YutingXiao

"indices = torch.topk(- distances, k)[1]" aims to find the top k nearest category-specific features in the codebook. It seems that the dimension of the codebook is not correct? I suggest...

Thanks for your interest. After your training, the trained model will be tested automatically. You can also use "python tools/train_net.py --config-file configs/{your_yaml_file} --eval-only MODEL.WEIGHTS {your_OUTPUT_DIR}/model_final.pth" to make inference.

The author of COCOA dataset ((Patrick Follmann ***@***.***)) gave me this link, and it seems unavailable now. I think you should connect to the author of COCOA dataset, I am...

The email is [email protected] This COCOA cls dataset comes from this paper: https://arxiv.org/pdf/1804.08864.pdf

Thanks for your interest. You can download the weight file at here: https://github.com/Kevin-KangZhou/P_Net_Anomaly_Detection/tree/master/str_models 发件人: kanwangshijie 发送时间: 2021年10月22日 10:27 收件人: YutingXiao/P-Net_Mvtec_AD 抄送: Subscribed 主题: [YutingXiao/P-Net_Mvtec_AD] P-Net weights and data set (Issue...

Isee dataset is not the public dataset. If you want to use it, you should connect to Professor Jiang Liu. He is the co-author of our paper. 发件人: kanwangshijie 发送时间:...

Hi, this is the supplementary. [AAAI_supplementary_2021.pdf](https://github.com/YutingXiao/Amodal-Segmentation-Based-on-Visible-Region-Segmentation-and-Shape-Prior/files/6758477/AAAI_supplementary_2021.pdf)

The classes "rider" has 0 instance

Thanks for your help!! My email: [email protected]