GitHub - qubvel/segmentation_models.pytorch: Segmentation models with pretrained...
source link: https://github.com/qubvel/segmentation_models.pytorch
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
README.md
Segmentation models
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
Quick start
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
Architectires
Encoders
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 senet154Weights
Weights name Encoder names imagenet+5k dpn68b, dpn92, dpn107 imagenet * all other encodersInstallation
PyPI version:
$ pip install segmentation-models-pytorch
Latest version from source:
$ pip install git+https://github.com/qubvel/segmentation_models.pytorch
License
Project is distributed under MIT License
Run tests
$ docker build -f docker/Dockerfile.dev -t smp:dev .
$ docker run --rm smp:dev pytest -p no:cacheprovider
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK