fsns_demo reshape error

[fredO13]

I have an error at line 156 of fsns.py when running fsns_demo.py with an image from SVHN test dataset.
images = F.reshape(images, (batch_size, num_channels, height, 4, -1))
batch_size = 1
num_channels = 3
height = 48
width = 182

the error is raised in chainer.function.reshape() :

Invalid operation is performed in: Reshape (Forward)

Expect: prod(x.shape) % known_size(=576) == 0
Actual: 288 != 0

command line is
python ./chainer/fsns_demo.py --gpu -1 ./downloads/model/ model_35000.npz ./downloads/svhn/test/2.png ./datasets/svhn/svhn_char_map.json

thanks

[fredO13]

I don't get this error when using a cropped version of the image (64x64) obtained using the prepare_svhn_crops.py script.
but I get another error :

File "C:\Users\U043511\Anaconda3\envs\SEE\lib\site-packages\chainer\functions\pooling\average_pooling_2d.py", line 227, in average_pooling_2d
return AveragePooling2D(ksize, stride, pad, False).apply((x,))[0]
File ".\SEE\lib\site-packages\chainer\function_node.py", line 334, in apply
outputs = self.forward(in_data)
File ".\SEE\lib\site-packages\chainer\function_node.py", line 592, in forward
return self.forward_cpu(inputs)
File ".\SEE\lib\site-packages\chainer\functions\pooling\average_pooling_2d.py", line 27, in forward_cpu
col = conv.im2col_cpu(x[0], self.kh, self.kw, self.sy, self.sx,
File ".\SEE\lib\site-packages\chainer\utils\conv.py", line 74, in im2col_cpu
assert out_w > 0, 'Width in the output should be positive.'
AssertionError: Width in the output should be positive.