pytorch-image-models/timm/loss
Hoan Nguyen 39190f5f44
Remove inplace operators when calculating the loss
Remove inplace operators to overcome the following error when using `asymmetric_loss`
```
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation
```
2022-10-17 10:41:21 +02:00
..
__init__.py Update binary cross ent impl to use thresholding as an option (convert soft targets from mixup/cutmix to 0, 1) 2021-09-23 15:45:39 -07:00
asymmetric_loss.py Remove inplace operators when calculating the loss 2022-10-17 10:41:21 +02:00
binary_cross_entropy.py Update binary cross ent impl to use thresholding as an option (convert soft targets from mixup/cutmix to 0, 1) 2021-09-23 15:45:39 -07:00
cross_entropy.py Update binary cross ent impl to use thresholding as an option (convert soft targets from mixup/cutmix to 0, 1) 2021-09-23 15:45:39 -07:00
jsd.py Fix some attributions, add copyrights to some file docstrings 2020-07-27 13:44:56 -07:00