Skip to main content
Donate to the Python Software Foundation or Purchase a PyCharm License to Benefit the PSF! Donate Now

Image segmentation models with pre-trained backbones. PyTorch.

Project description

# Segmentation models
[![Build Status](]( [![Generic badge](<COLOR>.svg)](

Segmentation models is python library with Neural Networks for Image Segmentation based on PyTorch.

The main features of this library are:

- High level API (just two lines to create neural network)
- 4 models architectures for binary and multi class segmentation (including legendary Unet)
- 30 available encoders for each architecture
- All encoders have pre-trained weights for faster and better convergence

### Table of content
1. [Quick start](#start)
2. [Models](#models)
1. [Architectires](#architectires)
2. [Encoders](#encoders)
3. [Pretrained weights](#weights)
3. [Installation](#installation)
4. [License](#license)

### Quick start <a name="start"></a>
Since the library is built on the PyTorch framework, created segmentation model is just a PyTorch nn.Module, which can be created as easy as:
import segmentation_models_pytorch as smp

model = smp.Unet()
Depending on the task, you can change the network architecture by choosing backbones with fewer or more parameters and use pretrainded weights to initialize it:

model = smp.Unet('resnet34', encoder_weights='imagenet')

Change number of output classes in the model:

model = smp.Unet('resnet34', classes=3, activation='softmax')

All models have pretrained encoders, so you have to prepare your data the same way as during weights pretraining:
from segmentation_models_pytorch.encoders import get_preprocessing_fn

preprocess_input = get_preprocessing_fn('renset18', pretrained='imagenet')

**Model training example** on CamVid dataset [here](

### Models <a name="models"></a>

#### Architectires <a name="architectires"></a>
- [Unet](
- [Linknet](
- [FPN](
- [PSPNet](

#### Encoders <a name="encoders"></a>

| Type | Encoder names |
| VGG | vgg11, vgg13, vgg16, vgg19, vgg11bn, vgg13bn, vgg16bn, vgg19bn |
| DenseNet | densenet121, densenet169, densenet201, densenet161 |
| DPN | dpn68, dpn68b, dpn92, dpn98, dpn107, dpn131 |
| Inception | inceptionresnetv2 |
| ResNet | resnet18, resnet34, resnet50, resnet101, resnet152 |
| SE-ResNet | se_resnet50, se_resnet101, se_resnet152 |
| SE-ResNeXt | se_resnext50_32x4d, se_resnext101_32x4d |
| SENet | senet154 | |

#### Weights <a name="weights"></a>

| Weights name | Encoder names |
| imagenet+5k | dpn68b, dpn92, dpn107 |
| imagenet | * all other encoders |

### Installation <a name="installation"></a>
PyPI version is not released yet, to install package from source run following command:
$ pip install git+
### License <a name="license"></a>
Project is distributed under [MIT License](

### Run tests
$ docker build -f docker/ -t smp:dev .
$ docker run --rm smp:dev pytest -p no:cacheprovider

Project details

Release history Release notifications

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
segmentation_models_pytorch-0.0.1-py2.py3-none-any.whl (24.1 kB) Copy SHA256 hash SHA256 Wheel py2.py3
segmentation_models_pytorch-0.0.1.tar.gz (16.8 kB) Copy SHA256 hash SHA256 Source None

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page