The error encountered when executing train.py

[ZC-peng]

Hello, I encountered the following console prompt when executing train.py. I suspect it may be caused by a version conflict. I have installed the latest versions of PyTorch and CUDA according to your requirements in the readme. I would like to confirm the specific versions you are using. (I can obtain training results, but after testing, the generated training results are incorrect. When I replace the training results with the ckpt you provided, the test results are normal. So I suspect the error is caused by this prompt.)

console prompt：Detected call of lr_scheduler.step() before optimizer.step(). In PyTorch 1.1.0 and later, you should call them in the opposite order: optimizer.step() before lr_scheduler.step(). Failure to do this will result in PyTorch skipping the first value of the learning rate schedule.

[htcr]

Hi @ZC-peng , this codebase is intended to use the latest version of pytorch. The network architecture is quite simple and standard so it's unlikely to have weird dependencies or compatibility issues.