GAN icon indicating copy to clipboard operation
GAN copied to clipboard

After training , cannot test the cgan if i define a variable and use cgan.generate(example) always wrong

Open tangchen2 opened this issue 5 years ago • 0 comments

Variable G_conv_mnist/fully_connected/weights already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope? Originally defined at:

File "C:\Users\tc\Anaconda3\envs\keras-gpu\lib\site-packages\tensorflow\python\framework\ops.py", line 1718, in init self._traceback = self._graph._extract_stack() # pylint: disable=protected-access File "C:\Users\tc\Anaconda3\envs\keras-gpu\lib\site-packages\tensorflow\python\framework\ops.py", line 3392, in create_op op_def=op_def) File "C:\Users\tc\Anaconda3\envs\keras-gpu\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper op_def=op_def)

tangchen2 avatar Mar 26 '19 02:03 tangchen2