deeplab v3+: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Clone or download
Latest commit 9ee39f1 Dec 1, 2018
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
dataloaders DeepLab v3+ Dec 1, 2018
doc DeepLab v3+ Dec 1, 2018
networks DeepLab v3+ Dec 1, 2018
.gitignore DeepLab v3+ Dec 1, 2018
LICENSE DeepLab v3+ Dec 1, 2018
README.md DeepLab v3+ Dec 1, 2018
mypath.py DeepLab v3+ Dec 1, 2018
train.py DeepLab v3+ Dec 1, 2018
train_cityscapes.py DeepLab v3+ Dec 1, 2018

README.md

pytorch-deeplab-xception

TODO

  • Basic deeplab v3+ model, using modified xception as backbone
  • Training deeplab v3+ on Pascal VOC 2012, SBD, Cityscapes datasets
  • Results evaluation on Pascal VOC 2012 test set
  • Deeplab v3+ model using resnet as backbone

Introduction

This is a PyTorch(0.4.0) implementation of DeepLab-V3-Plus. It can use Modified Aligned Xception and ResNet as backbone. Currently, we train DeepLab V3 Plus using Pascal VOC 2012, SBD and Cityscapes datasets.

Results

Installation

The code was tested with Anaconda and Python 3.5. After installing the Anaconda environment:

  1. Clone the repo:

    git clone https://github.com/jfzhang95/pytorch-deeplab-xception.git
    cd pytorch-deeplab-xception
  2. Install dependencies:

    For PyTorch dependency, see pytorch.org for more details.

    For custom dependencies:

    pip install matplotlib pillow tensorboardX
  3. Configure your dataset path in mypath.py.

  4. You can train deeplab v3+ using xception or resnet as backbone.

    To train DeepLabV3+ on Pascal VOC 2012, please do:

    python train.py

    To train it on Cityscapes, please do:

    python train_cityscapes.py