Closed AndyVerne closed 2 years ago
More specific, the loss_rnp_cls doesn't converge.
Did you try changing the hyperparams ? To get it straight, you can train Cascade RCNN, but not Faster RCNN ?
Did you try changing the hyperparams ? To get it straight, you can train Cascade RCNN, but not Faster RCNN ?
Thanks for the reply. I didn't change the hyperparams, the Cascade RCNN is fine. The Faster RCNN with HRNet doesn't work. Meanwhile the Faster RCNN with ResNet101 works out. I have no clue how to deal with it.
Then it is hyperparams most probably. Play around the learning rate, learning rate in this repo is set with 8 Gpus. If your number of gpus are less, use the linear scaling rule to adjust learning rate.
Then it is hyperparams most probably. Play around the learning rate, learning rate in this repo is set with 8 Gpus. If your number of gpus are less, use the linear scaling rule to adjust learning rate.
Thank you so much. Really appreciate for replies! I will give it a try and update the feedback soon. :)
Thanks for your error report and we appreciate it a lot.
Checklist
Describe the bug A clear and concise description of what the bug is.
When I tried to train the Faster R-CNN model via
The same results happened after I chose the ECP as the training method via
python tools/train.py configs/elephant/cityperson/faster_rcnn_hrnet.py
, the model trained generated blank results like below:python tools/train.py configs/elephant/eurocity/faster_rcnn_hrnet.py
.Meanwhile, when I use the cascade mask R-CNN as the training method via![image](https://user-images.githubusercontent.com/23656398/172271268-b7438fc1-550f-48ee-9d4d-f9619516e9bd.png)
python tools/train.py configs/elephant/cityperson/cascade_hrnet.py
. Everything works.I really have no clue why this happens. Any help is appreciated.
Reproduction
demo command:
A placeholder for the command.
Pedestron/tools/../mmdet/apis/inference.py:39: UserWarning: Class names are not saved in the checkpoint's meta data, use COCO classes by default. warnings.warn('Class names are not saved in the checkpoint\'s '