Similar issue, it either exits with no warning on hitting render of segfaults. As far as I can tell both crashes happen at the same time in the console window. It's happened with multiple gifs. The text from the window for me is:
cudnn is used OK E:/test/test.gif Input FPS: 12.5 E:/test/ E:/test/test.gif E:/test/test//test.mp4 12.5 0 0 0 Interpolate 1 frames
I'm on Win 7 (I really should update, I know. Just lazy), 24GB of ram, 1080ti.
cudnn is used OK C:/Users/t.becker/Desktop/MVI_2712.MP4 Input FPS: 25.0 C:/Users/t.becker/Desktop C:/Users/t.becker/Desktop/MVI_2712.MP4 C:/Users/t.becker/Desktop/MVI_2712//MVI_2712.mp4 25.0 0 0 0 Interpolate 1 frames The testing model weight is: ./model_weights/best.pth Framerate Index: 0 Traceback (most recent call last): File "my_design.py", line 79, in render File "my_DAIN_class.py", line 469, in RenderVideo File "my_DAIN_class.py", line 202, in interpolate File "site-packages\torch\nn\modules\module.py", line 541, in __call__ File "networks\DAIN_slowmotion.py", line 129, in forward File "site-packages\torch\nn\modules\module.py", line 541, in __call__ File "site-packages\torch\nn\modules\container.py", line 92, in forward File "site-packages\torch\nn\modules\module.py", line 541, in __call__ File "site-packages\torch\nn\modules\conv.py", line 345, in forward File "site-packages\torch\nn\modules\conv.py", line 342, in conv2d_forward RuntimeError: CUDA out of memory. Tried to allocate 8.10 GiB (GPU 0; 11.00 GiB total capacity; 919.56 MiB already allocated; 7.56 GiB free; 30.44 MiB cached)
