-
你好,我对你们的工作很感兴趣!
我注意到你们在论文里引用了CVPR2023的《Weakly Supervised Video Emotion Detection and Prediction via Cross-Modal Temporal Erasing Network》(参考文献[65]),但在实际对比实验的时候没有给出它的数据进行对比。请问你们的工作和他们比起来怎么样呢?
其次,VAAN…
-
### Checklist
- [X] The issue exists after disabling all extensions
- [X] The issue exists on a clean installation of webui
- [ ] The issue is caused by an extension, but I believe it is caused b…
-
-
I am fine-tuning OneFormer on my dataset(in coco format).
I have used pre-trained weights for swin - swin_large_patch4_window12_384_22kto1k.pth, which I got from here:
https://detrex.readthedocs.…
-
I am trying to build the docs with ```doc-builder ```
using the following command
```
doc-builder build transformers docs/source/en --build_dir ~/tmp/test-build
```
but got the following er…
ENate updated
6 months ago
-
我读了一下你的代码,试图理解一下论文的核心 axis attention机制
你将swin-tiny 最后2个stage的特征图dump出来,拼接后进行了通道信息混叠,得到特征图a,送入了axis attention block。
然后将a按照通道切分成2部分,第一部分特征图沿宽度轴均分成几个纵向条状区域(每个宽度k=5像素),并在每个区域内部计算两两像素(token)的相关性。
第二部…
-
We used video swin transformer to generate 3D attention mask, but we extract the onnx's mask output which is not the same. Can you public the gen_mask function, thanks!
-
Nougat
https://huggingface.co/docs/transformers/v4.34.0/en/model_doc/nougat
I love nougat chocolate
-
- When I tried to use cuda to speed up training, an error occurred. Using CPU alone is too slow. How can I solve the problem。
- Environment:Windows 10
- PDF:
[Probability and Statistics (4th Editi…
-