UGATIT icon indicating copy to clipboard operation
UGATIT copied to clipboard

Published 20 hours ago • verified publisher icon taki0112

Single channel training set

Open TKassis opened this issue 6 years ago • 4 comments
trafficstars

Trying to train on single-channel grayscale images using '--img_ch 1' argument during training but I get the following error immediately after starting training:

ValueError: Trying to share variable generator_A/conv/conv2d/kernel, but specified shape (7, 7, 3, 64) and found shape (7, 7, 1, 64).

TKassis avatar Aug 05 '19 21:08 TKassis

Similar problem here. I am using 4-channel image and get an error message: ValueError: Trying to share variable generator_A/conv/conv2d/kernel, but specified shape (7, 7, 3, 64) and found shape (7, 7, 4, 64).

Did you solve the problem? what if the input is 4-channel and output is 1-channel?

yxt132 avatar Aug 12 '19 11:08 yxt132

Similar problem here. I am using 4-channel image and get an error message: ValueError: Trying to share variable generator_A/conv/conv2d/kernel, but specified shape (7, 7, 3, 64) and found shape (7, 7, 4, 64).

Did you solve the problem? what if the input is 4-channel and output is 1-channel?

I have not. Just been using 3 channels instead.

TKassis avatar Aug 12 '19 18:08 TKassis

Is there an error in the train phase?

taki0112 avatar Aug 15 '19 05:08 taki0112

Same problems, in training Code.

chokyungjin avatar Nov 23 '20 11:11 chokyungjin