我的顯卡有6g顯存，但是每次都提示不夠用，model 跑的是yolo v3 , 求指導怎么弄。
錯誤提示：
Traceback (most recent call last):
File "D:/08-YOLO/PyTorch-YOLOv3/train.py", line 125, in <module>
optimizer.step()
File "C:\ProgramData\Anaconda3\envs\CSGPU\lib\site-packages\torch\optim\adam.py", line 101, in step
denom = exp_avg_sq.sqrt().add_(group['eps'])
RuntimeError: CUDA out of memory. Tried to allocate 18.00 MiB (GPU 0; 6.00 GiB total capacity; 870.30 MiB already allocated; 8.60 MiB free; 89.70 MiB cached)
轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/226509.html
標籤：人工智能技術
上一篇：關于DQN訓練神經網路的問題
下一篇：socket on SSL: attempt to connect already-connected SSLSocket!