Closed infiniteperplexity closed 7 years ago
Need to wrap with int()
for python 3 compatibility. python 2 int division results in an int. Similar fixes need to be made to the other examples.
Just merged the changes so you should just be able to pull. Thank @isaacmg for the fix. https://github.com/bstriner/keras-adversarial/pull/30
Cheers
Great, thanks!
Sent from my iPhone
On Jun 27, 2017, at 11:09 PM, Ben notifications@github.com wrote:
Need to wrap with int() for python 3 compatibility. python 2 int division results in an int. Similar fixes need to be made to the other examples.
Just merged the changes so you should just be able to pull. Thank @isaacmg for the fix. #30
Cheers
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.
I get the following error when I try to run the code:
main() Traceback (most recent call last):
File "", line 1, in
main()
File "", line 137, in main
generator = model_generator()
File "", line 33, in model_generator
model.add(Convolution2D(nch / 2, h, h, border_mode='same', W_regularizer=reg()))
File "C:\Users\M543015\AppData\Local\Continuum\Anaconda3\lib\site-packages\keras\models.py", line 476, in add output_tensor = layer(self.outputs[0])
File "C:\Users\M543015\AppData\Local\Continuum\Anaconda3\lib\site-packages\keras\engine\topology.py", line 569, in call self.build(input_shapes[0])
File "C:\Users\M543015\AppData\Local\Continuum\Anaconda3\lib\site-packages\keras\layers\convolutional.py", line 134, in build constraint=self.kernel_constraint)
File "C:\Users\M543015\AppData\Local\Continuum\Anaconda3\lib\site-packages\keras\legacy\interfaces.py", line 88, in wrapper return func(*args, **kwargs)
File "C:\Users\M543015\AppData\Local\Continuum\Anaconda3\lib\site-packages\keras\engine\topology.py", line 391, in add_weight weight = K.variable(initializer(shape), dtype=dtype, name=name)
File "C:\Users\M543015\AppData\Local\Continuum\Anaconda3\lib\site-packages\keras\initializers.py", line 208, in call dtype=dtype, seed=self.seed)
File "C:\Users\M543015\AppData\Local\Continuum\Anaconda3\lib\site-packages\keras\backend\theano_backend.py", line 2123, in random_uniform return rng.uniform(shape, low=minval, high=maxval, dtype=dtype)
File "C:\Users\M543015\AppData\Local\Continuum\Anaconda3\lib\site-packages\theano\sandbox\rng_mrg.py", line 1339, in uniform for i in size]), msg
AssertionError: size must be a tuple of int or a Theano variable
Is this an issue somehow related to versioning, or to choice of backend?