Guys. I have trained model in train_condition.py with images dimension 192x256. But when I try to start train_generator I receive next error:
Traceback (most recent call last): File "train_generator.py", line 713, in <module> main() File "train_generator.py", line 703, in main train(opt, train_loader, test_loader, test_vis_loader, board, tocg, generator, discriminator, model) File "train_generator.py", line 301, in train fake_concat = torch.cat((parse, output_paired), dim=1) RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 192 but got size 128 for tensor number 1 in the list.
On 768x1024 It works nice. But on low dimension. all width stays in tensor 128. Why not 192?
Guys. I have trained model in train_condition.py with images dimension 192x256. But when I try to start train_generator I receive next error:
Traceback (most recent call last): File "train_generator.py", line 713, in <module> main() File "train_generator.py", line 703, in main train(opt, train_loader, test_loader, test_vis_loader, board, tocg, generator, discriminator, model) File "train_generator.py", line 301, in train fake_concat = torch.cat((parse, output_paired), dim=1) RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 192 but got size 128 for tensor number 1 in the list.
On 768x1024 It works nice. But on low dimension. all width stays in tensor 128. Why not 192?