https://github.com/charmve/semantic-segmentation-pytorch

PyTorch implementation for Semantic Segmentation, include FCN, U-Net, SegNet, GCN, PSPNet, Deeplabv3, Deeplabv3+, Mask R-CNN, DUC, GoogleNet, and more dataset
https://github.com/charmve/semantic-segmentation-pytorch

charmve computer-vision deep-learning fcn image-classification image-processing mask-rcnn pytorch pytorch-implementation segnet semantic-segmentation unet-pytorch

Last synced: 18 days ago
JSON representation

PyTorch implementation for Semantic Segmentation, include FCN, U-Net, SegNet, GCN, PSPNet, Deeplabv3, Deeplabv3+, Mask R-CNN, DUC, GoogleNet, and more dataset

• Host: GitHub
• URL: https://github.com/charmve/semantic-segmentation-pytorch
• Owner: Charmve
• License: other
• Created: 2020-10-10T07:32:57.000Z (about 4 years ago)
• Default Branch: master
• Last Pushed: 2023-02-26T03:58:44.000Z (over 1 year ago)
• Last Synced: 2024-04-15T09:05:23.452Z (7 months ago)
• Topics: charmve, computer-vision, deep-learning, fcn, image-classification, image-processing, mask-rcnn, pytorch, pytorch-implementation, segnet, semantic-segmentation, unet-pytorch
• Language: Python
• Homepage: https://charmve.github.io/L0CV-web/
• Size: 2.71 MB
• Stars: 48
• Watchers: 3
• Forks: 10
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Semantic Segmentation in PyTorch

This repository contains some models for semantic segmentation and the pipeline of training and testing models, 

implemented in PyTorch

## Models

1. Vanilla FCN: FCN32, FCN16, FCN8, in the versions of VGG, ResNet and DenseNet respectively

([Fully convolutional networks for semantic segmentation](http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Long_Fully_Convolutional_Networks_2015_CVPR_paper.pdf))

2. U-Net ([U-net: Convolutional networks for biomedical image segmentation](https://arxiv.org/pdf/1505.04597))

3. SegNet ([Segnet: A deep convolutional encoder-decoder architecture for image segmentation](https://arxiv.org/pdf/1511.00561))

4. PSPNet ([Pyramid scene parsing network](https://arxiv.org/pdf/1612.01105))

5. GCN ([Large Kernel Matters](https://arxiv.org/pdf/1703.02719))

6. DUC, HDC ([understanding convolution for semantic segmentation](https://arxiv.org/pdf/1702.08502.pdf))

7. Mask-RCNN ([paper](https://arxiv.org/abs/1703.06870), [code from FAIR](https://github.com/facebookresearch/Detectron), [code PyTorch](https://github.com/multimodallearning/pytorch-mask-rcnn))

## Requirement

1. PyTorch 0.2.0

2. TensorBoard for PyTorch. [Here](https://github.com/lanpa/tensorboard-pytorch)  to install

3. Some other libraries (find what you miss when running the code :-P)

## Preparation

1. Go to ``*models*`` directory and set the path of pretrained models in ``*config.py*``

2. Go to ``*datasets*`` directory and do following the ``README``

## TODO

I'm going to implement The Image Segmentation Paper Top10 Net in PyTorch firstly.

- [ ] DeepLab v3  

- [ ] RefineNet 

- [ ] ImageNet

- [ ] GoogleNet

- [ ] More dataset (e.g. ADE)

## Citation

Use this bibtex to cite this repository:

```

@misc{PyTorch for Semantic Segmentation in Action,

  title={Some Implementation of Semantic Segmentation in PyTorch},

  author={Charmve},

  year={2020.10},

  publisher={Github},

  journal={GitHub repository},

  howpublished={\url{https://github.com/Charmve/Semantic-Segmentation-PyTorch}},

}

```