Vision Transformer Implementations Transformer Models

Reference implementations and educational repositories of Vision Transformer architectures across frameworks (TensorFlow, PyTorch, Keras). Includes core ViT models and variants for standard vision tasks. Does NOT include specialized vision-language models, 3D vision, medical imaging, or hybrid architectures that significantly depart from standard ViT design.

There are 44 vision transformer implementations models tracked. 2 score above 50 (established tier). The highest-rated is Kohulan/DECIMER-Image_Transformer at 55/100 with 345 stars.

Get all 44 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=transformers&subcategory=vision-transformer-implementations&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Model	Score	Tier	Stars	Language
1	Kohulan/DECIMER-Image_Transformer DECIMER Image Transformer is a deep-learning-based tool designed for...	55	Established	345	Python
2	sovit-123/vision_transformers Vision Transformers for image classification, image segmentation, and object...	53	Established	65	Python
3	fcakyon/video-transformers Easiest way of fine-tuning HuggingFace video classification models	48	Emerging	148	Python
4	leaderj1001/BottleneckTransformers Bottleneck Transformers for Visual Recognition	47	Emerging	279	Python
5	qubvel/transformers-notebooks Inference and fine-tuning examples for vision models from 🤗 Transformers	46	Emerging	165	Jupyter Notebook
6	rishikksh20/convolution-vision-transformers PyTorch Implementation of CvT: Introducing Convolutions to Vision Transformers	45	Emerging	226	Python
7	alohays/awesome-visual-representation-learning-with-transformers Awesome Transformers (self-attention) in Computer Vision	44	Emerging	269	—
8	xmindflow/Awesome-Transformer-in-Medical-Imaging [MedIA Journal] An ultimately comprehensive paper list of Vision...	42	Emerging	218	—
9	mmaaz60/EdgeNeXt [CADL'22, ECCVW] Official repository of paper titled "EdgeNeXt: Efficiently...	42	Emerging	411	Python
10	sayakpaul/robustness-vit Contains code for the paper "Vision Transformers are Robust Learners" (AAAI 2022).	42	Emerging	122	Jupyter Notebook
11	adaptivetokensampling/ATS Adaptive Token Sampling for Efficient Vision Transformers (ECCV 2022 Oral...	41	Emerging	104	Shell
12	cmhungsteve/Awesome-Transformer-Attention An ultimately comprehensive paper list of Vision Transformer/Attention,...	38	Emerging	5,022	—
13	RLado/STB-VMM STB-VMM: Swin Transformer Based Video Motion Magnification (official repository)	37	Emerging	50	Python
14	ziplab/HVT [ICCV 2021] Official implementation of "Scalable Vision Transformers with...	36	Emerging	33	Python
15	GiannakopoulosIlias/vision-transformer-network-for-mr-electrical-properties-tomography A 3D Vision Transformer-based neural network for reconstructing electrical...	36	Emerging	9	Python
16	varchasvee108/vision-transformer-maze-agent Vision Transformer agent that learns to navigate mazes while visualizing...	31	Emerging	3	Python
17	rajatsaini0294/awesome-image-transformer List of all the papers on Transformers for Vision.	29	Experimental	7	—
18	sayakpaul/vision-transformers-tf A non-exhaustive collection of vision transformer models implemented in TensorFlow.	28	Experimental	10	—
19	EMalagoli92/CvT-TensorFlow TensorFlow 2.X reimplementation of CvT: Introducing Convolutions to Vision...	28	Experimental	3	Python
20	MingSun-Tse/Awesome-Efficient-ViT Recent Advances on Efficient Vision Transformers	24	Experimental	55	—
21	danilodjor/image-retrieval-using-transformers This repository contains code used to perform image retrieval using...	23	Experimental	3	Python
22	chagmgang/dinov2-remote-sensing Implementation dino v2 for remote sensing with huggingface transformers	23	Experimental	36	Jupyter Notebook
23	vitality-vis/vitality-vis.github.io Promoting Serendipitous Discovery of Academic Literature with Transformers &...	23	Experimental	1	JavaScript
24	uakarsh/TiLT-Implementation Implementation of the paper: Going Full-TILT Boogie on Document...	22	Experimental	18	Jupyter Notebook
25	revanurambareesh/instantaneous_transformer Official repo of Instantaneous Transformers for Video based Physiology...	22	Experimental	22	Python
26	Kotomiya07/kuzushiji-vision くずし字認識システム	21	Experimental	—	Python
27	jmanuelc87/vision-transformer Implementation of different vision transformer models for classification,...	21	Experimental	—	Python
28	tim-roderick/VST Video Summarization Transformer: Implementation in PyTorch of the...	21	Experimental	10	Jupyter Notebook
29	matin-ghorbani/Video-Classification-Transformers Implement a video classification using transformers	20	Experimental	8	Jupyter Notebook
30	ahmedgh970/convnext-charm Official Tensorflow implementation of ConvNeXt-ChARM: ConvNeXt-based...	20	Experimental	5	Python
31	koc-lab/vispool Enhancing Transformer Encoders with Vector Visibility Graph Neural Networks...	19	Experimental	3	Python
32	mbari-org/vitstrain Fine-tune vision transformer models to classify Plankton, UAV(drone),...	18	Experimental	5	Python
33	Justin900429/vision-transformer Implement the vision transformer using pytorch	17	Experimental	1	Python
34	nakshatrasinghh/Vision-Transformer Tensorflow implementation of the Vision Transformer (Bye-Bye Convolutions)	17	Experimental	1	Python
35	nachiket273/VisTrans Implementations of transformers based models for different vision tasks	17	Experimental	1	Python
36	curiousbrutus/fNIRS-Vise NIRS-VIS is a Master Thesis Project for decoding visual stimuli from fNIRS...	13	Experimental	4	Jupyter Notebook
37	GuillaumeZahnd/vision-transformer Vision Transformer	13	Experimental	—	Python
38	4rtux/3D-CNN-Action-Recognition-Model Identificación de actividades cotidianas basado en visión por computador y...	13	Experimental	—	Python
39	CodeBy-HP/vit-pose-classifier-aws-fargate-deploy AI-powered human pose classification API—serverless, scalable, and blazing...	12	Experimental	1	Jupyter Notebook
40	DaniGarciaPerez/vision_transformer A repo to explore the implementation of a Vision Transformer from scratch...	11	Experimental	—	Python
41	Ruhaan838/Vision-Transformer Implementation of Vision Transformer Using PyTorch ...	11	Experimental	—	Python
42	inuwamobarak/swin-transformers Swin Transformers, short for "Shifted Windows," were introduced in the paper...	11	Experimental	3	Jupyter Notebook
43	HilaManor/CycleTransformer Final assignment in the NLP course at the Technion (IEM097215). In this...	10	Experimental	2	Python
44	Bessouat40/vit-transformers-finetuning vision-transformers-finetunning	10	Experimental	2	Python

Comparisons in this category

awesome-visual-representation-learning-with-transformers and Awesome-Transformer-Attention (44 vs 38) Awesome-Transformer-in-Medical-Imaging and Awesome-Transformer-Attention (42 vs 38) vision_transformers and awesome-visual-representation-learning-with-transformers (53 vs 44) vision_transformers and convolution-vision-transformers (53 vs 45) convolution-vision-transformers and CvT-TensorFlow (45 vs 28) vision_transformers and vision-transformers-tf (53 vs 28) vision_transformers and awesome-image-transformer (53 vs 29)