git/gitflow/gitlib>> Awesome-Segmentations>> 返回
项目作者： kozistr

项目描述 ：
Lots of semantic image segmentation implementations in Tensorflow/Keras
高级语言： Python
项目地址: git://github.com/kozistr/Awesome-Segmentations.git
创建时间： 2018-06-22T18:19:16Z
项目社区：https://github.com/kozistr/Awesome-Segmentations
开源协议：MIT License
下载


Awesome-Segmentation

Lots of Image Semantic Segmentation Implementations in Tensorflow/Keras

Highly inspired by HERE

Currently, under-development :(

Prerequisites

  • python 3.x
  • tensorflow 1.x
  • keras 2.x
  • numpy
  • scikit-image
  • opencv-python
  • h5py
  • tqdm

Usage

Dependency Install

  1. $ sudo python3 -m pip install -r requirements.txt

Training Model

  1. (Before running train.py, MAKE SURE run after downloading DataSet & changing DataSet's directory in xxx_train.py)
  2. just after it, RUN train.py
  3. $ python3 xxx_train.py

Implementation List

  • FCNet
  • SegNet
  • U-Net
  • FusionNet
  • FC-DenseNet
  • ENet
  • LinkNet
  • RefineNet
  • PSPNet
  • Mask R-CNN
  • DecoupledNet
  • GAN-SS
  • G-FRNet

DataSets

  • MS COCO 2017 DataSet will be used!
DataSet Train Validate Test Disk
MS COCO 2017 118287 5000 40670 26.3GB

Repo Tree

  1. │
  2. ├── xxNet
  3. │    ├──gan_img (generated images)
  4. │    │     ├── train_xxx.png
  5. │    │     └── train_xxx.png
  6. │    ├── model  (model)
  7. │    │     └── model.txt (google-drive link for pre-trained model)
  8. │    ├── xxx_model.py (model)
  9. │    ├── xxx_train.py (trainer)
  10. │    ├── xxx_tb.png   (Tensor-Board result)
  11. │    └── readme.md    (results & explains)
  12. ├── metrics.py        (metrics)
  13. ├── tfutil.py         (useful TF utils)
  14. ├── image_utils.py    (image processing)
  15. └── datasets.py       (DataSet loader)

Pre-Trained Models

Here’s a google drive link. You can download pre-trained models from here !

Papers & Codes

Name Summary Paper Code
FCN Fully Convolutional Networks for Semantic Segmentation [arXiv]
SegNet A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation [arXiv]
U-Net Convolutional Networks for Biomedical Image Segmentation [arXiv]
FusionNet A deep fully residual convolutional neural network for image segmentation in connectomics [arXiv]
FC-DenseNet Fully Convolutional DenseNets for Semantic Segmentation [arXiv]
ENet A Deep Neural Network Architecture for Real-Time Semantic Segmentation [arXiv]
LinkNet Exploiting Encoder Representations for Efficient Semantic Segmentation [arXiv]
Mask R-CNN Mask R-CNN [arXiv]
PSPNet Pyramid Scene Parsing Network [arXiv]
RefineNet Multi-Path Refinement Networks for High-Resolution Semantic Segmentation [arXiv]
G-FRNet Gated Feedback Refinement Network for Dense Image Labeling [CVPR2017]
DeepLabv3+ Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation [arXiv]
DecoupledNet Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation [arXiv]
GAN-SS Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network [arXiv]

To-Do

  1. Implement FCN
  2. Implement Mask R-CNN
  3. Upload U-Net (Tuned)
  4. Upload FC-DenseNet
  5. Upload DeepLabv3+

ETC

Any suggestions and PRs and issues are WELCONE :)

Author

HyeongChan Kim / @kozistr