I use the Chainer v1.9.0, but got an AssertionError when i run the catgan_test.py. I guess that the version of Chainer we have used are different.

$ python catgan_test.py
Traceback (most recent call last):
File "catgan_test.py", line 70, in
fake_x=gen(z,test=True).data
File "catgan_test.py", line 53, in call
h1=F.leaky_relu(self.bn0(self.l0(z),test),slope=0.1)
File "/usr/local/lib/python2.7/dist-packages/chainer/links/connection/linear.py", line 72, in call
return linear.linear(x, self.W, self.b)
File "/usr/local/lib/python2.7/dist-packages/chainer/functions/connection/linear.py", line 79, in linear
return LinearFunction()(x, W, b)
File "/usr/local/lib/python2.7/dist-packages/chainer/function.py", line 115, in call
self._check_data_type_forward(in_data)
File "/usr/local/lib/python2.7/dist-packages/chainer/function.py", line 182, in _check_data_type_forward
in_type = type_check.get_types(in_data, 'in_types', False)
File "/usr/local/lib/python2.7/dist-packages/chainer/utils/type_check.py", line 46, in get_types
_get_type(name, i, x, accept_none) for i, x in enumerate(data))
File "/usr/local/lib/python2.7/dist-packages/chainer/utils/type_check.py", line 46, in
_get_type(name, i, x, accept_none) for i, x in enumerate(data))
File "/usr/local/lib/python2.7/dist-packages/chainer/utils/type_check.py", line 60, in _get_type
isinstance(array, cuda.ndarray))
AssertionError

Hello,

I keep getting this error when I try to compile your code:
GPU: -1

Minibatch-size: 100

epoch: 200

load MNIST dataset
Downloading train-images-idx3-ubyte.gz...
Done
Downloading train-labels-idx1-ubyte.gz...
Done
Downloading t10k-images-idx3-ubyte.gz...
Done
Downloading t10k-labels-idx1-ubyte.gz...
Done
Converting training data...
Done
Converting test data...
Done
Save output...
Done
Convert completed
epoch 1
Traceback (most recent call last):
File "catgan_train.py", line 164, in
fake_x=gen(z)
File "catgan_train.py", line 73, in call
h1=F.leaky_relu(self.bn0(self.l0(z),test),slope=0.1)
TypeError: call() takes exactly 2 arguments (3 given)

Could you please help? Thank you.

load MNIST dataset
epoch 1
Traceback (most recent call last):
File "catgan_train.py", line 164, in
fake_x=gen(z)
File "catgan_train.py", line 73, in call
h1=F.leaky_relu(self.bn0(self.l0(z),test),slope=0.1)
TypeError: call() takes 2 positional arguments but 3 were given

Even after making above changes, I get this error..
load MNIST dataset epoch 1 Traceback (most recent call last): File "catgan_train.py", line 164, in <module> fake_x=gen(z) File "catgan_train.py", line 74, in __call__ h2=F.leaky_relu(self.bn1(self.l1(h1),test),slope=0.1) TypeError: __call__() takes 2 positional arguments but 3 were given

I removed test from all these 3 line..


h1=F.leaky_relu(self.bn0(self.l0(z)),slope=0.1)
h2=F.leaky_relu(self.bn1(self.l1(h1)),slope=0.1)
h3=F.leaky_relu(self.bn2(self.l2(h2)))
h4=F.sigmoid(self.l3(h3))
It still gives me this error..


load MNIST dataset
epoch 1
Traceback (most recent call last):
File "catgan_train.py", line 165, in
fake_y=dis(fake_x)
File "catgan_train.py", line 117, in call
h1=F.leaky_relu(self.bn0(self.l0(x)+F.gaussian(mu_array2,log_std_array2),test),slope=0.1)
TypeError: call() takes 2 positional arguments but 3 were given

So I removed test in other calls too... like this..

h1=F.leaky_relu(self.bn0(self.l0(x)+F.gaussian(mu_array2,log_std_array2)),slope=0.1)
h2=F.leaky_relu(self.bn1(self.l1(h1)+F.gaussian(mu_array3,log_std_array3)),slope=0.1)
h3=F.leaky_relu(self.bn2(self.l2(h2)+F.gaussian(mu_array4,log_std_array4)),slope=0.1)
h4=F.leaky_relu(self.bn3(self.l3(h3)+F.gaussian(mu_array5,log_std_array5)),slope=0.1)
h5=F.leaky_relu(self.bn4(self.l4(h4)+F.gaussian(mu_array6,log_std_array6)),slope=0.1)
h6=F.softmax(self.l5(h5))

It gives me this error..

load MNIST dataset
epoch 1
Traceback (most recent call last):
File "catgan_train.py", line 170, in
o_dis.zero_grads()
AttributeError: 'Adam' object has no attribute 'zero_grads'

I am a little confused about the loss function of generator.
I think it should be L_gen=-d_entropy1(fake_y)+d_entropy2(fake_y)

Sorry!! Got an ImportError: No module named net??

And how to train with my own dataset?

Thanks for the help