Performance is worse while training

[186big]

Thank u for your great job. I use your code and pretrained model to train a Lidar + Camera detection model in Nuscene dataset , but the more epochs I trained, the worse it got. The loss is lower But the map is lower too.

[971022jing]

Thank u for your great job. I use your code and pretrained model to train a Lidar + Camera detection model in Nuscene dataset , but the more epochs I trained, the worse it got. The loss is lower But the map is lower too. hello，have you solved the problem?

[186big]

Thank u for your great job. I use your code and pretrained model to train a Lidar + Camera detection model in Nuscene dataset , but the more epochs I trained, the worse it got. The loss is lower But the map is lower too. hello，have you solved the problem?

sorry, not yet

[Li-Whasaka]

using full dataset?

[186big]

using full dataset?

Yes

[Acc2386]

same problem, have you salved this?

[zhijian-liu]

Thank you for your interest in our project. This repository is no longer actively maintained, so we will be closing this issue. Please refer to the amazing implementation at MMDetection3D. Thank you again!