Can't run FLAVR

[FranGamer1892]

At first I tried to use Flowframes, but since it gave out an error I tried following your instructions on github. When I tried to run python interpolate.py --input_video input.mp4 --factor 8 --load_model FLAVR8X.pth I got a very similar if not identical error message:

13.000209881905063 Traceback (most recent call last): File "interpolate.py", line 133, in <module> videoTensor , resizes = video_transform(videoTensor , args.downscale) File "interpolate.py", line 121, in video_transform videoTensor = transforms(videoTensor) File "C:\Users\frangamer1892roblox\MiniConda3\lib\site-packages\torchvision\transforms\transforms.py", line 60, in __call__ img = t(img) File "D:\FLAVR\dataset\transforms.py", line 333, in __call__ return to_tensor(clip) File "D:\FLAVR\dataset\transforms.py", line 107, in to_tensor return clip.float().permute(3, 0, 1, 2) / 255.0 RuntimeError: [enforce fail at ..\c10\core\CPUAllocator.cpp:79] data. DefaultCPUAllocator: not enough memory: you tried to allocate 25944883200 bytes.

I am not really use what to do now. This are my specs if they help in any way:

DxDiag.txt

[tarun005]

Hi,

As the error message states, you unfortunately do not have enough CPU memory to load all the frames and perform interpolation. Alternatively you can only load four frames at a time into the memory.

[FranGamer1892]

And how would I do that? Thanks.

El vie., 9 de julio de 2021 8:15 p. m., Tarun K @.***> escribió:

Hi,

As the error message states, you unfortunately do not have enough CPU memory to load all the frames and perform interpolation. Alternatively you can only load four frames at a time into the memory.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/tarun005/FLAVR/issues/29#issuecomment-877503901, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADEKT6FBVMC2M455YLHBSNTTW57JLANCNFSM4735THCQ .

[tarun005]

One way is to save all frame in a folder and write a pytorch dataloader to load only 4 frames at once, like how you generally train a network.

https://pytorch.org/tutorials/beginner/data_loading_tutorial.html

[FranGamer1892]

Thanks, I'll check it out.

El vie., 16 de julio de 2021 5:27 a. m., Tarun K @.***> escribió:

One way is to save all frame in a folder and write a pytorch dataloader to load only 4 frames at once, like how you generally train a network.

https://pytorch.org/tutorials/beginner/data_loading_tutorial.html

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/tarun005/FLAVR/issues/29#issuecomment-881271792, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADEKT6B55HPTYOBBKSSDKLLTX7UNRANCNFSM4735THCQ .