안녕하세요, 우선 정말 좋은 코드를 공유해주셔서 감사드립니다.
예제로 공개해주신 코드를 돌려보았는데 쿠다 메모리가 초과됐다는 에러가 발생합니다.
Hello, first of all, thank you for sharing such a good code.
I returned the code you released as an example, but there is an error that the Cuda memory has been exceeded.
C:\Users\user\anaconda3\envs\stargan-v2\lib\site-packages\torch\nn\functional.py:2506: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
"See the documentation of nn.Upsample for details.".format(mode))
Traceback (most recent call last):
File "main.py", line 182, in
main(args)
File "main.py", line 59, in main
solver.train(loaders)
File "C:\Users\user\stargan\stargan-v2\core\solver.py", line 123, in train
nets, args, x_real, y_org, y_trg, z_trgs=[z_trg, z_trg2], masks=masks)
File "C:\Users\user\stargan\stargan-v2\core\solver.py", line 259, in compute_g_loss
x_rec = nets.generator(x_fake, s_org, masks=masks)
File "C:\Users\user\anaconda3\envs\stargan-v2\lib\site-packages\torch\nn\modules\module.py", line 532, in call
result = self.forward(*input, kwargs)
File "C:\Users\user\stargan\stargan-v2\core\model.py", line 181, in forward
x = block(x, s)
File "C:\Users\user\anaconda3\envs\stargan-v2\lib\site-packages\torch\nn\modules\module.py", line 532, in call
result = self.forward(*input, *kwargs)
File "C:\Users\user\stargan\stargan-v2\core\model.py", line 117, in forward
out = self._residual(x, s)
File "C:\Users\user\stargan\stargan-v2\core\model.py", line 111, in _residual
x = self.norm2(x, s)
File "C:\Users\user\anaconda3\envs\stargan-v2\lib\site-packages\torch\nn\modules\module.py", line 532, in call
result = self.forward(input, kwargs)
File "C:\Users\user\stargan\stargan-v2\core\model.py", line 77, in forward
return (1 + gamma) * self.norm(x) + beta
RuntimeError: CUDA out of memory. Tried to allocate 64.00 MiB (GPU 0; 8.00 GiB total capacity; 6.33 GiB already allocated; 24.12 MiB free; 6.45 GiB reserved in total by PyTorch)
이렇게 오류가 뜨는데 해결 방법을 알고 싶습니다 ㅠㅠ
I'd like to know how to solve this error.
1170300814
commented
2 years ago
안녕하세요, 우선 정말 좋은 코드를 공유해주셔서 감사드립니다. 예제로 공개해주신 코드를 돌려보았는데 쿠다 메모리가 초과됐다는 에러가 발생합니다. Hello, first of all, thank you for sharing such a good code. I returned the code you released as an example, but there is an error that the Cuda memory has been exceeded.
C:\Users\user\anaconda3\envs\stargan-v2\lib\site-packages\torch\nn\functional.py:2506: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. "See the documentation of nn.Upsample for details.".format(mode)) Traceback (most recent call last): File "main.py", line 182, in
main(args)
File "main.py", line 59, in main
solver.train(loaders)
File "C:\Users\user\stargan\stargan-v2\core\solver.py", line 123, in train
nets, args, x_real, y_org, y_trg, z_trgs=[z_trg, z_trg2], masks=masks)
File "C:\Users\user\stargan\stargan-v2\core\solver.py", line 259, in compute_g_loss
x_rec = nets.generator(x_fake, s_org, masks=masks)
File "C:\Users\user\anaconda3\envs\stargan-v2\lib\site-packages\torch\nn\modules\module.py", line 532, in call
result = self.forward(*input, kwargs)
File "C:\Users\user\stargan\stargan-v2\core\model.py", line 181, in forward
x = block(x, s)
File "C:\Users\user\anaconda3\envs\stargan-v2\lib\site-packages\torch\nn\modules\module.py", line 532, in call
result = self.forward(*input, *kwargs)
File "C:\Users\user\stargan\stargan-v2\core\model.py", line 117, in forward
out = self._residual(x, s)
File "C:\Users\user\stargan\stargan-v2\core\model.py", line 111, in _residual
x = self.norm2(x, s)
File "C:\Users\user\anaconda3\envs\stargan-v2\lib\site-packages\torch\nn\modules\module.py", line 532, in call
result = self.forward(input, kwargs)
File "C:\Users\user\stargan\stargan-v2\core\model.py", line 77, in forward
return (1 + gamma) * self.norm(x) + beta
RuntimeError: CUDA out of memory. Tried to allocate 64.00 MiB (GPU 0; 8.00 GiB total capacity; 6.33 GiB already allocated; 24.12 MiB free; 6.45 GiB reserved in total by PyTorch)
이렇게 오류가 뜨는데 해결 방법을 알고 싶습니다 ㅠㅠ I'd like to know how to solve this error.