-
@xinghaochen Hi, xinghao. Thanks for sharing so nice work **TokenFusion**. However, I cannot find the code of **3D object detection** by your TokenFusion repository. I want to know whether you will re…
-
Hi! Is loss2d_class_error 100.0000 normal?
Thanks
[12/21 19:28:05] group-free INFO: Train: [2][30/95] 0head_neg_ratio 0.6538 0head_pos_ratio 0.3462 1head_neg_ratio 0.6538 1head_pos_ratio 0…
-
Hi, congratulations on your great work.
Could you elaborate more on how you preprocess the depth image in NYUv2 dataset. Did you use the raw depth image, colorization depth image or HHA encoding i…
-
As someone who studies Multimodal Fusion, I found your paper really interesting! I was also thinking about ways to improve cross attention calculation, and I was impressed by your idea of solving th…
-
Great work! Thanks for releasing the code. However, I cannot run the code successfully based on the instructions. Have you tested it by rebuilding a new conda environment?
Thanks!
-
I followed the README file to evaluate semantic segmentation, with the command below:
```bash
python3 main.py --gpu 0 --resume ./pretrained_models/model-best.pth.tar --evaluate
```
where the `mode…
-
我是一个初学者，请问这个错误的解决方案是什么。是不是因为训练的时候没有指定文件的放置路径，所以没有生成ckpt文件。我应该如何修改这个问题呢？期待您的解答，谢谢！
-
Hi, many thanks for your work. When I try to reproduce your code. In your forward there are 4 stages, in each stage, you use this code
```
x, H, W = self.patch_embed4(x)
for i, blk in enumerate(se…
-
Hi, /sunrgbd/sunrgbd_pc_bbox_votes_50k_v1_train How can I get this file
-
In
https://github.com/yikaiw/TokenFusion/blob/6fe364ee6229e2d950dcadd9c011b5a48f45c0ec/semantic_segmentation/models/mix_transformer.py#L120
and in paper, the threshold is set to 0.02, but it seems …