sjscotti
commented
3 years ago I am having the same problem when I use the flags --GPU -1 --with_scratch
The runtime error does not appear to depend on the image size since it also occurs when I use a small image
that would work with --GPU 0
python run.py --input_folder test_images\old_w_scratch --output_folder output --GPU -1 --with_scratch Running Stage 1: Overall restoration initializing the dataloader model weights loaded directory of testing image: D:\project\Bringing-Old-Photos-Back-to-Life\test_images\old_w_scratch processing 1.png Traceback (most recent call last): File "detection.py", line 174, in
main(config)
File "detection.py", line 144, in main
P = torch.sigmoid(model(scratch_image_scale))
File "D:\ProgramData\Anaconda3\envs\GAN\lib\site-packages\torch\nn\modules\module.py", line 889, in _call_impl
result = self.forward(*input, kwargs)
File "D:\project\Bringing-Old-Photos-Back-to-Life\Global\detection_models\networks.py", line 112, in forward
x = self.first(x)
File "D:\ProgramData\Anaconda3\envs\GAN\lib\site-packages\torch\nn\modules\module.py", line 889, in _call_impl
result = self.forward(*input, *kwargs)
File "D:\ProgramData\Anaconda3\envs\GAN\lib\site-packages\torch\nn\modules\container.py", line 119, in forward
input = module(input)
File "D:\ProgramData\Anaconda3\envs\GAN\lib\site-packages\torch\nn\modules\module.py", line 889, in _call_impl
result = self.forward(input, kwargs)
File "D:\ProgramData\Anaconda3\envs\GAN\lib\site-packages\torch\nn\modules\conv.py", line 399, in forward
return self._conv_forward(input, self.weight, self.bias)
File "D:\ProgramData\Anaconda3\envs\GAN\lib\site-packages\torch\nn\modules\conv.py", line 396, in _conv_forward
self.padding, self.dilation, self.groups)
RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same
You are using NL + Res
Finish Stage 1 ...
Running Stage 2: Face Detection Finish Stage 2 ...