf.RF(
label='grey 4 bin RF',
preprocessing=[],
features=[greyscale_histogram(bins=4)]
)
rf_model_grey8 = rf.RF(
label='grey 8 bin RF',
preprocessing=[],
features=[greyscale_histogram(bins=8)]
)
rf_model_grey16 = rf.RF(
label='grey 16 bin RF',
preprocessing=[],
features=[greyscale_histogram(bins=16)]
)
rf_model_grey32 = rf.RF(
label='grey 32 bin RF',
preprocessing=[],
features=[greyscale_histogram(bins=32)]
)
rf_model_grey64 = rf.RF(
label='grey 64 bin RF',
preprocessing=[],
features=[greyscale_histogram(bins=64)]
)
svm_model_grey2 = svm.SVM(
label='grey 2 bin SVM',
preprocessing=[],
features=[greyscale_histogram(bins=2)]
)
svm_model_grey4 = svm.SVM(
label='grey 4 bin SVM',
preprocessing=[],
features=[greyscale_histogram(bins=4)]
)
svm_model_grey8 = svm.SVM(
label='grey 8 bin SVM',
preprocessing=[],
features=[greyscale_histogram(bins=8)]
)
svm_model_grey16 = svm.SVM(
label='grey 16 bin SVM',
preprocessing=[],
features=[greyscale_histogram(bins=16)]
)
svm_model_grey32 = svm.SVM(
label='grey 32 bin SVM',
preprocessing=[],
features=[greyscale_histogram(bins=32)]
)
svm_model_grey64 = svm.SVM(
label='grey 64 bin SVM',
preprocessing=[],
features=[greyscale_histogram(bins=64)]
)
run_training_and_tests(
'system_selection_1_hist_grey',
'kaggle',
[
rf_model_grey2,
rf_model_grey4,
rf_model_grey8,
rf_model_grey16,
rf_model_grey32,
rf_model_grey64,
svm_model_grey2,
svm_model_grey4,
svm_model_grey8,
svm_model_grey16,
svm_model_grey32,
svm_model_grey64
],
n_iterations=5, n_images=10000, training_split=0.5
)
def hist_hu_moments_haralick_evaluation():
"""Run comparative evaluation of hu moments, haralick texture
attributes, colour histograms and greyscale histograms
"""
rf_model_haralick = rf.RF(
label='RF with haralick',
preprocessing=[],
features=[haralick]
)
rf_model_hu = rf.RF(
label='RF with hu moments',
preprocessing=[],
features=[hu_moments]
)
rf_model_grey_hist = rf.RF(
label='RF with grey hist',
preprocessing=[],
features=[greyscale_histogram(bins=64)]
)
rf_model_colour_hist = rf.RF(
label='RF with colour hist',
preprocessing=[],
features=[colour_histogram(bins=16)]
)
svm_model_haralick = svm.SVM(
label='SVM with haralick',
preprocessing=[],
features=[haralick]
)
svm_model_hu = svm.SVM(
label='SVM with hu moments',
preprocessing=[],
features=[hu_moments]
)
svm_model_grey_hist = svm.SVM(
label='SVM with grey hist',
preprocessing=[],
features=[greyscale_histogram(bins=64)]
)
svm_model_colour_hist = svm.SVM(
label='SVM with colour hist',
preprocessing=[],
features=[colour_histogram(bins=16)]
)
run_training_and_tests(
'system_selection_1_hist_hu_haralick',
'kaggle',
[
rf_model_haralick,
rf_model_hu,
rf_model_grey_hist,
rf_model_colour_hist,
svm_model_haralick,
svm_model_hu,
svm_model_grey_hist,
svm_model_colour_hist
],
n_iterations=5, n_images=10000, training_split=0.5)
def initial_colour_histogram_bins_evaluation():
"""Run evaluation of colour histogram bin sizes"""
rf_model_colour2 = rf.RF(
label='colour 2 bin RF',
preprocessing=[],
features=[colour_histogram(bins=2)]
)
rf_model_colour4 = rf.RF(
label='colour 4 bin RF',
preprocessing=[],
features=[colour_histogram(bins=4)]
)
rf_model_colour8 = rf.RF(
label='colour 8 bin RF',
preprocessing=[],
features=[colour_histogram(bins=8)]
)
rf_model_colour16 = rf.RF(
label='colour 16 bin RF',
preprocessing=[],
features=[colour_histogram(bins=16)]
)
rf_model_colour32 = rf.RF(
label='colour 32 bin RF',
preprocessing=[],
features=[colour_histogram(bins=32)]
)
svm_model_colour2 = svm.SVM(
label='colour 2 bin SVM',
preprocessing=[],
features=[colour_histogram(bins=2)]
)
svm_model_colour4 = svm.SVM(
label='colour 4 bin SVM',
preprocessing=[],
features=[colour_histogram(bins=4)]
)
svm_model_colour8 = svm.SVM(
label='colour 8 bin SVM',
preprocessing=[],
features=[colour_histogram(bins=8)]
)
svm_model_colour16 = svm.SVM(
label='colour 16 bin SVM',
preprocessing=[],
features=[colour_histogram(bins=16)]
)
run_training_and_tests(
'system_selection_1_hist_colour',
'kaggle',
[
rf_model_colour2,
rf_model_colour4,
rf_model_colour8,
rf_model_colour16,
rf_model_colour32,
svm_model_colour2,
svm_model_colour4,
svm_model_colour8,
svm_model_colour16
],
n_iterations=5, n_images=10000, training_split=0.5
)
def greyscale_histogram_with_filters():
"""Run evaluation of greyscale histograms with filters"""
rf_model_normal = rf.RF(label='RF with no preprocessing',
preprocessing=[],
features=[greyscale_histogram(bins=64)])
rf_model_hsv = rf.RF(label='RF with hsv',
preprocessing=[hsv_model],
features=[greyscale_histogram(bins=64)])
rf_model_hsv_is = rf.RF(label='RF with hsv and isolate saturation',
preprocessing=hsv_saturation,
features=[greyscale_histogram(bins=64)])
rf_model_hsv_is_thresh = rf.RF(
label='RF with hsv, isolate saturation, threshold',
preprocessing=hsv_saturation_threshold,
features=[greyscale_histogram(bins=64)])
rf_model_hsv_is_c = rf.RF(
label='RF with hsv, isolate saturation, contrast',
preprocessing=hsv_saturation_contrast,
features=[greyscale_histogram(bins=64)])
svm_model_normal = svm.SVM(label='SVM with no preprocessing',
preprocessing=[],
features=[greyscale_histogram(bins=64)])
svm_model_hsv = svm.SVM(label='SVM with hsv',
preprocessing=[hsv_model],
features=[greyscale_histogram(bins=64)])
svm_model_hsv_is = svm.SVM(label='SVM with hsv and isolate saturation',
preprocessing=hsv_saturation,
features=[greyscale_histogram(bins=64)])
svm_model_hsv_is_thresh = svm.SVM(
label='SVM with hsv, isolate saturation, threshold',
preprocessing=hsv_saturation_threshold,
features=[greyscale_histogram(bins=64)])
svm_model_hsv_is_c = svm.SVM(
label='SVM with hsv, isolate saturation, contrast',
preprocessing=hsv_saturation_contrast,
features=[greyscale_histogram(bins=64)])
run_training_and_tests('system_selection_2_grey_hist_preprocessing',
'kaggle', [
rf_model_normal,
rf_model_hsv,
rf_model_hsv_is,
rf_model_hsv_is_c,
rf_model_hsv_is_thresh,
svm_model_normal,
svm_model_hsv,
svm_model_hsv_is,
svm_model_hsv_is_c,
svm_model_hsv_is_thresh,
],
n_iterations=5,
n_images=10000,
training_split=0.5)
def haralick_with_filters():
"""Run evaluation of haralick texture attributes with filters"""
rf_model_normal = rf.RF(label='RF with no preprocessing',
preprocessing=[],
features=[haralick])
rf_model_hsv = rf.RF(label='RF with hsv',
preprocessing=hsv,
features=[haralick])
rf_model_hsv_is = rf.RF(label='RF with hsv and isolate saturation',
preprocessing=hsv_saturation,
features=[haralick])
rf_model_hsv_is_thresh = rf.RF(
label='RF with hsv, isolate saturation, threshold',
preprocessing=hsv_saturation_threshold,
features=[haralick])
rf_model_hsv_is_c = rf.RF(
label='RF with hsv, isolate saturation, contrast',
preprocessing=hsv_saturation_contrast,
features=[haralick])
svm_model_normal = svm.SVM(label='SVM with no preprocessing',
preprocessing=[],
features=[haralick])
svm_model_hsv = svm.SVM(label='SVM with hsv',
preprocessing=hsv,
features=[haralick])
svm_model_hsv_is = svm.SVM(label='SVM with hsv and isolate saturation',
preprocessing=hsv_saturation,
features=[haralick])
svm_model_hsv_is_thresh = svm.SVM(
label='SVM with hsv, isolate saturation, threshold',
preprocessing=hsv_saturation_threshold,
features=[haralick])
svm_model_hsv_is_c = svm.SVM(
label='SVM with hsv, isolate saturation, contrast',
preprocessing=hsv_saturation_contrast,
features=[haralick])
run_training_and_tests('system_selection_2_haralick_preprocessing',
'kaggle', [
rf_model_normal,
rf_model_hsv,
rf_model_hsv_is,
rf_model_hsv_is_c,
rf_model_hsv_is_thresh,
svm_model_normal,
svm_model_hsv,
svm_model_hsv_is,
svm_model_hsv_is_c,
svm_model_hsv_is_thresh,
],
n_iterations=5,
n_images=10000,
training_split=0.5)