douyh

I can't use my GPU?

1

I run the pretrain model on tensorflow-gpu1.8.0. The system print ` Generating testing graph on 1 GPUs ...` two times. But it needs **several hours** to finish the test process....

Some problems about generate_target

2

Hello, I'm so glad to read your paper and code. But I have some problems.  \+1 in ```transform_pixel```  \-1 in ```__getitem__``` I'm a little confused. I debug the...

Some problems about concat feature

1

The author concat last 3 feature maps and then use a FC layer to get the landmarks. In your code ```model2.py```, gloabal average pooling is added to the last 3...

I know very little about tensorflow. I use this code...from the Internet... and try to load the pretrained model W30. ``` import tensorflow as tf from net.model import HRNet import...

[Feature] 多模态模型量化示例

1

### Motivation VLM量化相关的文档还不是很完善 ### Related resources 在这里有找到一些关于LLM量化的文档：https://github.com/InternLM/lmdeploy/blob/main/docs/en/quantization/w4a16.md 想请教一下如果需要量化VLM，应该怎么做，我看到支持的模型列表中有InternVL，比如这样的模型量化应该注意一些什么，是否可以补充一些示例。 非常感谢！ ### Additional context _No response_