Skip to content

Added placeholders to fix memory leak in perceptual model #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Added placeholders to fix memory leak in perceptual model #4

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 14 additions & 2 deletions encoder/perceptual_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,12 @@ def __init__(self, img_size, layer=9, batch_size=1, sess=None):
self.features_weight = None
self.loss = None

self.features_weight_placeholder = None
self.img_features_placeholder = None

self.features_weight_op = None
self.img_features_op = None

def build_perceptual_model(self, generated_image_tensor):
vgg16 = VGG16(include_top=False, input_shape=(self.img_size, self.img_size, 3))
self.perceptual_model = Model(vgg16.input, vgg16.layers[self.layer].output)
Expand All @@ -46,6 +52,12 @@ def build_perceptual_model(self, generated_image_tensor):
self.loss = tf.losses.mean_squared_error(self.features_weight * self.ref_img_features,
self.features_weight * generated_img_features) / 82890.0

self.features_weight_placeholder = tf.placeholder(self.features_weight.dtype, shape=self.features_weight.get_shape())
self.img_features_placeholder = tf.placeholder(self.ref_img_features.dtype, shape=self.ref_img_features.get_shape())

self.features_weight_op = self.features_weight.assign(self.features_weight_placeholder)
self.img_features_op = self.ref_img_features.assign(self.img_features_placeholder)

def set_reference_images(self, images_list):
assert(len(images_list) != 0 and len(images_list) <= self.batch_size)
loaded_image = load_images(images_list, self.img_size)
Expand All @@ -65,8 +77,8 @@ def set_reference_images(self, images_list):

image_features = np.vstack([image_features, np.zeros(empty_features_shape)])

self.sess.run(tf.assign(self.features_weight, weight_mask))
self.sess.run(tf.assign(self.ref_img_features, image_features))
self.sess.run(self.features_weight_op, {self.features_weight_placeholder: weight_mask})
self.sess.run(self.img_features_op, {self.img_features_placeholder: image_features})

def optimize(self, vars_to_optimize, iterations=500, learning_rate=1.):
vars_to_optimize = vars_to_optimize if isinstance(vars_to_optimize, list) else [vars_to_optimize]
Expand Down