Feng Liu

The results of my rerunned 'save.pth' is also different with the results in PoinetNetClass.ipyb.

Hi, @jihanyang Thank you for your interesting work. Can you release the code for vanilla Office-Home? Thanks!

I also encountered similar error. `Traceback (most recent call last): File "train_partseg.py", line 262, in train(model, args) File "train_partseg.py", line 148, in train train_acc = metrics.accuracy_score(train_true_cls, train_pred_cls) File "/userhome/evns/jittor/lib/python3.7/site-packages/sklearn/utils/validation.py", line...

Hi，@kkkcx，thank you for your interest in our work. We don't have the plan to release the config and weights of R101 for the time being. It may be realeased after...

你好，用的卡是3090，训练时长我现在已经看不了了，应该不会太多，论文中有streampetr的相关实验，resnet 50，256*704分辨率，24 epoch，训练时长从7h增加到7.5h

Hi, thank you for your interest in our work. RayDN takes several frames of muliti-view(i.e., 6-view) images as input. Besides, it also requires the transformation matirx of the camera. You...

I haven't tried it. You may refer to [link](https://github.com/exiawsh/StreamPETR/issues/217).

Maybe you can also refer to [link](https://github.com/exiawsh/StreamPETR/issues/16).

Domain: 3D Object Detection Paper name/title: Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection Paper link: https://arxiv.org/abs/2402.03634 Code link: https://github.com/LiewFeng/RayDN

Paper title: Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model Paper link: https://arxiv.org/abs/2411.19108 Code link: https://github.com/ali-vilab/TeaCache Project: https://liewfeng.github.io/TeaCache/ Topic: Visual Generation Acceleration