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)

合集 - Pytorch深度学习(4)

1.Pytorch学习笔记-（一）基础入门2023-10-142.Pytorch学习笔记-（二）搭建Pytorch环境（Pytorch2.1+CUDA12.1+Anaconda3_2023+Pycharm2023）2023-10-09

3.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)2021-09-07

4.Pytorch学习笔记-（三）张量2023-10-18

收起

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