-
Thank you for your work, but I am using FocalLoss and LocLoss in your loc_loss. The output is nan
ghost updated
3 years ago
-
## ❓ Questions and Help
Hi All,
I Have this code
```
import optuna
from torch.optim.lr_scheduler import ReduceLROnPlateau
# Assuming dataset is already defined
train_size = int(0.8 * len(da…
-
## 🚀 Feature
Currently we only support focal loss for binary cases.
Some users have reported the need to use it for multi class classification #551
Consider adapting MONAI version: https://gith…
-
Why there are two version of focal loss methods in _"class FocalLoss(nn.Module): URL: [https://github.com/kuangliu/pytorch-retinanet/blob/2199fd9711fd787ae409800a499db73e6d466fd7/loss.py](url)" ????
-
### Motivation for the feature
The [SoftSeg paper](https://pubmed.ncbi.nlm.nih.gov/33784599/) recommends an omega of 8 for MS lesion segmentation, but that parameter is hard-coded to 14:
https:/…
-
When I run this program , an error occurs:
"NameError: name 'long' is not defined"
it points to line 11 of file focalloss.py:
if isinstance(alpha,(float,int,long)): self.alpha = torch.Tensor(…
-
作者您好！
我运行python setup.py develop时候出现,运行环境cuda11.0 python3.6 pytorch1.7.1 .请问怎么解决呢？
running develop
running egg_info
creating focalloss.egg-info
writing focalloss.egg-info/PKG-INFO
wr…
-
你好，请问该项目的运行效果是什么样的呢
我在运行时会出现以下错误，请问可以帮忙解答下吗 不胜感激
D:\GP\GraduationProject-main\src\utils\FocalLoss.py:43: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to in…
-
Hello All, how should I use the focal loss inside the config file? It pops up this strange message for me...
32
33 loss = -1 * (1-pt)**self.gamma * logpt
---> 34 if self.size_average: return loss.mean()
35 …