-
I have trained a one class detection model with EfficientNet+Deconv，but I find the detection box is always shift in the upper left corner, what could be the reason？
-
## ❓ Questions and Help
-
2020-06-17 13:16:06,637 - mmdet - INFO - Environment info:
------------------------------------------------------------
sys.platform: linux
Python: 3.7.0 (default, Oct 9 2018, 10:31:47) [GCC 7.3.0…
qih96 updated
4 years ago
-
我将COCO数据集的相关输入更改为了自己的训练集的相关参数，会有如下报错：
`2020-04-15 15:25:19,647 - mmdet - INFO - Distributed training: False
2020-04-15 15:25:19,647 - mmdet - INFO - MMDetection Version: 1.0.0+unknown
2020-04-15 15…
-
作者你好，最近再用你的代码做实验，十分感谢，训练过程中有几个问题想请教一下
1.对于focalloss，我的理解是仅作为系数，那么虽然计算过程中用了预测的结果，但是不是不应该计算这块的梯度，也就是用stop_gradient？还是说因为本身focal也在引导confidence向正确标签靠近所以应当计算其梯度？另外yolov3的论文提到focalloss对yolo没有提升，请问你在实验的时候…
-
Have you tried the effect of focalloss on semantic segmentation? I tried to implement focalloss myself but the effect is worse than cross entropy. Can you add focalloss to your loss function?
-
When using the command stated in the `README` file I got the following error:
```
2020-01-28 19:01:54 training at epoch 1, lr 0.000100
Traceback (most recent call last):
File "train.py", line …
-
**Checklist**
1. I have searched related issues but cannot get the expected help.
2. The bug has not been fixed in the latest version.
**Describe the bug**
Get a TypeError while running tools/d…
-
When I using get_flops.py to test the flops of FCOS detector, the result seems wrong in FPN and FCOS Head. It seems that flops computing is model-independent, so I don't think it is caused by the FCOS…
-
Your losses.py at https://github.com/MendelXu/ANN/blob/master/models/seg/loss/seg_modules.py has a number of different loss functions including some for embedding layers which are not mentioned in you…