search

dyabel / detpro

Apache License 2.0
171 stars 26 forks source link

proposals/ RPn_R101_fpn_lvis_train.pkl #27

Closed hantaotao closed 2 years ago

hantaotao commented 2 years ago

Hello, thank you very much for your work!

I have a question. How can I use code to generate 'proposals/ RPn_R101_fpn_lvis_train.pkl 'if you don't give them? Or are there detailed code instructions?

Thank you so much!

dyabel commented 2 years ago

I have provided the training code of RPN in Readme, just follow the instructions of mmdetection to train RPN. Regards

ustcjinggg commented 1 year ago

Hi, I've tried the code of RPN you provided and work on building a more generalized rpn. Thanks for sharing the code and model. However, I have the following issues and would appreciate your help :

  1. I test the epoch20.pth you provide on lvis_1 dataset. I get AR@100=36.5, far from the AR given by ViLD paper, Table 1: AR@100=39.3. Why does this happen? I understand that ViLD tests on the lvis novel data and you test the whole data. Shouldn't the epoch_20.pth perform much better than the ViLD rpn?
  2. I don't get the same performance when training RPN using your code. I use the config rpn_r101_fpn_1x_lvis.py (training 12 epoch, no 20epoch config is provided) and only get AR@100=9.5. I follow the mmdet instructions and simply use bash tools/dist_tran.sh configs/rpn/rpn_r101_fpn_1x_lvis.py 2 to train the RPN, why do I get such low performance?
  3. I can only test the RPN model using proposal_fast mode. When I use bash tools/dist_test.sh configs/rpn/rpn_r101_fpn_1x_lvis.py models/epoch_20.pth 1 --out work_dirs/result.pkl --eval proposal , I get all zero results. image