def blackwhite_colorized_comparison(dir_color):
images = os.listdir(dir_color)
# dfine plot
num_col = 6
num_rows = math.ceil(len(images) * 2 / num_col)
plt.figure(figsize=(num_col * 2.5 + 1, (num_rows + 2) * 2.5 + 1))
gs1 = gridspec.GridSpec(num_rows + 2, num_col, width_ratios=[1] * num_col,
wspace=0.03, hspace=0.03, top=1, bottom=0, left=0, right=1)
# make plots
for i, image in enumerate(images):
image1 = load_images(dir_color, image)
# plot image
ax1 = plt.subplot(gs1[i * 2])
ax1.imshow(image1[:, :, 0], cmap='gray')
ax2 = plt.subplot(gs1[i * 2 + 1])
ax2.imshow(color.lab2rgb(image1))
ax1.axis('off')
ax2.axis('off')
plt.subplot_tool()
plt.savefig("../../../black-colored-comparison.jpg", bbox_inches='tight')
plt.close()
def image_check(model, num_of_images, name, b_size=32, dim=3):
script_dir = os.path.dirname(
os.path.abspath(inspect.getfile(
inspect.currentframe()))) # script directory
rel_path = "../../test_set"
abs_file_path = os.path.join(script_dir, rel_path)
image_list = os.listdir(abs_file_path)
all_images = np.zeros((num_of_images, 224, 224, dim))
for i in range(num_of_images):
# get image
image_lab = load_images(abs_file_path, image_list[i],
size=(224, 224)) # image is of size 256x256
image_l = images_to_l(image_lab)
all_images[i, :, :, :] = np.tile(image_l[:, :, np.newaxis],
(1, 1, 1, dim))
color_im = model.predict(all_images, batch_size=b_size)
for i in range(num_of_images):
# to rgb
lab_im = np.concatenate(
(all_images[i, :, :, 0][:, :, np.newaxis], color_im[i]), axis=2)
im_rgb = color.lab2rgb(lab_im)
# save
abs_svave_path = os.path.join(script_dir, '../../result_images/')
scipy.misc.toimage(im_rgb, cmin=0.0,
cmax=1.0).save(abs_svave_path + name +
image_list[i])
def whole_image_check(model, num_of_images, name):
# find directory
script_dir = os.path.dirname(
os.path.abspath(inspect.getfile(
inspect.currentframe()))) # script directory
rel_path = "../../test_set"
abs_file_path = os.path.join(script_dir, rel_path)
image_list = os.listdir(abs_file_path)
# repeat for each image
# lets take first n images
for i in range(num_of_images):
# get image
image_lab = load_images(abs_file_path,
image_list[i]) # image is of size 256x256
image_l = images_to_l(image_lab)
h, w = image_l.shape
# split images to list of images
slices_dim = 256 // 32
slices = np.zeros((slices_dim * slices_dim, 32, 32, 1))
for a in range(slices_dim):
for b in range(slices_dim):
slices[a * slices_dim + b] = image_l[a * 32:(a + 1) * 32,
b * 32:(b + 1) * 32,
np.newaxis]
# lover originals dimension to 224x224 to feed vgg and increase dim
image_l_224_b = resize_image(image_l, (224, 224))
image_l_224 = np.repeat(image_l_224_b[:, :, np.newaxis], 3,
axis=2).astype(float)
# append together booth lists
input_data = [slices,
np.array([
image_l_224,
] * slices_dim**2)]
# predict
predictions_ab = model.predict(input_data)
# reshape back
original_size_im = np.zeros((h, w, 2))
for n in range(predictions_ab.shape[0]):
a, b = n // slices_dim * 32, n % slices_dim * 32
original_size_im[a:a + 32, b:b + 32, :] = predictions_ab[n, :, :]
# to rgb
color_im = np.concatenate(
(image_l[:, :, np.newaxis], original_size_im), axis=2)
# color_im = np.concatenate(((np.ones(image_l.shape) * 50)[:, :, np.newaxis], original_size_im), axis=2)
im_rgb = color.lab2rgb(color_im)
# save
abs_svave_path = os.path.join(script_dir, '../../result_images/')
scipy.misc.toimage(im_rgb, cmin=0.0,
cmax=1.0).save(abs_svave_path + name +
image_list[i])
def generate_h5_small_vgg(self, size, name):
import h5py
# generate examples
x1 = np.zeros((size, 32, 32, 1))
x2 = np.zeros((size, 224, 224, 1))
y = np.zeros((size, 32, 32, 2))
z1 = np.zeros((size, 224, 224, 3))
i = 0
while i < size:
# print(i)
# download image
file_dir, file_name = self.select_file(i)
lab_im = load_images(os.path.join(self.dir_from, file_dir), file_name, size=self.im_size)
if type(lab_im) is not np.ndarray or lab_im == "error":
continue
h, w, _ = lab_im.shape
random_i, random_j = random.randint(0, h - 32), random.randint(0, w - 32)
im_part = lab_im[random_i: random_i + 32, random_j: random_j + 32, :]
x1[i, :, :, :] = images_to_l(im_part)[:, :, np.newaxis]
x2[i, :, :, :] = images_to_l(lab_im)[:, :, np.newaxis]
y[i, :, :] = images_to_ab(im_part)
z1[i, :, :, :] = lab_im
i += 1
f = h5py.File(os.path.join(self.dir_to1, name), 'w')
# Creating dataset to store features
f.create_dataset('small', (size, 32, 32, 1), dtype='float', data=x1)
f.create_dataset('vgg224', (size, self.im_size[0], self.im_size[0], 1), dtype='float', data=x2)
# Creating dataset to store labels
f.create_dataset('ab_hist', (size, 32, 32, 2), dtype='float', data=y)
f.close()
f = h5py.File(os.path.join(self.dir_to2, name), 'w')
# Creating dataset to store features
X1_dset = f.create_dataset('im', (i, 224, 224, 3), dtype='float')
X1_dset[:] = z1[:i]
f.close()
def alg_comparison_vertical(im_dir):
# dfine plot
files = os.listdir(im_dir)
just_im_names = list(set([x.split("-")[-1] for x in files]))
# just_im_names = ['n02215770_4433.JPEG', 'Screen Shot 2017-07-05 at 12.42.28.png', 'n02867401_971.JPEG', 'n02783994_7940.JPEG', 'n03219483_4276.JPEG', 'n03891538_27243.JPEG', 'n02213543_4098.JPEG', 'n01322221_4873.JPEG', 'n02903126_318.JPEG', 'n02124623_8147.JPEG', 'maruti-suzuki-swift-default-image.png-version201707131518.png', 'n02940385_203.JPEG']
num_col = 8
num_rows = len(just_im_names)
plt.figure(figsize=(num_col * 2.5 + 1, (num_rows + 2) * 2.5 + 1))
gs1 = gridspec.GridSpec(num_rows + 2, num_col, width_ratios=[1] * num_col,
wspace=0.03, hspace=0.03, top=1, bottom=0, left=0, right=1)
orders_tup = sorted(methods_order_v.items(), key=itemgetter(1))
ordered_methods = [x[0] for x in orders_tup]
# make plots
for j in range(num_rows):
for i in range(num_col):
image1 = load_images(im_dir, ordered_methods[i] + just_im_names[j])
# plot image
ax1 = plt.subplot(gs1[j * num_col + i])
ax1.imshow(color.lab2rgb(image1))
ax1.axis('off')
# if ax1.is_first_row():
# ax1.set_title(images[i].split(".")[0], fontsize=9)
if ax1.is_first_row():
ax1.set_title(rename_methods_v[ordered_methods[i]], fontsize=22, y=1.08)
# ax1.text(-0.12, 0.5, rename_methods_v[ordered_methods[i]],
# horizontalalignment='left',
# verticalalignment='center',
# transform=ax1.transAxes,
# color="black",
# rotation=90)
plt.savefig("../../../images-methods-comparison-full.pdf", bbox_inches='tight', format='pdf')
plt.close()
def alg_comparison(im_dir, methods, images):
# dfine plot
num_rows = len(methods)
num_col = len(images)
plt.figure(figsize=(num_col * 2.5 + 1, (num_rows + 2) * 2.5 + 1))
gs1 = gridspec.GridSpec(num_rows + 2, num_col, width_ratios=[1] * num_col,
wspace=0.03, hspace=0.03, top=1, bottom=0, left=0, right=1)
orders_tup = sorted(methods_order.items(), key=itemgetter(1))
ordered_methods = [x[0] for x in orders_tup]
# make plots
for j in range(num_rows):
for i in range(num_col):
image1 = load_images(im_dir, ordered_methods[j] + images[i])
# plot image
ax1 = plt.subplot(gs1[j * num_col + i])
ax1.imshow(color.lab2rgb(image1))
ax1.axis('off')
# if ax1.is_first_row():
# ax1.set_title(images[i].split(".")[0], fontsize=9)
if ax1.is_first_col():
ax1.text(-0.10, 0.5, rename_methods[ordered_methods[j]],
horizontalalignment='right',
verticalalignment='center',
transform=ax1.transAxes,
color="black",
rotation=90,
multialignment='center')
plt.savefig("../../../images-methods-comparison-100.jpg", bbox_inches='tight')
plt.close()
plt.figure(figsize=(num_col * 2.5 + 1, (num_rows + 2) * 2.5 + 1))
gs1 = gridspec.GridSpec(num_rows + 2,
num_col,
width_ratios=[1] * num_col,
wspace=0.03,
hspace=0.03,
top=1,
bottom=0,
left=0,
right=1)
original = []
# add grayscale image at beginning
for j, alg in enumerate(file_prefix):
image = load_images("../../test_set", image_name)
# original.append(image)
# plot image
ax1 = plt.subplot(gs1[j])
ax1.imshow(image[:, :, 0], cmap='gray')
ax1.text(0.03,
0.97,
"črno-bela",
horizontalalignment='left',
verticalalignment='top',
transform=ax1.transAxes,
size=22,
color="white",
bbox=dict(boxstyle="round,pad=0.05", fc="black", lw=2))
# for directory_ in os.listdir(dir_to):
# for file_ in os.listdir(os.path.join(dir_to, directory_)):
# name = file_.split("-")[-1]
# os.rename(os.path.join(dir_to, directory_, file_), os.path.join(dir_to, directory_, name))
# get originals
# for file_ in os.listdir(os.path.join(dir_to, "imp9-full-test-full-")):
# copyfile("../../../validation/" + file_,
# "../../../EvalueationApp/static/images/originals/" + file_)
import matplotlib.pyplot as plt
for file_ in os.listdir(os.path.join(dir_to, "hist05-test-full-")):
image1 = load_images(os.path.join(dir_to, "hist05-test-full-"),
file_,
size=(224, 224))
scipy.misc.toimage(color.lab2rgb(image1), cmin=0.0, cmax=1.0)\
.save(os.path.join(dir_to, "hist05-test-full-", file_))
# add other methods
# methods_order_v = {
# # "hist02-test-full-": 10,
# "hist05-test-full-": 12,
# "hyper03-test-full-": 3,
# # "imp09-test-full-": 4,
# # "imp9-full-test-full-": 7,
# # "let-there-color-test-full-": 2,
# "vgg-test-full-": 9}
#
def whole_image_check_hist(model, num_of_images, name):
# find directory
script_dir = os.path.dirname(
os.path.abspath(inspect.getfile(
inspect.currentframe()))) # script directory
rel_path = "../../test_set"
abs_file_path = os.path.join(script_dir, rel_path)
image_list = os.listdir(abs_file_path)
# repeat for each image
# lets take first n images
for i in range(num_of_images):
# get image
image_lab = load_images(abs_file_path,
image_list[i]) # image is of size 256x256
image_l = images_to_l(image_lab)
h, w = image_l.shape
# split images to list of images
slices_dim = 256 // 32
slices = np.zeros((slices_dim * slices_dim * 4, 32, 32, 1))
for a in range(slices_dim * 2 - 1):
for b in range(slices_dim * 2 - 1):
slices[a * slices_dim * 2 +
b] = image_l[a * 32 // 2:a * 32 // 2 + 32,
b * 32 // 2:b * 32 // 2 + 32, np.newaxis]
# lover originals dimension to 224x224 to feed vgg and increase dim
image_l_224_b = resize_image(image_l, (224, 224))
image_l_224 = np.repeat(image_l_224_b[:, :, np.newaxis], 3,
axis=2).astype(float)
# append together booth lists
input_data = [slices,
np.array([
image_l_224,
] * slices_dim**2 * 4)]
# predict
predictions_hist = model.predict(input_data)
# reshape back
indices = np.argmax(predictions_hist[:, :, :, :], axis=3)
predictions_a = indices // 20 * 10 - 100 + 5
predictions_b = indices % 20 * 10 - 100 + 5 # +5 to set in the middle box
predictions_ab = np.stack((predictions_a, predictions_b), axis=3)
original_size_im = np.zeros((h, w, 2))
for n in range(predictions_ab.shape[0]):
a, b = n // (slices_dim * 2) * 16, n % (slices_dim * 2) * 16
if a + 32 > 256 or b + 32 > 256:
continue # it is empty edge
# weight decision
if a == 0 and b == 0:
weight = weight_top_left
elif a == 0 and b == 224:
weight = weight_top_right
elif a == 0:
weight = weight_top
elif a == 224 and b == 0:
weight = weight_bottom_left
elif b == 0:
weight = weight_left
elif a == 224 and b == 224:
weight = weight_bottom_right
elif a == 224:
weight = weight_bottom
elif b == 224:
weight = weight_right
else:
weight = weight_m
im_a = predictions_ab[n, :, :, 0] * weight
im_b = predictions_ab[n, :, :, 1] * weight
original_size_im[a:a + 32, b:b + 32, :] += np.stack((im_a, im_b),
axis=2)
# to rgb
color_im = np.concatenate(
(image_l[:, :, np.newaxis], original_size_im), axis=2)
# color_im = np.concatenate(((np.ones(image_l.shape) * 50)[:, :, np.newaxis], original_size_im), axis=2)
im_rgb = color.lab2rgb(color_im)
# save
abs_svave_path = os.path.join(script_dir, '../../result_images/')
scipy.misc.toimage(im_rgb, cmin=0.0,
cmax=1.0).save(abs_svave_path + name +
image_list[i])
def whole_image_check_overlapping_no_vgg(model, num_of_images, name):
# find directory
script_dir = os.path.dirname(
os.path.abspath(inspect.getfile(
inspect.currentframe()))) # script directory
rel_path = "../../test_set"
abs_file_path = os.path.join(script_dir, rel_path)
image_list = os.listdir(abs_file_path)
# repeat for each image
# lets take first n images
for i in range(num_of_images):
# get image
image_lab = load_images(abs_file_path,
image_list[i]) # image is of size 256x256
image_l = images_to_l(image_lab)
h, w = image_l.shape
# split images to list of images
slices_dim = 256 // 32
slices = np.zeros((slices_dim * slices_dim * 4, 32, 32, 1))
for a in range(slices_dim * 2 - 1):
for b in range(slices_dim * 2 - 1):
slices[a * slices_dim * 2 +
b] = image_l[a * 32 // 2:a * 32 // 2 + 32,
b * 32 // 2:b * 32 // 2 + 32, np.newaxis]
# append together booth lists
input_data = slices
# predict
predictions_ab = model.predict(input_data, batch_size=32)
# reshape back
original_size_im = np.zeros((h, w, 2))
for n in range(predictions_ab.shape[0]):
a, b = n // (slices_dim * 2) * 16, n % (slices_dim * 2) * 16
if a + 32 > 256 or b + 32 > 256:
continue # it is empty edge
# weight decision
if a == 0 and b == 0:
weight = weight_top_left
elif a == 0 and b == 224:
weight = weight_top_right
elif a == 0:
weight = weight_top
elif a == 224 and b == 0:
weight = weight_bottom_left
elif b == 0:
weight = weight_left
elif a == 224 and b == 224:
weight = weight_bottom_right
elif a == 224:
weight = weight_bottom
elif b == 224:
weight = weight_right
else:
weight = weight_m
im_a = predictions_ab[n, :, :, 0] * weight
im_b = predictions_ab[n, :, :, 1] * weight
original_size_im[a:a + 32, b:b + 32, :] += np.stack((im_a, im_b),
axis=2)
# to rgb
color_im = np.concatenate(
(image_l[:, :, np.newaxis], original_size_im), axis=2)
# color_im = np.concatenate(((np.ones(image_l.shape) * 50)[:, :, np.newaxis], original_size_im), axis=2)
im_rgb = color.lab2rgb(color_im)
# save
abs_svave_path = os.path.join(script_dir, '../../result_images/')
scipy.misc.toimage(im_rgb, cmin=0.0,
cmax=1.0).save(abs_svave_path + name +
image_list[i])
