This repository includes the official project of TransUNet, presented in our paper: TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation.
Beckschen/TransUNet is ranked 8,039 with 3,246 stars.
Same-category comparison
Beckschen/TransUNet is ranked 8,039 among these 8 peers; cocktailpeanut/fluxgym is ranked 8,035.
Same-category comparison| Name | Rank | Metrics |
|---|
| facebookresearch/vissl | 8,018 | - Language:
- Jupyter Notebook
- Stars:
- 3,290
- Forks:
- 323
- Description:
- VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
|
|---|
| facebookresearch/MUSE | 8,027 | - Language:
- Python
- Stars:
- 3,266
- Forks:
- 569
- Description:
- A library for Multilingual Unsupervised or Supervised word Embeddings.
|
|---|
| MAIF/shapash | 8,031 | - Language:
- Jupyter Notebook
- Stars:
- 3,264
- Forks:
- 389
- Description:
- 🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models.
|
|---|
| cocktailpeanut/fluxgym | 8,035 | - Language:
- Python
- Stars:
- 3,257
- Forks:
- 369
- Description:
- Dead simple FLUX LoRA training UI with LOW VRAM support.
|
|---|
| Jittor/jittor | 8,046 | - Language:
- Python
- Stars:
- 3,237
- Forks:
- 328
- Description:
- Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
|
|---|
| kerlomz/captcha_trainer | 8,054 | - Language:
- Python
- Stars:
- 3,215
- Forks:
- 821
- Description:
- This project is only for training the model.
|
|---|
| JoePenna/Dreambooth-Stable-Diffusion | 8,058 | - Language:
- Jupyter Notebook
- Stars:
- 3,212
- Forks:
- 524
- Description:
- Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) by way of Textual Inversion (https://arxiv.org/abs/2208.01618) for Stable Diffusion (https://arxiv.org/abs/2112.10752). Tweaks focused on training faces, objects, and styles.
|
|---|
| webdataset/webdataset | 8,059 | - Language:
- Python
- Stars:
- 3,209
- Forks:
- 234
- Description:
- A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.
|
|---|
Key parameters and specifications
Key parameters and specifications| Parameter | Value |
|---|
| Language | Python |
|---|
| Category | Model Development |
|---|
| Subcategory | Architecture, Domain-specific training |
|---|
| Keywords | Biomedical, Computer vision, Healthcare |
|---|
| Stars | 3,246 |
|---|
| Forks | 584 |
|---|
| Contributors | 4 |
|---|
| Created date | 2021-02-08 |
|---|
| Updated date | 2026-10-12 |
|---|
| Stars in 1 day | 0 |
|---|
| Stars in 7 days | 1 |
|---|
| Rank | 8,039 |
|---|
| Previous rank | 8,127 |
|---|
| Rank change | 88 |
|---|
| 7-day stars rank | 9,214 |
|---|
| Previous 7-day stars rank | 9,277 |
|---|
| 7-day stars rank change | 63 |
|---|
| Total stars rank | 4,193 |
|---|
| Previous total stars rank | 4,188 |
|---|
| Total stars rank change | -5 |
|---|
| Country | USA |
|---|
README summary
TransUNet This repo holds code for TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation 📰 News [7/26/2024] TransUNet, which supports both 2D and 3D data and incorporates a Transformer encoder and decoder, has been featured in the journal Medical Image Analysis (link). [10/15/2023] 🔥 3D version of TransUNet is out! Our 3D TransUNet surpasses nn-UNet with 88. 11% Dice score on the BTCV dataset and outperforms the top-1 solution in the BraTs 2021 challenge and
secure the second place in BraTs 2023 challenge. Please take a look at the code and paper. Download Google pre-trained ViT models Get models in this link: R50-ViT-B_16, ViT-B_16, ViT-L_16. [Update 2026/02] The official ViT weights appear to have expired. You can still download a copy from the project folder (same to BTCV preprocessed data). ) All data are available so no need to send emails for data. Please use the BTCV
preprocessed data and ACDC data. Environment Please prepare an environment with python=3. 7, and then use the command "pip install -r requirements. Train/Test Run the train script on synapse dataset. The batch size can be reduced to 12 or 6 to save memory (please also decrease the base_lr linearly), and both can reach similar performance. It supports testing for both 2D images and 3D volumes. Reference Google ViT ViT-pytorch segmentation_models.
Frequently asked questions
How many stars and forks are recorded?
Beckschen/TransUNet has 3,246 stars and 584 forks.
What is the repository rank?
Beckschen/TransUNet is ranked 8,039.
What language and category are recorded?
Beckschen/TransUNet has 3,246 stars, uses Python and belongs to Model Development.
Which repository is closest in rank?
Beckschen/TransUNet is compared with cocktailpeanut/fluxgym, ranked 8,035 with 3,257 stars.
TransUNet
This repo holds code for TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
📰 News
- [7/26/2024] TransUNet, which supports both 2D and 3D data and incorporates a Transformer encoder and decoder, has been featured in the journal Medical Image Analysis (link).
@article{chen2024transunet,
title={TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers},
author={Chen, Jieneng and Mei, Jieru and Li, Xianhang and Lu, Yongyi and Yu, Qihang and Wei, Qingyue and Luo, Xiangde and Xie, Yutong and Adeli, Ehsan and Wang, Yan and others},
journal={Medical Image Analysis},
pages={103280},
year={2024},
publisher={Elsevier}
}
- [10/15/2023] 🔥 3D version of TransUNet is out! Our 3D TransUNet surpasses nn-UNet with 88.11% Dice score on the BTCV dataset and outperforms the top-1 solution in the BraTs 2021 challenge and secure the second place in BraTs 2023 challenge. Please take a look at the code and paper.
Usage
1. Download Google pre-trained ViT models
wget https://storage.googleapis.com/vit_models/imagenet21k/{MODEL_NAME}.npz &&
mkdir ../model/vit_checkpoint/imagenet21k &&
mv {MODEL_NAME}.npz ../model/vit_checkpoint/imagenet21k/{MODEL_NAME}.npz
[Update 2026/02] The official ViT weights appear to have expired.
You can still download a copy from the project folder (same to BTCV preprocessed data). After extraction, find the file at:
../model/vit_checkpoint/imagenet21k/R50+ViT-B_16.npz
2. Prepare data (All data are available!)
All data are available so no need to send emails for data. Please use the BTCV preprocessed data and ACDC data.
3. Environment
Please prepare an environment with python=3.7, and then use the command "pip install -r requirements.txt" for the dependencies.
4. Train/Test
- Run the train script on synapse dataset. The batch size can be reduced to 12 or 6 to save memory (please also decrease the base_lr linearly), and both can reach similar performance.
CUDA_VISIBLE_DEVICES=0 python train.py --dataset Synapse --vit_name R50-ViT-B_16
- Run the test script on synapse dataset. It supports testing for both 2D images and 3D volumes.
python test.py --dataset Synapse --vit_name R50-ViT-B_16
Reference
Citations
@article{chen2021transunet,
title={TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation},
author={Chen, Jieneng and Lu, Yongyi and Yu, Qihang and Luo, Xiangde and Adeli, Ehsan and Wang, Yan and Lu, Le and Yuille, Alan L., and Zhou, Yuyin},
journal={arXiv preprint arXiv:2102.04306},
year={2021}
}