Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
| Date | Stars |
|---|---|
| 2026-07-24 | 11666 |
| 2026-07-25 | 11667 |
| 2026-07-28 | 11668 |
| 2026-07-30 | 11668 |
| 2026-08-06 | 11668 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
**Python library with Neural Networks for Image Semantic
Segmentation based on [PyTorch](https://pytorch.org/).**
[](https://github.com/qubvel/segmentation_models.pytorch/actions/workflows/tests.yml)
[](https://smp.readthedocs.io/en/latest/)
<br>
[](https://pypi.org/project/segmentation-models-pytorch/)
[](https://pepy.tech/project/segmentation-models-pytorch)
[](https://pepy.tech/project/segmentation-models-pytorch)
<br>
[](https://github.com/qubvel/segmentation_models.pytorch/blob/main/LICENSE)
[](https://pepy.tech/project/segmentation-models-pytorch)
</div>
The main features of the library are:
- Super simple high-level API (just two lines to create a neural network)
- 12 encoder-decoder model architectures (Unet, Unet++, Segformer, DPT, ...)
- 800+ **pretrained** convolution- and transform-based encoders, including [timm](https://github.com/huggingface/pytorch-image-models) support
- Popular metrics and losses for training routines (Dice, Jaccard, Tversky, ...)
- ONNX export and torch script/trace/compile friendly
### 🤝 Sponsor: withoutBG
<a href="https://github.com/withoutbg/withoutbg" target="_blank">
<img src="https://withoutbg.com/images/img-and-matte.png" alt="Sponsored by withoutBG"/>
</a>
[withoutBG](https://github.com/withoutbg/withoutbg) is a high-quality background removal tool. They built their open-source image matting and refiner models using `smp.Unet` and are proudly sponsoring this project.
### [📚 Project Documentation 📚](http://smp.readthedocs.io/)
Visit [Read The Docs Project Page](https://smp.readthedocs.io/) or read the following README to know more about Segmentation Models Pytorch (SMP for short) library
### 📋 Table of content
1. [Quick start](#start)
2. [Examples](#examples)
3. [Models and encoders](#models-and-encoders)
4. [Models API](#api)
1. [Input channels](#input-channels)
2. [Auxiliary classification output](#auxiliary-classification-output)
3. [Depth](#depth)
5. [Installation](#installation)
6. [Competitions won with the library](#competitions)
7. [Contributing](#contributing)
8. [Citing](#citing)
9. [License](#license)
## ⏳ Quick start <a name="start"></a>
#### 1. Create your first Segmentation model with SMP
The segmentation model is just a PyTorch `torch.nn.Module`, which can be created as easy as:
```python
import segmentation_models_pytorch as smp
model = smp.Unet(
encoder_name="resnet34", # choose encoder, e.g. mobilenet_v2 or efficientnet-b7
encoder_weights="imagenet", # use `imagenet` pre-trained weights for encoder initialization
in_channels=1, # model input channels (1 for gray-scale images, 3 for RGB, etc.)
classes=3, # model output channels (number of classes in your dataset)
)
```
- see [table](#architectures) with available model architectures
- see [table](#encoders) with available encoders and their corresponding weights
#### 2. Configure data prepExcerpt of 15,170 characters
Read on GitHub
Adam J. Stewart · Technical University of Munich · Germany
261
243
Pavel Iakubovskii · AI Engineer @ Praktika.ai | ex HuggingFace 🤗
197
Ryan · Taiwan
10
Siarhei Fedartsou · Poland
4
4
4
3
3
2
Alexander
2
2
2
João G. Atkinson A.
2
Michael Monashev
2
2
2
2
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ff2206dcaff054da, topic:computer-vision, topic:image-segmentation, desc:semantic segmentation