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)

Home Page:https://arxiv.org/pdf/2004.09927.pdf

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

RuntimeError: CUDA out of memory.

gohguodong opened this issue · comments

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)

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