Qiankun Liu

@ramilmsh Hi, thanks for your work. Have you validated the converted models? And can you public your models for PyTorch 1.0+? Thanks a lot

@MatthewInkawhich Hi, have you fixed this problem?

@PK15946 Hi~, thanks for your information, but I can not open the link you provided, so did you remember how to fix this problem?

@MatthewInkawhich I figured out the reason. There is something wrong in the file `./FlowNet2_src/models/components/ops/channelnorm/functions/channelnorm.py`. Compared with the file [here](https://github.com/NVIDIA/flownet2-pytorch/blob/master/networks/channelnorm_package/channelnorm.py), we can find that the defination of backward function calls `ctx.norm_deg`,...

Hi @FengLi-ust , Thanks for your wonderful works. In the paper, Section 3.2, third paragraph, “It does not support mask refinement as the mask positional prediction from one layer cannot...

Hi @timmeinhardt , Thanks for your great works! I found that the number of classes is added by 1 during the definition of classifier. https://github.com/timmeinhardt/trackformer/blob/d62d81023dbffb4a1820db39ce527b66df6d7b61/src/trackformer/models/detr.py#L37 At the post process, the...

Hi @afiaka87, Amazing results! Can you share more details about your configurations? such as the dataset, learning rate, lr scheduler, number of text and image (8192, right?) tokens? Thanks.

It means that the code can not find any images or masks in your provided paths. The relative path is better than the abs path while using the inference script.

Hi @CyrilCsy, Thanks for your interests in our work. CNN-based encoder indeed can learn a good feature. However, the feature is not suitable for UQ-Transformer (it is good for reconstruction)....

Hi @CyrilCsy , According to my experience, P-VQVAE can achieve a promising reconstruction capability when the number of epochs are reduced. But you need to pay attention to some settings....