Repository files navigation

English |中文

⭐Please give a star if this project helps you.⭐

The main features of this library are:

• High level API (just a line to create a neural network)
• 7 models architectures for binary and multi class segmentation (including legendary Unet)
• 15 available encoders
• All encoders have pre-trained weights for faster and better convergence
• 35% or more inference speed boost compared with pytorch cuda, same speed for cpu. (Unet tested in rtx 2070s).

VisitLibtorch Tutorials Project if you want to know more about Libtorch Segment library.

1. Quick start
2. Examples
3. Train your own data
4. Models
   1. Architectures
   2. Encoders
5. Installation
6. Thanks
7. To do list
8. Citing
9. License
10. Related repository

A resnet34 trochscript file is providedhere. Segmentation model is just a LibTorch torch::nn::Module, which can be created as easy as:

#include"Segmentor.h"auto model = UNet(1,/*num of classes*/"resnet34",/*encoder name, could be resnet50 or others*/"path to resnet34.pt"/*weight path pretrained on ImageNet, it is produced by torchscript*/                  );

• seetable with available model architectures
• seetable 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 your better results (higher metric score and faster convergence). And you can also train only the decoder and segmentation head while freeze the backbone.

importtorchfromtorchvisionimportmodels# resnet34 for examplemodel=models.resnet34(pretrained=True)model.eval()var=torch.ones((1,3,224,224))traced_script_module=torch.jit.trace(model,var)traced_script_module.save("resnet34.pt")

Congratulations! You are done! Now you can train your model with your favorite backbone and segmentation framework.

• Training model for person segmentation using images from PASCAL VOC Dataset. "voc_person_seg" dir contains 32 json labels and their corresponding jpeg images for training and 8 json labels with corresponding images for validation.

Segmentor<FPN> segmentor;segmentor.Initialize(0/*gpu id, -1 for cpu*/,512/*resize width*/,512/*resize height*/,                    {"background","person"}/*class name dict, background included*/,"resnet34"/*backbone name*/,"your path to resnet34.pt");segmentor.Train(0.0003/*initial leaning rate*/,300/*training epochs*/,4/*batch size*/,"your path to voc_person_seg",".jpg"/*image type*/,"your path to save segmentor.pt");

• Predicting test. A segmentor.pt file is provided in the projecthere. It is trained through a FPN with ResNet34 backbone for a few epochs. You can directly test the segmentation result through:

cv::Mat image = cv::imread("your path to voc_person_seg\\val\\2007_004000.jpg");Segmentor<FPN> segmentor;segmentor.Initialize(0,512,512,{"background","person"},"resnet34","your path to resnet34.pt");segmentor.LoadWeight("segmentor.pt"/*the saved .pt path*/);segmentor.Predict(image,"person"/*class name for showing*/);

the predicted result shows as follow:

• Create your own dataset. Usinglabelme through "pip install" and label your images. Split the output json files and images into folders just like below:

Dataset├── train│   ├── xxx.json│   ├── xxx.jpg│   └......├── val│   ├── xxxx.json│   ├── xxxx.jpg│   └......

• Training or testing. Just like the example of "voc_person_seg", replace "voc_person_seg" with your own dataset path.
• Refer totraining tricks to improve your final training performance.

• Unet [paper]
• FPN [paper]
• PAN [paper]
• PSPNet [paper]
• LinkNet [paper]
• DeepLabV3 [paper]
• DeepLabV3+ [paper]

• ResNet
• ResNext
• VGG

The following is a list of supported encoders in the Libtorch Segment. All the encoders weights can be generated through torchvision except resnest. Select the appropriate family of encoders and click to expand the table and select a specific encoder and its pre-trained weights.

Dependency:

• Opencv 3+
• Libtorch 1.7+

Windows:

Configure the environment for libtorch development.Visual studio andQt Creator are verified for libtorch1.7x release.

Linux && MacOS:

Install libtorch and opencv.

For libtorch, follow the official pytorch c++ tutorialshere.

For opencv, follow the official opencv install stepshere.

If you have already configured them both, congratulations!!! Download the pretrained weighthere and a demo .pt filehere into weights.

Building shared or static library -DBUILD_SHARED=<TRUE/FALSE>:

export Torch_DIR='/path/to/libtorch'cd buildcmake -DBUILD_SHARED=TRUE ..makesudo make install

Building tests:

cdtestmkdir build&&cd buildcmake ..make./resnet34 ../../voc_person_seg/val/2007_003747.jpg ../../weights/resnet34.pt ../../weights/segmentor.pt

• More segmentation architectures and backbones
  • UNet++ [paper]
  • ResNest
  • Se-Net
  • ...
• Data augmentations
  • Random horizontal flip
  • Random vertical flip
  • Random scale rotation
  • ...
• Training tricks
  • Combined dice and cross entropy loss
  • Freeze backbone
  • Multi step learning rate schedule
  • ...

By now, these projects helps a lot.

• official pytorch
• qubvel SMP
• wkentaro labelme
• nlohmann json

@misc{Chunyu:2021,  Author = {Chunyu Dong},  Title = {Libtorch Segment},  Year = {2021},  Publisher = {GitHub},  Journal = {GitHub repository},  Howpublished = {\url{https://github.com/AllentDan/SegmentationCpp}}}

Project is distributed underMIT License.

Based on libtorch, I released following repositories:

• LibtorchTutorials
• LibtorchSegmentation
• LibtorchDetection

Last but not least,don't forget your star...

Feel free to commit issues or pull requests, contributors wanted.