def colorcube_analysis():
# m = 'densenet121'
for m in models:
test_data = dt.get_data('cifar10', (50000, 60000))
top_n = 2000
model_name0 = mt.weight_file_name(m, 'cifar10-2-5', 50, False)
# model_name0 = mt.weight_file_name(m, 'cifar10-2-5', 50, False, suffix='ft20ep-exp')
model = mt.load_by_name(model_name0, test_data[0].shape[1:], h5_path+model_name0)
# y_predicted = model.predict(np.array(test_data[0]))
y_predicted = t_log.load_predictions(model_name0, file_path=csv_path)
true_classes = [int(k) for k in test_data[1]]
scores = metrics.prediction_ratings(y_predicted, true_classes)
score_sorted_ids = np.argsort(scores)
cc_high = metrics_color.ColorDensityCube(resolution=4)
for img_id in score_sorted_ids[-top_n:]:
cc_high.feed(test_data[0][img_id])
cc_high.normalize()
cc_high.plot_cube()
cc_low = metrics_color.ColorDensityCube(resolution=4)
for img_id in score_sorted_ids[:top_n]:
cc_low.feed(test_data[0][img_id])
cc_low.normalize()
cc_diff = cc_high.substract(cc_low, 'value')
cc_low.plot_cube()
cc_diff.normalize()
cc_diff.plot_cube(title='Color cube analysis difference (' + str(top_n) + ' images/series)', normalize=True,
save=True)
def car_example():
test_data = dt.get_data('cifar10', (50000, 60000))
cars = [6983, 3678, 3170, 1591]
cc0 = metrics_color.ColorDensityCube(resolution=4)
cc0.feed(test_data[0][cars[0]])
plotting.imshow(test_data[0][cars[0]])
cc0.plot_cube()
cc0 = metrics_color.ColorDensityCube(resolution=4)
cc0.feed(test_data[0][cars[1]])
plotting.imshow(test_data[0][cars[1]])
cc0.plot_cube()
def cc_grant():
img_name = '/Users/user/Desktop/grant.jpg'
cc = metrics_color.ColorDensityCube(64)
img = cv2.imread(img_name)
cc.feed(img)
cc.normalize()
cc.plot_cube()
def show_distribution():
images_cube = dt.cifar10_maxcolor_domains(granularity=4,
data_range=(50000, 60000))
region_sizes = dt.cube_cardinals(images_cube)
cc = metrics_color.ColorDensityCube(resolution=4, cube=region_sizes)
cc.normalize()
cc.plot_cube()
def show_imgs(id_list, title, dataset, tag_list=None, showColorCube=False, resolution=16): # list of img list
n_images = min(10, len(id_list))
if n_images >= 1:
fig, axes = plt.subplots(1 + showColorCube, n_images, squeeze=False, figsize=(n_images, 12),
subplot_kw={'xticks': (), 'yticks': ()})
if showColorCube:
cc = metrics_color.ColorDensityCube(resolution=resolution)
for i in xrange(n_images):
ax = axes[0][i]
img_id = id_list[i]
cc.feed(dataset[img_id])
ax.imshow(dataset[img_id], vmin=0, vmax=1)
if tag_list:
ax.set_title(tag_list[i])
# ax.set_title('label #' + str(id_list) + ' (' + str(i) + '/' + str(len(id_list)) + ' images)')
plot_cube(cc, fig)
else:
for i in xrange(n_images):
ax = axes[0][i]
img_id = id_list[i]
ax.imshow(dataset[img_id], vmin=0, vmax=1)
if tag_list:
ax.set_title(tag_list[i])
# ax.set_title('label #' + str(id_list) + ' (' + str(i) + '/' + str(len(id_list)) + ' images)')
if title:
fig.suptitle(title + ' - label #' + str(id_list))
# fig.subplots_adjust()
plt.show()
plt.close()
def bdd100k_cc_analysis():
model_files = ['densenet121_bdd100k_cl0-500k_20ep_woda_ep20_vl0.22.hdf5',
]
# 'resnet50_bdd100k_cl0-500k_20ep_woda_ep13_vl0.27.hdf5',
# 'mobilenet_bdd100k_cl0-500k_20ep_woda_ep15_vl0.24.hdf5',
# 'mobilenetv2_bdd100k_cl0-500k_20ep_woda_ep17_vl0.22.hdf5',
# 'nasnet_bdd100k_cl0-500k_20ep_woda_ep17_vl0.24.hdf5']
class_map_file = bu.class_mapping(input_json=val_json, output_csv=labels_path + 'class_mapping.csv')
# Dataset for analysis
val_partition, val_labels = bu.get_ids_labels(val_labels_csv, class_map_file)
for m in model_files:
# test_subset creation
pr_file = '.'.join(m.split('.')[:-1]) + '_predictions.csv'
predictions, y_scores, img_ids = dt.get_scores_from_file(csv_path + pr_file, val_labels)
top_n_args, bot_n_args = dt.get_topbot_n_args(20000, y_scores)
cc_high = metrics_color.ColorDensityCube(resolution=4)
for arg in top_n_args:
cc_high.feed(cv2.imread(img_ids[arg]))
print('high sum', np.sum(cc_high.get_cube().flatten()))
cc_high.normalize()
cc_high.plot_cube()
cc_low = metrics_color.ColorDensityCube(resolution=4)
for arg in bot_n_args:
cc_low.feed(cv2.imread(img_ids[arg]))
print('low sum', np.sum(cc_low.get_cube().flatten()))
cc_low.normalize()
cc_low.plot_cube()
cc_diff = cc_high.substract(cc_low, 'value')
print('diff mean', np.sum(cc_diff.get_cube().flatten()))
print('diff mean', np.mean(cc_diff.get_cube().flatten()))
cc_diff.normalize()
# cc_diff.plot_cube()
# cc_diff.normalize()
cc_diff.plot_cube(title='Color cube analysis difference (' + str(20000) + ' images/series)', normalize=True,
save=True)
def pr_on_fair_distribution(models=['densenet121'], top_n=100, res=4):
test_data = dt.get_data('cifar10', (50000, 60000))
# Add every image's cube in densities
densities = []
for img in test_data[0]:
cc = metrics_color.ColorDensityCube(res)
cc.feed(img)
densities.append(cc.get_cube())
# ccf = np.array(cc.get_cube()).flatten()
# Shape densities (list of cubes) to make a list per color
densities_lists = np.swapaxes(np.swapaxes(np.swapaxes(densities, 0, 3), 0, 2), 0, 1)
# print(densities_lists.shape)
densities_cube = np.empty((res, res, res), dtype=object)
# For each color keep the ids of the top_n most dense images in this color (same image can be in 2 colors)
for i in xrange(res):
for j in xrange(res):
for k in xrange(res):
# pr_most_dense = []
density_list = densities_lists[i][j][k].tolist()
args_most_dense = np.argsort(density_list)[-top_n:]
densities_cube[i][j][k] = args_most_dense
# print(densities_cube.shape)
# Per model analysis
for m in models:
# Load model predictions and ground_truth values
model_name0 = mt.weight_file_name(m, 'cifar10-2-5', 50, False)
y_predicted = t_log.load_predictions(model_name0, file_path=csv_path)
true_classes = [int(k) for k in test_data[1]]
pr = metrics.prediction_ratings(y_predicted, true_classes)
# For each color get prediction score of the top_n images
score_cube = np.zeros((res, res, res))
global_cc = metrics_color.ColorDensityCube(resolution=res)
args_most_dense_all = []
for i in xrange(res):
for j in xrange(res):
for k in xrange(res):
pr_most_dense = []
densities_args = densities_cube[i][j][k].tolist()
# args_most_dense = np.argsort(density_list)[-topn:]
ijk_cc = metrics_color.ColorDensityCube(res)
for a in densities_cube[i][j][k].tolist():
pr_most_dense.append(pr[a])
ijk_cc.feed(test_data[0][a])
global_cc.feed(test_data[0][a])
ijk_cc.normalize()
ttl = 'color = (' + str(float(i/res)) + ', ' + str(float(j/res)) + ', ' + str(float(k/res)) + ')'
# ijk_cc.plot_cube()
score_cube[i][j][k] = np.mean(pr_most_dense)
print(np.mean(pr_most_dense))
# args_most_dense_all.append(args_most_dense)
ttl = 'color = (' + str(float(i/res)) + ', ' + str(float(j/res)) + ', ' + str(float(k/res)) + ')'
# plotting.show_imgs(densities_args[:10], ttl, test_data[0], showColorCube=True, resolution=4)
global_cc.normalize()
global_cc.plot_cube(title='Fair distributed dataset ColorCube')
sc = metrics_color.ColorDensityCube(resolution=res, cube=score_cube)
sc.normalize()
sc.plot_cube(title='Scores per color for ' + m)