-
大佬！你好，想问下使用的混合损失函数都是线性组合吗？像dice和focal就是loss=dice loss +focal loss。自己不大确定想问问。谢谢！
-
I want to add focal loss for my dataset training for classification to tackle the class imbalance problem. As I went through the focal_loss only applicable for yolo layer.
_Can anyone please tell me …
-
### Description
Please specify cuda:0 at the very beginning.
```python
import torch
import numpy as np
import os
from network.cv.SSD.backbone_mobilenetv1_pytorch import SSDWithMobileNetV1 as SSD…
-
## 🚀 Feature
A loss functions API in torchvision.
## Motivation
The request is simple, we have loss functions available in torchvision
E.g. `sigmoid_focal_loss` , `l1_loss`. But these are qu…
-
focal loss at iteration 30995: 7.344306945800781
pull loss at iteration 30995: 0.05117112770676613
push loss at iteration 30995: 0.10568550229072571
regr loss at iteration 30995: 0.2…
-
# focal_loss028/029
- **gamma = 0.5 train failed**
- gamma = 1.0 miou=0.377 (for upsamle_layer=3) 0.386 (for upsample_layer=5)
- gamma = 2.0 is slight better than gamma=1.0
```
python test/pspn…
-
如题，我样本 最小的类和 最大类 数量 倍数达到了 50倍，tensorflow 里用 focal loss 起到了作用，请问 API方式啥时候提供？目前在用你们 API方式
-
### Prerequisite
- [X] I have searched [Issues](https://github.com/open-mmlab/mmcv/issues) and [Discussions](https://github.com/open-mmlab/mmcv/discussions) but cannot get the expected help.
- [X] Th…
-
-
Two questions
1. `alpha_t` is unused below.
2. should we use the following to derive the BCECrossEntropyLoss:
> ` pt = torch.log(p) * target.float() + torch.log(1.0 - p) * (1 - target).float(…