YoloV5_RuntimeError: CUDA out of memory. Tried to allocate 100.00 MiB (GPU 0; 2.00 GiB total capacity; 1.15 GiB already allocated; 0 bytes free; 1.19 GiB reserved in total by PyTorch)

报错信息：

RuntimeError: CUDA out of memory. Tried to allocate 100.00 MiB (GPU 0; 2.00 GiB total capacity; 1.15 GiB already allocated; 0 bytes free; 1.19 GiB reserved in total by PyTorch)
  0%|          | 0/8 [00:02<?, ?it/s]

对策：

　　train.py：减小batch-size的default大小