thanks the code, when use discriminator, gl inpaint input maybe use input_gd_fake = x * (1 - mask) + input_gd_fake * mask, while in this line input_gd_fake direct use generate network output, how do you think this diff ?
|
output_fake = model_cd((input_ld_fake.to(gpu), input_gd_fake.to(gpu))) |
thanks the code, when use discriminator, gl inpaint input maybe use
input_gd_fake = x * (1 - mask) + input_gd_fake * mask, while in this lineinput_gd_fakedirect use generate network output, how do you think this diff ?GLCIC-PyTorch/train.py
Line 229 in 71870a1