GithubHelp home page GithubHelp logo

jingjing12110 / mixphm Goto Github PK

View Code? Open in Web Editor NEW
13.0 2.0 1.0 679 KB

[CVPR 2023] Pytorch Code of MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering

Home Page: https://arxiv.org/abs/2303.01239

License: MIT License

Shell 0.55% Python 99.45%

mixphm's Introduction

MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering

Overview

PyTorch implementation of MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering (CVPR 2023).


This repository is based on VL-T5, the implementation on X-VLM can be found here.

Installation

We adopt PyTorch 1.10.0 and transformers 4.15.0. See requirements.txt for other requirements.

pip install -r requirements.txt

Datasets

Please see data/README.md to prepare datasets.

├── data
│   ├── annotation
│   │   ├── answer_list.json
│   │   ├── gqa
│   │   │   ├── testdev.json
│   │   │   ├── train.json
│   │   │   ├── trainval_ans2label.json
│   │   │   ├── trainval_label2ans.json
│   │   │   └── valid.json
│   │   ├── lxmert_split
│   │   │   ├── minival.json
│   │   │   ├── nominival.json
│   │   │   ├── test.json
│   │   │   ├── train.json
│   │   │   └── val.json
│   │   ├── okvqa
│   │   │   ├── mscoco_train2014_annotations.json
│   │   │   ├── mscoco_val2014_annotations.json
│   │   │   ├── train.json
│   │   │   ├── trainval_ans2label.json
│   │   │   ├── trainval_label2ans.json
│   │   │   └── val.json
│   │   └── vqav2
│   │       ├── trainval_ans2label.json
│   │       ├── trainval_label2ans.json
│   │       ├── v2_mscoco_train2014_annotations.json
│   │       ├── v2_mscoco_val2014_annotations.json
│   │       └── val.json
│   ├── coco_imgfeat
│   │       ├── train_obj36.h5
│   │       └── val_obj36.h5
│   └── vg_imgfeat
│   │       ├── vg_gqa_obj36.h5
│   │       └── gqa_testdev_obj36.h5

Parameter-efficient tuning and evaluation

  • Experiments on OK-VQA dataset.
bash scripts/okvqa_vlt5_mixphm.sh $GPU_IDS $num_GPU
  • Experiments on VQA v2 dataset.
bash scripts/vqav2_vlt5_mixphm.sh $GPU_IDS $num_GPU
  • Experiments on GQA dataset.
bash scripts/gqa_vlt5_mixphm.sh $GPU_IDS $num_GPU

Acknowledgement

We acknowledge the use of the following public code in this project: VL-T5, Adapters, compacter, LoRA, AdaMix.

mixphm's People

Contributors

jingjing12110 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

Forkers

csguoh

mixphm's Issues

urllib3

Hello author, I would like to ask you which part of your code you are using urllib3, I am reproducing your code with urllib3.exceptions. NewConnectionError: : Failed to establish a new connection: [Errno 110] Connection timed out.

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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.