Adapt the code for custom input format (different input size / channels)

[bamos]

Adapt the code for custom input format (different input size / channels)

[mgarbade]

Ok, let's say it wasn't super hard :D.

def imread(path,c_dim):
    if c_dim == 3:
        im  = scipy.misc.imread(path, mode='RGB').astype(np.float)
    elif c_dim == 1:
        im  = scipy.misc.imread(path, mode='L').astype(np.float)
        im = np.expand_dims(im, 3)
    else:
        print('Error: c_dim must be either 3 or 1')
            
    return im

Sorry for the spamming ;)

[bamos]

:) Glad you figured it out.

-Brandon.

[kplettl]

@mgarbade do you mind sharing how you were able to make the network work for 1 channel images? I'm new to tensorflow. I have made the modification to the imread function as you suggested but I still get an error about reshaping:
InvalidArgumentError: Cannot reshape a tensor with 786432 elements to shape [64,8,8,8,8,1] (262144 elements) for 'Reshape_1' (op: 'Reshape') with input shapes: [64,64,64,3], [6] and with input tensors computed as partial shapes: input[1] = [64,8,8,8,8,1].

Any advice you can offer would be wonderful!! Thanks!