Reproduction of Vision Transformer in Tensorflow2. Train from scratch and Finetune.

Related tags

Deep Learning vision-transformer-tf
Overview

Vision Transformer(ViT) in Tensorflow2

Tensorflow2 implementation of the Vision Transformer(ViT).

This repository is for An image is worth 16x16 words: Transformers for image recognition at scale and How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers.

Limitations.

  • Due to memory limitations, only the ti/16, s/16, and b/16 models were tested.
  • Due to memory limitations, batch_size 2048 in s16 and 1024 in b/16 (in paper, 4096).
  • Due to computational resource limitations, only reproduce using imagenet1k.

All experimental results and graphs are opend in Wandb.

Model weights

Since this is personal project, it is hard to train with large datasets like imagenet21k. For a pretrain model with good performance, see the official repo. But if you really need it, contact me.

Install dependencies

pip install -r requirements

All experiments were done on tpu_v3-8 with the support of TRC. But you can experiment on GPU. Check conf/config.yaml and conf/downstream.yaml

  # TPU options
  env:
    mode: tpu
    gcp_project: {your_project}
    tpu_name: node-1
    tpu_zone: europe-west4-a
    mixed_precision: True
  # GPU options
  # env:
  #   mode: gpu
  #   mixed_precision: True

Train from scratch

python run.py experiment=vit-s16-aug_light1-bs_2048-wd_0.1-do_0.1-dp_0.1-lr_1e-3 base.project_name=vit-s16-aug_light1-bs_2048-wd_0.1-do_0.1-dp_0.1-lr_1e-3 base.save_dir={your_save_dir} base.env.gcp_project={your_gcp_project} base.env.tpu_name={your_tpu_name} base.debug=False

Downstream

python run.py --config-name=downstream experiment=downstream-imagenet-ti16_384 base.pretrained={your_checkpoint} base.project_name={your_project_name} base.save_dir={your_save_dir} base.env.gcp_project={your_gcp_project} base.env.tpu_name={your_tpu_name} base.debug=False

Board

To track metics, you can use wandb or tensorboard (default: wandb). You can change in conf/callbacks/{filename.yaml}.

modules:
  - type: MonitorCallback
  - type: TerminateOnNaN
  - type: ProgbarLogger
    params:
      count_mode: steps
  - type: ModelCheckpoint
    params:
      filepath: ???
      save_weights_only: True
  - type: Wandb
    project: vit
    nested_dict: False
    hide_config: True
    params: 
      monitor: val_loss
      save_model: False
  # - type: TensorBoard
  #   params:
  #     log_dir: ???
  #     histogram_freq: 1

TFC

This open source was assisted by TPU Research Cloud (TRC) program

Thank you for providing the TPU.

Citations

@article{dosovitskiy2020image,
  title={An image is worth 16x16 words: Transformers for image recognition at scale},
  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and others},
  journal={arXiv preprint arXiv:2010.11929},
  year={2020}
}

@article{steiner2021train,
  title={How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers},
  author={Steiner, Andreas and Kolesnikov, Alexander and Zhai, Xiaohua and Wightman, Ross and Uszkoreit, Jakob and Beyer, Lucas},
  journal={arXiv preprint arXiv:2106.10270},
  year={2021}
}
You might also like...
Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm

Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetu

null 3 Dec 5, 2022
Ever felt tired after preprocessing the dataset, and not wanting to write any code further to train your model? Ever encountered a situation where you wanted to record the hyperparameters of the trained model and able to retrieve it afterward? Models Playground is here to help you do that. Models playground allows you to train your models right from the browser.
Ever felt tired after preprocessing the dataset, and not wanting to write any code further to train your model? Ever encountered a situation where you wanted to record the hyperparameters of the trained model and able to retrieve it afterward? Models Playground is here to help you do that. Models playground allows you to train your models right from the browser.

Models Playground 🗂️ Upload a Preprocessed Dataset 🌠 Choose whether to perform Classification or Regression 🦹 Enter the Dependent Variable ?

null 19 Dec 10, 2022
Minimal But Practical Image Classifier Pipline Using Pytorch, Finetune on ResNet18, Got 99% Accuracy on Own Small Datasets.

PyTorch Image Classifier Updates As for many users request, I released a new version of standared pytorch immage classification example at here: http:

JinTian 106 Nov 6, 2022
Finetune SSL models for MOS prediction

Finetune SSL models for MOS prediction This is code for our paper under review for ICASSP 2022: "Generalization Ability of MOS Prediction Networks" Er

Yamagishi and Echizen Laboratories, National Institute of Informatics 32 Nov 22, 2022
Finetune the base 64 px GLIDE-text2im model from OpenAI on your own image-text dataset

Finetune the base 64 px GLIDE-text2im model from OpenAI on your own image-text dataset

Clay Mullis 82 Oct 13, 2022
A pytorch reproduction of { Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation }.
A pytorch reproduction of { Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation }.

A PyTorch Reproduction of HCN Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation. Ch

Guyue Hu 210 Dec 31, 2022
Episodic Transformer (E.T.) is a novel attention-based architecture for vision-and-language navigation. E.T. is based on a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions.
Episodic Transformer (E.T.) is a novel attention-based architecture for vision-and-language navigation. E.T. is based on a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions.

Episodic Transformers (E.T.) Episodic Transformer for Vision-and-Language Navigation Alexander Pashevich, Cordelia Schmid, Chen Sun Episodic Transform

Alex Pashevich 62 Dec 24, 2022
Reproduction process of AlexNet

PaddlePaddle论文复现杂谈 背景 注：该repo基于PaddlePaddle，对AlexNet进行复现。时间仓促，难免有所疏漏，如果问题或者想法，欢迎随时提issue一块交流。 飞桨论文复现赛地址：https://aistudio.baidu.com/aistudio/competitio

null 19 Nov 29, 2022
Classical OCR DCNN reproduction based on PaddlePaddle framework.

Paddle-SVHN Classical OCR DCNN reproduction based on PaddlePaddle framework. This project reproduces Multi-digit Number Recognition from Street View I

null 1 Nov 12, 2021
Owner
sungjun lee
AI Researcher
sungjun lee
GitHub
Neural-net-from-scratch - A simple Neural Network from scratch in Python using the Pymathrix library

A Simple Neural Network from scratch A Simple Neural Network from scratch in Pyt

Youssef Chafiqui 2 Jan 7, 2022
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Phil Wang 12.6k Jan 9, 2023
Train a state-of-the-art yolov3 object detector from scratch!

TrainYourOwnYOLO: Building a Custom Object Detector from Scratch This repo let's you train a custom image detector using the state-of-the-art YOLOv3 c

AntonMu 616 Jan 8, 2023
Custom TensorFlow2 implementations of forward and backward computation of soft-DTW algorithm in batch mode.

Batch Soft-DTW(Dynamic Time Warping) in TensorFlow2 including forward and backward computation Custom TensorFlow2 implementations of forward and backw

null 19 Aug 30, 2022
YoloV5 implemented by TensorFlow2 , with support for training, evaluation and inference.

Efficient implementation of YOLOV5 in TensorFlow2

null 202 Jan 6, 2023
Regression Metrics Calculation Made easy for tensorflow2 and scikit-learn

Regression Metrics Installation To install the package from the PyPi repository you can execute the following command: pip install regressionmetrics I

Ashish Patel 11 Dec 16, 2022
Pointer networks Tensorflow2

Pointer networks Tensorflow2 原文：https://arxiv.org/abs/1506.03134 仅供参考与学习，内含代码备注 环境 tensorflow==2.6.0 tqdm matplotlib numpy 《pointer networks》阅读笔记 应用场景

HUANG HAO 7 Oct 27, 2022
Tf alloc - Simplication of GPU allocation for Tensorflow2

tf_alloc Simpliying GPU allocation for Tensorflow Developer: korkite (Junseo Ko)

Junseo Ko 3 Feb 10, 2022
Tensorflow2 Keras-based Semantic Segmentation Models Implementation

Tensorflow2 Keras-based Semantic Segmentation Models Implementation

Hah Min Lew 1 Feb 8, 2022
Collection of TensorFlow2 implementations of Generative Adversarial Network varieties presented in research papers.

TensorFlow2-GAN Collection of tf2.0 implementations of Generative Adversarial Network varieties presented in research papers. Model architectures will

null 41 Apr 28, 2022