-
Papers Weighted CE Loss and Focal Loss are set to the opposite
-
Thanks for your amazing job.
i make a custom dataset. but my training is wrong. my loss is 0.
so i want to ask for dataset.
Do i normalized Object Size Range by image width and height?
And …
-
Hi, I have read through the paper and have a question above. I guess focal loss's performance usually better than OHEM in imbalance problems.
Thanks in advance.
-
### Prerequisite
- [X] I have searched [Issues](https://github.com/open-mmlab/mmdetection3d/issues) and [Discussions](https://github.com/open-mmlab/mmdetection3d/discussions) but cannot get the exp…
-
I try to merge your focal-loss with SSD, the training loss can converge to 1.x, but the testset mAP is not as well as OHEM method. Have you test focal-loss on any dataset?
-
Hi, thanks for such a great package!
I'm currently training a simple U-net on a binary image classification problem (in this case, identifying water in satellite imagery). I am exploring different …
-
Hi,
I see that starting from deformable DETR, it doesn't make sense to have cardinality loss. In the original DETR paper, the class_embed head outputs num_classes + 1, to also output a value for th…
-
### What happened + What you expected to happen
If I add pytorch profiler tool in train_function of TorchTrainer, it will report an error:
```
Training started without custom configuration.
(Torch…
-
Hi,
I see that starting from deformable DETR, it doesn't make sense to have cardinality loss. In the original DETR paper, the class_embed head outputs num_classes + 1, to also output a value for th…
-
- [检测论文综述（一） : 从RCNN到Mask-RCNN - 简书](https://www.jianshu.com/p/79314ce72007)
- [讲透RCNN, Fast-RCNN, Faster-RCNN，将CNN用于目标检测 - 简书](https://www.jianshu.com/p/d06514a8ffe4)
- [实例分割模型Mask R-CNN详解：从R-CNN，F…