Awesome

Python library with Neural Networks for Image
Segmentation based on PyTorch.

<br> <br>

The main features of this library are:

• High-level API (just two lines to create a neural network)
• 11 models architectures for binary and multi class segmentation (including legendary Unet)
• 124 available encoders (and 500+ encoders from timm)
• All encoders have pre-trained weights for faster and better convergence
• Popular metrics and losses for training routines

📚 Project Documentation 📚

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

📋 Table of content

1. Quick start
2. Examples
3. Models
   1. Architectures
   2. Encoders
   3. Timm 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

⏳ 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:

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

2. Configure data preprocessing

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!

💡 Examples <a name="examples"></a>

• Training model for pets binary segmentation with Pytorch-Lightning notebook and
• Training model for cars segmentation on CamVid dataset here.
• Training SMP model with Catalyst (high-level framework for PyTorch), TTAch (TTA library for PyTorch) and Albumentations (fast image augmentation library) - here
• Training SMP model with Pytorch-Lightning framework - here (clothes binary segmentation by @ternaus).
• Export trained model to ONNX - notebook

📦 Models <a name="models"></a>

Architectures <a name="architectures"></a>

• Unet [paper] [docs]
• Unet++ [paper] [docs]
• MAnet [paper] [docs]
• Linknet [paper] [docs]
• FPN [paper] [docs]
• PSPNet [paper] [docs]
• PAN [paper] [docs]
• DeepLabV3 [paper] [docs]
• DeepLabV3+ [paper] [docs]
• UPerNet [paper] [docs]
• Segformer [paper] [docs]

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

The following is a list of supported encoders in the SMP. Select the appropriate family of encoders and click to expand the table and select a specific encoder and its pre-trained weights (encoder_name and encoder_weights parameters).

Backbone from SegFormer pretrained on Imagenet! Can be used with other decoders from package, you can combine Mix Vision Transformer with Unet, FPN and others!

Limitations:

• encoder is not supported by Linknet, Unet++
• encoder is supported by FPN only for encoder depth = 5

Apple's "sub-one-ms" Backbone pretrained on Imagenet! Can be used with all decoders.

Note: In the official github repo the s0 variant has additional num_conv_branches, leading to more params than s1.

* ssl, swsl - semi-supervised and weakly-supervised learning on ImageNet (repo).

Timm Encoders <a name="timm"></a>

docs

Pytorch Image Models (a.k.a. timm) has a lot of pretrained models and interface which allows using these models as encoders in smp, however, not all models are supported

• not all transformer models have features_only functionality implemented that is required for encoder
• some models have inappropriate strides

Total number of supported encoders: 549

• table with available encoders

🔁 Models API <a name="api"></a>

• model.encoder - pretrained backbone to extract features of different spatial resolution
• model.decoder - depends on models architecture (Unet/Linknet/PSPNet/FPN)
• model.segmentation_head - last block to produce required number of mask channels (include also optional upsampling and activation)
• model.classification_head - optional block which create classification head on top of encoder
• model.forward(x) - sequentially pass x through model`s encoder, decoder and segmentation head (and classification head if specified)

Input channels

Input channels parameter allows you to create models, which process tensors with arbitrary number of channels. If you use pretrained weights from imagenet - weights of first convolution will be reused. For 1-channel case it would be a sum of weights of first convolution layer, otherwise channels would be populated with weights like new_weight[:, i] = pretrained_weight[:, i % 3] and than scaled with new_weight * 3 / new_in_channels.

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

Auxiliary classification output

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

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)

🛠 Installation <a name="installation"></a>

PyPI version:

$ pip install segmentation-models-pytorch

Latest version from source:

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

🏆 Competitions won with the library

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

🤝 Contributing

Install SMP

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

Run tests and code checks

make fixup         # Ruff for formatting and lint checks

Update table with encoders

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

📝 Citing

@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}}
}

🛡️ License <a name="license"></a>

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.