RuntimeError: CUDA out of memory. Tried to allocate 756.00 MiB (GPU 0; 6.00 GiB total capacity; 3.41 GiB already allocated; 0 bytes free; 4.59 GiB reserved in total by PyTorch)

[909982211]

The GPU i used is RTX 2060 6G...really not enough?

OK，It's my fault,i should use --gpu1(because the 0 is not the Nvidia gpu),but .....an other problem appears when the program was to be end:

RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

i am sure that my cuda version is correct and it match the pytorch .

[monero778176]

I used GTX 1650 4G on windows platform, it's work and enough, maybe check the environment setting.

[909982211]

I used GTX 1650 4G on windows platform, it's work and enough, maybe check the environment setting.

Now it said:
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.