qubvel-org/segmentation_models.pytorch

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 support
• Popular metrics and losses for training routines (Dice, Jaccard, Tversky, ...)
• ONNX export and torch script/trace/compile friendly

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.

Visit Read The Docs Project Page or read the following README to know more about Segmentation Models Pytorch (SMP for short) library

1. Quick start
2. Examples
3. Models and encoders
4. Models API
   1. Input channels
   2. Auxiliary classification output
   3. Depth
5. Installation
6. Competitions won with the library
7. Contributing
8. Citing
9. License

The segmentation model is just a PyTorch torch.nn.Module, which can be created as easy as:

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 with available model architectures
• see table with available encoders and their corresponding weights

All encoders have pretrained weights. Preparing your data the same way as during weights pre-training may give you better results (higher metric score and faster convergence). It is not necessary in case you train the whole model, not only the decoder.

from segmentation_models_pytorch.encoders import get_preprocessing_fn

preprocess_input = get_preprocessing_fn('resnet18', pretrained='imagenet')

Congratulations! You are done! Now you can train your model with your favorite framework!

Name	Link	Colab
Train pets binary segmentation on OxfordPets	Notebook
Train cars binary segmentation on CamVid	Notebook
Train multiclass segmentation on CamVid	Notebook
Train clothes binary segmentation by @ternaus	Repo
Load and inference pretrained Segformer	Notebook
Load and inference pretrained DPT	Notebook
Load and inference pretrained UPerNet	Notebook
Save and load models locally / to HuggingFace Hub	Notebook
Export trained model to ONNX	Notebook

The library provides a wide range of pretrained encoders (also known as backbones) for segmentation models. Instead of using features from the final layer of a classification model, we extract intermediate features and feed them into the decoder for segmentation tasks.

All encoders come with pretrained weights, which help achieve faster and more stable convergence when training segmentation models.

Given the extensive selection of supported encoders, you can choose the best one for your specific use case, for example:

• Lightweight encoders for low-latency applications or real-time inference on edge devices (mobilenet/mobileone).
• High-capacity architectures for complex tasks involving a large number of segmented classes, providing superior accuracy (convnext/swin/mit).

By selecting the right encoder, you can balance efficiency, performance, and model complexity to suit your project needs.

All encoders and corresponding pretrained weight are listed in the documentation:

• table with natively ported encoders
• table with timm encoders supported

The input channels parameter allows you to create a model that can process a tensor with an arbitrary number of channels. If you use pretrained weights from ImageNet, the weights of the first convolution will be reused:

• For the 1-channel case, it would be a sum of the weights of the first convolution layer.
• Otherwise, channels would be populated with weights like new_weight[:, i] = pretrained_weight[:, i % 3], and then scaled with new_weight * 3 / new_in_channels.

model = smp.FPN('resnet34', in_channels=1)
mask = model(torch.ones([1, 1, 64, 64]))

All models support aux_params parameters, which is default set to None. If aux_params = None then classification auxiliary output is not created, else model produce not only mask, but also label output with shape NC. Classification head consists of GlobalPooling->Dropout(optional)->Linear->Activation(optional) layers, which can be configured by aux_params as follows:

aux_params=dict(
    pooling='avg',             # one of 'avg', 'max'
    dropout=0.5,               # dropout ratio, default is None
    activation='sigmoid',      # activation function, default is None
    classes=4,                 # define number of output labels
)
model = smp.Unet('resnet34', classes=4, aux_params=aux_params)
mask, label = model(x)

Depth parameter specify a number of downsampling operations in encoder, so you can make your model lighter if specify smaller depth.

model = smp.Unet('resnet34', encoder_depth=4)

PyPI version:

$ pip install segmentation-models-pytorch

The latest version from GitHub:

$ pip install git+https://github.com/qubvel/segmentation_models.pytorch

Segmentation Models package is widely used in image segmentation competitions. Here you can find competitions, names of the winners and links to their solutions.

• withoutBG: An open-source background removal tool that uses smp.Unet for its image matting and refinement models. Check withoutBG Focus on HuggingFace.

1. Install SMP in dev mode

make install_dev  # Create .venv, install SMP in dev mode

1. Run tests and code checks

make test          # Run tests suite with pytest
make fixup         # Ruff for formatting and lint checks

1. Update a table (in case you added an encoder)

make table        # Generates a table with encoders and print to stdout

@misc{Iakubovskii:2019,
  Author = {Pavel Iakubovskii},
  Title = {Segmentation Models Pytorch},
  Year = {2019},
  Publisher = {GitHub},
  Journal = {GitHub repository},
  Howpublished = {\url{https://github.com/qubvel/segmentation_models.pytorch}}
}

The project is primarily distributed under MIT License, while some files are subject to other licenses. Please refer to LICENSES and license statements in each file for careful check, especially for commercial use.