Closed paul-ferragut closed 1 year ago
hey, you should look where this number 286 is coming from. There is an augmentation step in dataset.py:
input_image, real_image = resize(input_image, real_image, 286, 286)
This may not be what you want. I think this is where your error happens but you need to adjust the model, too. You would want your model to produce higher resolution which is defined by the number of up conv blocks. Same goes for your input (conv blocks). You should definitely add a layer there, too.
Anyway, for those questions you should rather check out the original repository I am sure people have asked this already.
closed due to lack of response
I managed to train images in format 256x256 and tried with format 512x512 in
config.py
got errors the following errors
Is it possible to train larger sizes? Is it possible training rectangular format images?