def run_style_transfer(self,
content_path,
style_path,
content_map_path="",
style_map_path="",
num_iterations=100,
content_weight=1e4,
style_weight=1e-2,
trans_weight=0):
# We don't need to (or want to) train any layers of our model, so we set their
# trainable to false.
model = self.get_model()
for layer in model.layers:
layer.trainable = False
# Get the style and content feature representations (from our specified intermediate layers)
style_features, content_features = self.get_feature_representations(
model, content_path, style_path)
style_map_features, _ = self.get_feature_representations(
model, content_map_path, style_map_path)
content_map_features, _ = self.get_feature_representations(
model, style_map_path, content_map_path)
size = 5
stride = 4
base_style_patches = []
i = 0
style_img = load_img(style_path)
for style_feat_img, style_map_img in zip(style_features,
style_map_features):
print(style_feat_img.shape)
print(style_map_img.shape)
style_feat_img = tf.concat([style_feat_img, style_map_img], -1)
print(style_feat_img.shape)
li = tf.squeeze(
tf.extract_image_patches(tf.expand_dims(style_feat_img,
axis=0),
ksizes=[1, size, size, 1],
strides=[1, stride, stride, 1],
rates=[1, 1, 1, 1],
padding='VALID'), 0)
li = tf.reshape(
li, [((style_feat_img.shape[0] - size) // stride + 1) *
((style_feat_img.shape[1] - size) // stride + 1), -1])
# li = tf.reshape(li, [(style_feat_img.shape[0] - 2) * (style_feat_img.shape[1] - 2), -1])
base_style_patches.append(li)
# print( i,len( base_style_patches[i] ), base_style_patches[i][0] )
i += 1
# print(len(base_style_patches))
# Set initial image
init_image = load_noise_img(load_and_process_img(content_path))
init_image = load_and_process_img(content_path)
init_image = tfe.Variable(init_image, dtype=tf.float32)
# Create our optimizer
opt = tf.train.AdamOptimizer(learning_rate=50,
beta1=0.99,
epsilon=1e-1)
# For displaying intermediate images
iter_count = 1
# Store our best result
best_loss, best_img = float('inf'), None
# Create a nice config
loss_weights = (style_weight, content_weight, trans_weight)
cfg = {
'model': model,
'loss_weights': loss_weights,
'init_image': init_image,
'base_style_patches': base_style_patches,
'content_features': content_features,
'content_map_features': content_map_features
}
# For displaying
num_rows = 2
num_cols = 10
display_interval = num_iterations / (num_rows * num_cols)
start_time = time.time()
global_start = time.time()
norm_means = np.array([103.939, 116.779, 123.68])
min_vals = -norm_means
max_vals = 255 - norm_means
imgs = []
for i in range(num_iterations):
print("himmat rakho")
grads, all_loss = self.compute_grads(cfg)
print("gradient aega")
loss, style_score, content_score, trans_score = all_loss
opt.apply_gradients([(grads, init_image)])
print("gradient agya")
clipped = tf.clip_by_value(init_image, min_vals, max_vals)
# print("II 1",init_image)
init_image.assign(clipped)
# print("II 2",cfg['init_image'])
end_time = time.time()
if loss < best_loss:
# Update best loss and best image from total loss.
best_loss = loss
best_img = deprocess_img(init_image.numpy())
if i % 1 == 0:
start_time = time.time()
# Use the .numpy() method to get the concrete numpy array
plot_img = init_image.numpy()
plot_img = deprocess_img(plot_img)
if i % display_interval == 0:
imgs.append(plot_img)
print('Iteration: {}'.format(i))
print('Total loss: {:.4e}, '
'style loss: {:.4e}, '
'content loss: {:.4e}, '
'trans loss: {:.4e}, '
'time: {:.4f}s'.format(loss, style_score, content_score,
trans_score,
time.time() - start_time))
print('Total time: {:.4f}s'.format(time.time() - global_start))
plt.figure(figsize=(14, 4))
for i, img in enumerate(imgs):
plt.subplot(num_rows, num_cols, i + 1)
plt.imshow(img)
plt.xticks([])
plt.yticks([])
plt.savefig(self.results + content_path + '_inter.jpg')
return best_img, best_loss
def load_and_process_img(path_to_img):
img = load_img(path_to_img)
#print("img shape",img.shape,"path ",path_to_img)
img = tf.keras.applications.vgg19.preprocess_input(img)
return img
def load_and_process_img(path_to_img):
img = load_img(path_to_img,max_size)
print(img.shape)
img = tf.keras.applications.vgg19.preprocess_input(img)
return img