RuntimeError: CUDA out of memory. Tried to allocate 1.07 GiB (GPU 0; 4.00 GiB total capacity; 2.57 GiB already allocated; 84.45 MiB free; 2.59 GiB reserved in total by PyTorch)

wmcnally / golfdb

GolfDB is a video database for Golf Swing Sequencing, which involves detecting 8 golf swing events in trimmed golf swing videos. This repo demos the baseline model, SwingNet.

204 stars 62 forks source link

RuntimeError: CUDA out of memory. Tried to allocate 1.07 GiB (GPU 0; 4.00 GiB total capacity; 2.57 GiB already allocated; 84.45 MiB free; 2.59 GiB reserved in total by PyTorch) #10

Closed HadhamiRjiba closed 3 years ago

HadhamiRjiba commented 3 years ago

Hello, when i am running "python train.py ",, i have this message in below: " **training, momentum, eps, torch.backends.cudnn.enabled

RuntimeError: CUDA out of memory. Tried to allocate 1.07 GiB (GPU 0; 4.00 GiB total capacity; 2.57 GiB already allocated; 84.45 MiB free; 2.59 GiB reserved in total by PyTorch)**"

Any idea what might cause this ?

HadhamiRjiba commented 3 years ago

Is there any way to know how big a model or a network my system can handle without running into this issue?

wmcnally commented 3 years ago

Your GPU ran out of memory. Try lowering the batch size.

HadhamiRjiba commented 3 years ago

yes!. I reduced the batch size to 1 and now it works with train.py.. but the problem now is in running eval.py (is showing the same error) : "RuntimeError: CUDA out of memory. Tried to allocate 58.00 MiB (GPU 0; 4.00 GiB total capacity; 2.49 GiB already allocated; 44.45 MiB free; 2.57 GiB reserved in total by PyTorch)"".. have you any idea ??

wmcnally commented 3 years ago

Hmm. The batch size is 1 by default in eval.py. You could try lowering seq_length. Looks like you only have 4 GB of GPU memory. I used a GPU with 12 GB memory.

HadhamiRjiba commented 3 years ago

@wmcnally it works..thank you