X-VLM: Multi-Grained Vision Language Pre-Training

Overview

X-VLM: learning multi-grained vision language alignments

Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts. Yan Zeng, Xinsong Zhang, Hang Li. arXiv 2021.

  • Jan 2022: release official PyTorch implementation and X-VLM-base checkpoints
  • Dec 2021: X-VLM-base (4M) achieves new SoTA
  • Nov 2021: release preprint in arXiv

Hiring

We are looking for interns at ByteDance AI-LAB (in Beijing / Shanghai)! If you are interested in working with us on vision language models, please send your resume to [email protected].

Features

  • Support several backbones
    • vision encoder: deit / clip-vit / swin-transformer
    • text encoder: bert / roberta
  • Support apex O1 / O2 for pre-training
  • Read from and write to HDFS
  • Distributed training across nodes for both pre-training and fine-tuning

Please read the code for more details.

Requirements

  • Install python3 environment
pip3 install -r requirements.txt
  • Download raw images from corresponding websites
  • Download the json files we provided, which contains image read paths and captions and/or bbox annotations
  • If running pre-training scripts:
  • Organize these files like this (% is for pre-training only):
X-VLM/
    data/
        finetune/
            refcoco+/*.json
            *.json
        
        %pretrain_4m/*.json
        %swin_base_patch4_window7_224_22k.pth
        %bert-base-uncased/
            config.json
            pytorch_model.bin
            tokenizer_config.json
            tokenizer.json
            vocab.txt

    images/
        coco/
            train2014/*.jpg
            val2014/*.jpg
            test2015/*.jpg
        
        visualgenome/
            image/*.jpg
        
        nlvr2/
            images/
                train/0-99/*.png
            dev/*.png
            test1/*.png
        
        %sbu/*.jpg
        %cc-3m/*.jpg

Pretrain

python3 run.py --task "pretrain_4m_base" --dist "1" --output_dir "output/pretrain_4m_base"

For distributed training across nodes, see run.py for more details.

Data

We are organizing the data and the scripts. All these will be released in Vision-Language-Data in March. Please feel free to prepare your own datasets by referring the code in dataset/pretrain_dataset.py.

Checkpoints

X-VLM-base (4M)
X-VLM-base 14M, WIP
X-VLM-large 14M, WIP

Finetune

2 nodes for fine-tuning, specify --output_hdfs to save some tmp results. # evaluate python3 run.py --task "vqa" --dist "1" --evaluate --output_dir "output/vqa_eval" --checkpoint "4m_base_finetune/vqa/model_state_epoch_9.th" ">
# train
python3 run.py --task "vqa" --dist "1" --output_dir "output/vqa" --checkpoint "4m_base_model_state_step_199999.th"
python3 run.py --task "vqa" --dist "all" --output_dir "output/vqa" --output_hdfs "hdfs://xxx/vqa_tmp" --checkpoint "4m_base_model_state_step_199999.th"  # if using >2 nodes for fine-tuning, specify --output_hdfs to save some tmp results.

# evaluate
python3 run.py --task "vqa" --dist "1" --evaluate --output_dir "output/vqa_eval" --checkpoint "4m_base_finetune/vqa/model_state_epoch_9.th" 

See run.py for fine-tuning on other tasks (Retrieval, NLVR2, RefCOCO). We set some python assertions to help you run the code correctly. The fine-tuning scripts are based on ALBEF. We thank the author for opening source their code.

Data

download json files

Checkpoints and Logs

retrieval-mscoco
retrieval-flickr
vqa
nlvr2
refcoco
refcoco-bbox
Note that fine-tuning configs are given in "X-VLM/configs/*.yaml"

Citation

If you use this code, please considering citing:

@article{xvlm,
  title={Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts},
  author={Zeng, Yan and Zhang, Xinsong and Li, Hang},
  journal={arXiv preprint arXiv:2111.08276},
  year={2021}
}

Contact

For issues or help using this code, please submit a GitHub issue.

Owner
Yan Zeng
Yan Zeng
A flexible and extensible framework for gait recognition.

A flexible and extensible framework for gait recognition. You can focus on designing your own models and comparing with state-of-the-arts easily with the help of OpenGait.

Shiqi Yu 335 Dec 22, 2022
2021 Artificial Intelligence Diabetes Datathon

A.I.D.D. 2021 2021 Artificial Intelligence Diabetes Datathon A.I.D.D. 2021은 ‘2021 인공지능 학습용 데이터 구축사업’을 통해 만들어진 학습용 데이터를 활용하여 당뇨병을 효과적으로 예측할 수 있는가에 대한 A

2 Dec 27, 2021
BASH - Biomechanical Animated Skinned Human

We developed a method animating a statistical 3D human model for biomechanical analysis to increase accessibility for non-experts, like patients, athletes, or designers.

Machine Learning and Data Analytics Lab FAU 66 Nov 19, 2022
StackRec: Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking

StackRec: Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking Datasets You can download datasets that have been pre-pr

25 May 29, 2022
SPEAR: Semi suPErvised dAta progRamming

Semi-Supervised Data Programming for Data Efficient Machine Learning SPEAR is a library for data programming with semi-supervision. The package implem

decile-team 91 Dec 06, 2022
Repository sharing code and the model for the paper "Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes"

Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes Setup virtualenv -p python3 venv source venv/bin/activate pip instal

Planet AI GmbH 9 May 20, 2022
Source codes for Improved Few-Shot Visual Classification (CVPR 2020), Enhancing Few-Shot Image Classification with Unlabelled Examples

Source codes for Improved Few-Shot Visual Classification (CVPR 2020), Enhancing Few-Shot Image Classification with Unlabelled Examples (WACV 2022) and Beyond Simple Meta-Learning: Multi-Purpose Model

PLAI Group at UBC 42 Dec 06, 2022
Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning (ICLR 2021)

Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning (ICLR 2021) Citation Please cite as: @inproceedings{liu2020understan

Sunbow Liu 22 Nov 25, 2022
Final report with code for KAIST Course KSE 801.

Orthogonal collocation is a method for the numerical solution of partial differential equations

Chuanbo HUA 4 Apr 06, 2022
CARL provides highly configurable contextual extensions to several well-known RL environments.

CARL (context adaptive RL) provides highly configurable contextual extensions to several well-known RL environments.

AutoML-Freiburg-Hannover 51 Dec 28, 2022
On Nonlinear Latent Transformations for GAN-based Image Editing - PyTorch implementation

On Nonlinear Latent Transformations for GAN-based Image Editing - PyTorch implementation On Nonlinear Latent Transformations for GAN-based Image Editi

Valentin Khrulkov 22 Oct 24, 2022
FAST-RIR: FAST NEURAL DIFFUSE ROOM IMPULSE RESPONSE GENERATOR

This is the official implementation of our neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment.

Anton Jeran Ratnarajah 89 Dec 22, 2022
On Generating Extended Summaries of Long Documents

ExtendedSumm This repository contains the implementation details and datasets used in On Generating Extended Summaries of Long Documents paper at the

Georgetown Information Retrieval Lab 76 Sep 05, 2022
Video Instance Segmentation with a Propose-Reduce Paradigm (ICCV 2021)

Propose-Reduce VIS This repo contains the official implementation for the paper: Video Instance Segmentation with a Propose-Reduce Paradigm Huaijia Li

DV Lab 39 Nov 23, 2022
A Jupyter notebook to play with NVIDIA's StyleGAN3 and OpenAI's CLIP for a text-based guided image generation.

A Jupyter notebook to play with NVIDIA's StyleGAN3 and OpenAI's CLIP for a text-based guided image generation.

Eugenio Herrera 175 Dec 29, 2022
Reproduced Code for Image Forgery Detection papers.

Image Forgery Detection With over 4.5 billion active internet users, the amount of multimedia content being shared every day has surpassed everyone’s

Umar Masud 15 Dec 06, 2022
Full Stack Deep Learning Labs

Full Stack Deep Learning Labs Welcome! Project developed during lab sessions of the Full Stack Deep Learning Bootcamp. We will build a handwriting rec

Full Stack Deep Learning 1.2k Dec 31, 2022
Tensorflow implementation of "Learning Deconvolution Network for Semantic Segmentation"

Tensorflow implementation of Learning Deconvolution Network for Semantic Segmentation. Install Instructions Works with tensorflow 1.11.0 and uses the

Fabian Bormann 224 Apr 15, 2022
Voice Conversion by CycleGAN (语音克隆/语音转换):CycleGAN-VC3

CycleGAN-VC3-PyTorch 中文说明 | English This code is a PyTorch implementation for paper: CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-spectr

Kun Ma 110 Dec 24, 2022