-
在运行PIDnet时遇到了下面错误：
Traceback (most recent call last):
File "C:\Users\Administrator\.conda\envs\torch\lib\site-packages\mmengine\registry\build_functions.py", line 121, in build_from_cfg
obj =…
-
The problem I encountered is that I changed the train image size 512 in the yaml file to train model, and I also changed the test image size, but when I actually ran the testing, the image size of the…
-
我注意到您在表现不错的模型都使用了ImageNet的预训练模型，
而这部分并没有在您的代码中体现，
我尝试过自定义设计网络但表现并不是很好，
这也许跟一个良好的预训练有关系，
请问能否告诉我怎样在ImageNet上进行预训练，并告知相关细节，万分感谢。
-
您好请问为什么网络最终输出1/8的分割图片，这样如何与标签进行比较和进行实际使用，如果是直接使用上采样不会有很大的误差吗？
-
### Prerequisite
- [X] I have searched [Issues](https://github.com/open-mmlab/mmengine/issues) and [Discussions](https://github.com/open-mmlab/mmengine/discussions) but cannot get the expected help…
-
Hello！
Thank you for your excellent work and analysis
Can you reproduce the PIDNet results with the same accuracy as the original version in the cityscapes test set 78.6? Why is my val 78.4 test 77.…
-
### Prerequisite
- [X] I have searched [Issues](https://github.com/open-mmlab/mmengine/issues) and [Discussions](https://github.com/open-mmlab/mmengine/discussions) but cannot get the expected help.
…
-
Hi, thank you for sharing your work. I tried to train the model on my custom dataset derived from CamVid and I'm getting error during calculating the loss function when target consists of only backgro…
-
Excellent work!
Could you provide a link to download for the 11 category camvid dataset?
-
i just want segmeantation lane,other as background
in the training, backgroud as class 0, lane as class 1, train 200 epoch,but result is very bad
predict
![image](https://user-images.githubuserc…