-
Focal loss is a method to process the imbalance examples. it is not better in the balance scene. for the level of imbalance , choose alpha=0.5 and gamma=2 may improve by 2% according to the author.
…
-
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…
-
### 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…
-
Did you try Focal loss, how about its performance ?
-
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 @unsky
Please, can you check, did I read your Focal Loss formulas correctly?
For CE, delta is:
* `if (i == j)` then `delta = 1-p`
* `if (i != j)` then `delta = -p`
----
For Focal Los…
-
total time is 254.24768543243408, average time is 0.9892906047954634
lfw face verification accuracy: 0.9095 threshold: 0.37753257
Sat Dec 23 08:19:27 2023 train epoch 2 iter 10 0.08301005559180279…
-
Hi, I'm trying to put `categorical_focal_loss` in my image segmentation task. The dataset is defined with tf.data.Dataset object and the model is defined with keras Model. The model is compiled like
…
-
我在tiny的版本上开启focal loss的训练，并设置50个epoch后才开始测试，此时仍然会出现因为nms导致的显存爆炸
```
Epoch gpu_mem GIoU obj cls total targets img_size
50/299 6.12G 0.05371 0.3158 0.006124 …