Implementation of ReSeg using PyTorch
- ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation
- Pascal-Part Annotations
- Pascal VOC 2010 Dataset
Setup
- Clone this repository :
git clone --recursive https://github.com/Wizaron/reseg-pytorch.git
- Download Pascal-Part Annotations and Pascal VOC 2010 Dataset to "reseg-pytorch/data/raw" then extract tar files.
- Go to the "reseg-pytorch/code/pytorch" :
cd reseg-pytorch/code/pytorch
- Download and install Anaconda or Miniconda
- Create environment :
conda env create -f pytorch_conda_environment.yml