BCELoss was unstable so just get logits from model and use BCEwithLog…

[deshwalmahesh]

Changes according to Performance Tuning: Official docs

1. Use bias = False in Line 9 of model of u2net.py
2. Line 67-69: Usetorch.backends.cudnn.benchmark = Trueand use Mixed Precision Training
3. Use BceWithLogitLoss : Line 29 in place of BCELoss of `training
4. Return logits as d0-d6 in place of Sigmoids: Line 525 of u2net.py
5. Set torch.backends.cudnn.benchmark = True : Line 69 of training