Kevin Lu

Adding the LPIPS metrics

6

I have add the lpips metrice by referring the https://github.com/xinntao/BasicSR/pull/367

when will the pretrain model released？

1

Excellent work! I hope can get the pretrain model and further research it. Thanks~

the input pixel range in [0,1]，but in some models which in [0,255]，so how to adjust it？ Thanks~

Is it possible the positional encoding rather than VSA works？

1

In your code file `ViTAE-VSA\Image-Classification\vitaev2_vsa\NormalCell.py` L130: `self.pos = nn.Conv2d(dim, dim, window_size//2*2+1, 1, window_size//2, groups=dim, bias=True)` your `window_size`is 7，so the `self.pos` convolution kernel is 7 too, in most Positional Encoding extractor...

这是我的菜单显示：  我看README上的菜单显示有个“设置面板”按钮，如下所示：  是需要什么额外的配置还是我的Obsidian版本的问题？

节省部署时间

The CubePlusPlus\challenge\make_preview.py make the photo a little white

9

Thanks for sharing your work~ I am the freshman and want to learn the color constancy. But now I don't know how to generate the original photo by the `gt.csv`...

[Feature] 自定义接口DeepSeek R1 模型的思考链显示异常？

11

**问题描述** 目前似乎只有硅基流动的接口支持带特定界面的思考链显示，其他接口调用不支持。 **解决思路** 接口输出大多数都兼容，请对思考链输出结果做特殊处理。 **附加上下文** 

[Feature] 标题自动生成不正确

2

**问题描述** 某些prompt会造成标题生成不正确。 **解决思路** 比如给定一个长文本，见截图，就会出现这个问题。 **附加上下文** 

使用教程提供的镜像不能正常启动容器，镜像应该是基于ARM64构建的。请问是否有提供amd64架构的docker镜像？