errors with gray scale input or output or both

[eyaler]

i am seeing errors when either input_c_dim=1 or output_c_dim=1 or both of them =1

only input or output ==1 and the other==3: ValueError: Trying to share variable d_h0_conv/w, but specified shape (5, 5, 6, 64) and found shape (5, 5, 4, 64).

both ==1: ValueError: Cannot feed value of shape (1, 256, 256, 1, 6) for Tensor 'real_A_and_B_images:0', which has shape '(1, 256, 256, 2)'

[eyaler]

i fixed this on my fork. if interested i can make a PR

[danmic]

@eyaler I experienced the same problem. How did you fix it?

[yangjax]

i have the same problem, have you solved it？

[danmic]

I changed the parameters of the init function like this:

def __init__(self, sess, db_path, image_size=256, batch_size=1, sample_size=1, output_size=256, gf_dim=64, df_dim=64, L1_lambda=100, input_c_dim=1, output_c_dim=1, dataset_name='data', checkpoint_dir=None, sample_dir=None):

which sounds quite strange because I passed the parameters in the main... You may also need to change something else in the code, I don't remember if it worked directly with this trick.

[joschkazj]

I was having similar issue and submitted #34 with a potential fix. HTH