About Results
Closed this issue · 7 comments
I pressed the Denoise button, but it seemed to add noise.
Did you train the network or used the CKPT file provided? I think our CKPT file is corrupted for some reason. I can upload the latest version when I get time but I would suggest you to train the n/w from scratch.
Traceback (most recent call last):
File "C:/ImageDenoisingGAN-master/train.py", line 91, in
train()
File "C:/ImageDenoisingGAN-master/train.py", line 23, in train
Dg = discriminator(Gz, reuse=True)
File "C:\ImageDenoisingGAN-master\model.py", line 32, in discriminator
conv1, conv1_weights = conv_layer(input, 4, 3, 48, 2, "d_conv1", reuse=reuse)
File "C:\ImageDenoisingGAN-master\conv_helper.py", line 10, in conv_layer
output = slim.batch_norm(output)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\contrib\framework\python\ops\arg_scope.py", line 181, in func_with_args
return func(*args, **current_args)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\contrib\layers\python\layers\layers.py", line 528, in batch_norm
outputs = layer.apply(inputs, training=is_training)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\layers\base.py", line 320, in apply
return self.call(inputs, **kwargs)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\layers\base.py", line 286, in call
self.build(input_shapes[0])
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\layers\normalization.py", line 125, in build
trainable=True)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 1049, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 948, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 349, in get_variable
validate_shape=validate_shape, use_resource=use_resource)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 1389, in wrapped_custom_getter
*args, **kwargs)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\layers\base.py", line 275, in variable_getter
variable_getter=functools.partial(getter, **kwargs))
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\layers\base.py", line 228, in _add_variable
trainable=trainable and self.trainable)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\contrib\layers\python\layers\layers.py", line 1334, in layer_variable_getter
return _model_variable_getter(getter, *args, **kwargs)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\contrib\layers\python\layers\layers.py", line 1326, in _model_variable_getter
custom_getter=getter, use_resource=use_resource)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\contrib\framework\python\ops\arg_scope.py", line 181, in func_with_args
return func(*args, **current_args)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\contrib\framework\python\ops\variables.py", line 262, in model_variable
use_resource=use_resource)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\contrib\framework\python\ops\arg_scope.py", line 181, in func_with_args
return func(*args, **current_args)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\contrib\framework\python\ops\variables.py", line 217, in variable
use_resource=use_resource)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 341, in _true_getter
use_resource=use_resource)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 653, in _get_single_variable
name, "".join(traceback.format_list(tb))))
ValueError: Variable d_conv1/BatchNorm/beta already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at:
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 1228, in init
self._traceback = _extract_stack()
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 2336, in create_op
original_op=self._default_original_op, op_def=op_def)
File "C:\Users\kuseet\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 768, in apply_op
op_def=op_def)
Process finished with exit code 1
Thank you for your reply.
When I run the train.py, the terminal show me the above issue.
I try to change reuse=True in the model.py , but errors still exist.
What GPU are you using and how much memory do you have?
My GPU is GTX960M 2G.
I did't use GPU，only CPU(core i7-4720HQ) and 16GB memory.
Can you try it with tensorflow V1.0 or wait for 2-3 days I will update the whole repo.
It seems to work now, thank you!
Hi Kusset,
I am facing the same problem like you have done. How did you make it run? thank you!!