Giter VIP home page Giter VIP logo

bt-adapter's Introduction

BT-Adapter

BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning


PWC PWC PWC PWC PWC PWC PWC PWC PWC PWC PWC PWC PWC


Paper Weights Video-text Pretraining Downstream Evaluation Instruction Tuning VideoChatGPT Evaluation
Video-text Pretraining Downstream Evaluation Instruction Tuning VideoChatGPT Evaluation

Overview and Highlights

πŸ’‘ Plug-and-use, parameter-efficient, multimodal-friendly, and temporal-sensitive structure

πŸ’‘ State-of-the-art zero-shot results on various video tasks using thousands of fewer GPU hours

πŸ’‘ State-of-the-art video conversation results with and without video instruction tuning

Qualitative Results

The Evaluation of BT-Adapter's Performance across Different Situations.

πŸ‘€ The Sequence of Actions

πŸ‘€ Unusual Actions

πŸ‘€ Complex Actions and Scenes In A Long Video

Citation

If you find the code useful for your research, please consider citing our paper:

@article{liu2023one,
  title={One for all: Video conversation is feasible without video instruction tuning},
  author={Liu, Ruyang and Li, Chen and Ge, Yixiao and Shan, Ying and Li, Thomas H and Li, Ge},
  journal={arXiv preprint arXiv:2309.15785},
  year={2023}
}

bt-adapter's People

Contributors

farewellthree avatar

Stargazers

Minglei Li avatar Zachariah Mustafa avatar  avatar BoweiPu avatar  avatar  avatar JoaquΓ­n wang avatar Coobiw avatar Jinfa Huang avatar zhouyikang avatar  avatar  avatar AreChen avatar Abdelhak Loukkal avatar Varun Ganjigunte Prakash avatar  avatar whzhong avatar  avatar Shawn J. avatar  avatar Jockey avatar Yusii avatar  avatar

Watchers

Weijian Li avatar Kostas Georgiou avatar  avatar Jun Zhang avatar  avatar

bt-adapter's Issues

Error when loadding pretrained weights

sft_mm_projector.bin is download from https://huggingface.co/farewellthree/BTAdapter-Weight.
run:
path="E:/Install/bili/sft_mm_projector.bin"
tt=torch.load(path, map_location='cpu')
then :
tt=torch.load(path, map_location='cpu')
File "C:\Users\tiang.conda\envs\test\lib\site-packages\torch\serialization.py", line 1005, in load
with _open_zipfile_reader(opened_file) as opened_zipfile:
File "C:\Users\tiang.conda\envs\test\lib\site-packages\torch\serialization.py", line 457, in init
super().init(torch._C.PyTorchFileReader(name_or_buffer))
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    πŸ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. πŸ“ŠπŸ“ˆπŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❀️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.