flowplusplus

flowplusplus copied to clipboard

> File "/data00/home/huwenbo.ml/flowplusplus/train.py", line 84, in main > train(epoch, net, trainloader, device, optimizer, scheduler, > File "/data00/home/huwenbo.ml/lib/conda/envs/f++/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 28, in decorate_context > return func(*args, **kwargs) > File "/data00/home/huwenbo.ml/flowplusplus/train.py", line 99,...

xchuwenbo

Autograd error: Inplace operations modify variable needed for gradient computations.

3

I followed instructions from ```README.md``` and ran the following ```python train.py --batch_size 1 --gpu_ids [0]``` This yields the following error: ```RuntimeError: one of the variables needed for gradient computation has...

AlexanderMath

Is this implementation finished?

1

Hello @chrischute, I hope you are good. I would like to learn from the FLOW ++ paper. Unfortunately, the original implementation is unintelligible to me. I would say it's because...

mjack3

bits per dim got only 3.38 in both train and valid

1

Thanks for your code! but i got an issue when running it i set the parameters all the same as the paper and change the epoch to 400 times (same...

ClaireTU