search

ZZUTK / Face-Aging-CAAE

Age Progression/Regression by Conditional Adversarial Autoencoder
636 stars 233 forks source link

ValueError: Variable E_conv0/w/Adam/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope? #4

Closed PHPerWu closed 7 years ago

PHPerWu commented 7 years ago

I run the train code , but in # optimizer for discriminator on image self.D_img_optimizer = tf.train.AdamOptimizer( learning_rate=EG_learning_rate, beta1=beta1 ).minimize( loss=self.loss_Di, var_list=self.D_img_variables ) tell me ValueError: Variable E_conv0/w/Adam/ does not exist how should I do ?

ZZUTK commented 7 years ago

Which version of Tensorflow are you using? The demo code is tested on r0.12. If you are working with r1.0, it may report this error. I'm quite sure about this issue because I have not started to work on r1.0. You may try other optimizers, e.g., GradientDescentOptimizer.

ZZUTK commented 7 years ago

Someone asked the similar issue, please refer to https://github.com/carpedm20/DCGAN-tensorflow/issues/66