解决CUDA out of memory

问题

用Pytorch跑模型时，会出现RuntimeError: CUDA out of memory

解决方法

1.真的没有内存了

RuntimeError: CUDA out of memory. Tried to allocate 64.00 MiB 
(GPU 0; 4.00 GiB total capacity; 2.92 GiB already allocated; 58.76 MiB free; 
2.95 GiB reserved in total by PyTorch)

可以改小batch_size
2.内存足够，不分配

RuntimeError: CUDA out of memory. 
Tried to allocate 784.00 MiB 
(GPU 0; 4.00 GiB total capacity; 456.81 MiB already allocated; 2.47 GiB free; 
548.00 MiB reserved in total by PyTorch)

Win10下多线程的问题，num_threads/workers=0解决