ItamarKanter

I had the same issue. I have researched the issue and found that with _cross entropy loss_ the precision do improved. Changing of [focal.py](https://github.com/ZhaoJ9014/face.evoLVe.PyTorch/blob/master/loss/focal.py) from: ``` class FocalLoss(nn.Module): def __init__(self,...

any update on this issue? is there a way to load multiple .beaton files into a single dataloader?

* the workload of creating files can be distributed among multiple processes which is faster and safer (in case of a fault in one of the processes) * provide flexibility...