search

Puzer / stylegan-encoder

StyleGAN Encoder - converts real images to latent space
Other
1.07k stars 166 forks source link

ValueError: Shape of a new variable (ref_img_features) must be fully defined, but instead was (?, 64, 64, 256) #11

Open Fresh-Orange opened 5 years ago

Fresh-Orange commented 5 years ago

When I run “python3 encode_images.py aligned_images/ generated_images/ latent_representations/”，I get the errer:

Traceback (most recent call last): File "encode_images.py", line 86, in main() File "encode_images.py", line 61, in main perceptual_model.build_perceptual_model(generator.generated_image) File "/media/data2/laixc/stylegan-encoder/encoder/perceptual_model.py", line 41, in build_perceptual_model dtype='float32', initializer=tf.initializers.zeros()) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 1328, in get_variable constraint=constraint) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 1090, in get_variable constraint=constraint) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 435, in get_variable constraint=constraint) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 404, in _true_getter use_resource=use_resource, constraint=constraint) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 764, in _get_single_variable "but instead was %s." % (name, shape)) ValueError: Shape of a new variable (ref_img_features) must be fully defined, but instead was (?, 64, 64, 256).

YZ576023775 commented 5 years ago

the same error,have you solved it?

Fresh-Orange commented 5 years ago

the same error,have you solved it?

Yes, I solved it by modifying the following two lines in perceptual_model.py

self.ref_img_features = tf.get_variable('ref_img_features', shape=generated_img_features.shape,
                                                dtype='float32', initializer=tf.initializers.zeros())

self.features_weight = tf.get_variable('features_weight', shape=generated_img_features.shape,
                                               dtype='float32', initializer=tf.initializers.zeros())

to

in_shape = (1, generated_img_features.shape[1], generated_img_features.shape[2], generated_img_features.shape[3])

self.ref_img_features = tf.get_variable('ref_img_features',
                                                shape=in_shape,
                                                dtype='float32', initializer=tf.initializers.zeros())

self.features_weight = tf.get_variable('features_weight', shape=in_shape,
                                               dtype='float32', initializer=tf.initializers.zeros())