HOU Yuenan
HOU Yuenan
We iteratively finetune the model with small learning rates. Instance augmentation is also adopted (Panoptic-PolarNet, CVPR 2021). You can have a try.
The pretrained weights can be reproduced by us on the A100 server. I have responded to most of the issues. I admit that the codes are very similar to the...
It is strange that why you are so hostile to us. The codebase is still under construction and more modules will be added. @lfl256
First, "There is no training code" is obviously a fake comment. I provide the normal training code. The distillation codes are under preparation. Second, "You paid many bot accounts to...
The distillation codes will be released soon after the DDP codes and all pre-trained models are ready.
Please refer to [this issue](https://github.com/cardwing/Codes-for-PVKD/issues/3).
The code link will be resumed soon. Please stay tuned. You can also refer to the [forked repos](https://github.com/huaduoshengkai/Codes-for-PVKD).
The code link is resumed.
@mpQuintana Do you feed the ground-truth label to the server? The predictions of our model are normal. Please refer to the following snapshot: 
@jialeli1 I wonder if you have successfully submitted the model predictions on val/test set to the online server?