Skip to main content

Indie game storeFree gamesFun gamesHorror games
Game developmentAssetsComics
SalesBundles
Jobs
TagsGame Engines

RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the same

A topic by asaph created Nov 09, 2020 Views: 716 Replies: 2
Viewing posts 1 to 3

Hi there, I have this crash report trying to render an mp4 file


App Crash Log Traceback (most recent call last):
  File "my_design.py", line 61, in run
  File "my_DAIN_class.py", line 1538, in RenderVideo
  File "my_DAIN_class.py", line 1391, in StepRenderInterpolation
  File "my_DAIN_class.py", line 1031, in DoInterpolation
  File "my_DAIN_class.py", line 673, in interpolate
  File "site-packages\torch\nn\modules\module.py", line 550, in __call__
  File "networks\DAIN_slowmotion.py", line 162, in forward
  File "site-packages\torch\nn\modules\module.py", line 550, in __call__
  File "site-packages\torch\nn\modules\container.py", line 100, in forward
  File "site-packages\torch\nn\modules\module.py", line 550, in __call__
  File "site-packages\torch\nn\modules\conv.py", line 349, in forward
  File "site-packages\torch\nn\modules\conv.py", line 345, in _conv_forward
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the same

It actually started the first frame

(1 edit)

I’ve tried with the PNG exported frames, and it works like a charm