Pengxiang Li

A typo about function name

1

https://github.com/open-mmlab/mmdetection/blob/7646ac48f2ff6b850a3afa6234eabd25e06f7b7d/mmdet/models/dense_heads/mask2former_head.py#L172 Maybe the func name should be `_get_targets_single`?

A question about comment in `mask2former_head`

2

Hi, Maybe the `shape` here should be `(batch_size, num_queries, c)`? https://github.com/open-mmlab/mmdetection/blob/56e42e72cdf516bebb676e586f408b98f854d84c/mmdet/models/dense_heads/mask2former_head.py#L331

About YTVOS

1

Hi, vealocia, Maybe we need to do it first to run this code. `pip install git+https://github.com/youtubevos/cocoapi.git#"egg=pycocotools&subdirectory=PythonAPI` So I think you can add it to requirements.🥰

Hello, I would like to ask if I want to train my own dataset, how can I prepare the dataset for training？😉

Interacting with GPT

2

How about using GPT as a **super glue** to achieve automated data annotation and training tasks, as mentioned in the readme, "A whole pipeline to automatically label images (with bounding...

Extend MiniGPT-4 for video level

1

Hi! We have simply extended MiniGPT-4 for video level in our project [DriveScenify](https://github.com/pixeli99/DSify). DSify is a tailored version of MiniGPT-4 that focuses on understanding and generating responses based on driving...

### Discussion Hi! Thank you very much for such an interesting project. After learning the mode of using GPT4 to generate data, we use GPT4 api to do similar things...

[Feature] Stable Video Diffusion Training Code

1

Hope this can also be of help. https://github.com/pixeli99/SVD_Xtend