chunyuanli / discogan Goto Github PK

Hello,
How can we replace the X and the Z dataset with real world datasets? Could you help to explain that with respect to the given code.
Thanks

File "C:/Users/DELL/PycharmProjects/DiscoGAN/DiscoGAN_demo.py", line 152, in
rec_z = inference_network(p_x, latent_dim, n_layer_inf, n_hidden_inf, eps_dim )
File "C:/Users/DELL/PycharmProjects/DiscoGAN/DiscoGAN_demo.py", line 103, in inference_network
h = slim.repeat(h, n_layer, slim.fully_connected, n_hidden, activation_fn=tf.nn.relu)

This is the error which i am getting

12 rec_z = inference_network(p_x, latent_dim, n_layer_inf, n_hidden_inf, eps_dim)
13 cost_z = tf.reduce_mean(tf.pow(rec_z - z, 2))
14

in inference_network(x, latent_dim, n_layer, n_hidden, eps_dim)
12 with tf.variable_scope("inference"):
13 h = x
---> 14 h = slim.repeat(h, n_layer, slim.fully_connected, n_hidden, activation_fn=tf.nn.relu)
15 z = slim.fully_connected(h, latent_dim, activation_fn=None, scope="q_z")
16 return z

ValueError: Variable inference/Repeat/fully_connected_1/weights already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at:

File "/home/nikhil/anaconda/envs/tfone/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 217, in variable
use_resource=use_resource)
File "/home/nikhil/anaconda/envs/tfone/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args
return func(*args, **current_args)
File "/home/nikhil/anaconda/envs/tfone/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 262, in model_variable
use_resource=use_resource)

I am getting this error for other projects when i am using a model repeatedly.
tensorflow: 1.1.0

Please suggest some solution.
I also tried to restart kernel and run each cell only once.