search

maudzung / TTNet-Real-time-Analysis-System-for-Table-Tennis-Pytorch

Unofficial implementation of "TTNet: Real-time temporal and spatial video analysis of table tennis" (CVPR 2020)
https://arxiv.org/pdf/2004.09927.pdf
586 stars 157 forks source link

RuntimeError: CUDA out of memory. #12

Open gohguodong opened 3 years ago

gohguodong commented 3 years ago

I followed the previous thread on this runtime error: CUDA out of memory issue. i tried reducing the batch_size to 1, to it still can't run the code. may i know what could the problem be? what's the required memory size in order to run it at the default batch size?

RuntimeError: CUDA out of memory. Tried to allocate 214.00 MiB (GPU 0; 2.00 GiB total capacity; 353.43 MiB already allocated; 108.59 MiB free; 410.00 MiB reserved in total by PyTorch)

koren88i commented 3 years ago

Buy better graphics card. Or reduce batch size to 6 or even 4. Worked for me.