Skip to content

charlio23/DeepSkeleton-pytorch

Repository files navigation

DeepSkeleton Pytorch reimplementation

PyTorch reimplementation of Deep Skeleton: Learning Multi-task Scale-associated Deep Side Outputs (LMSDS) for object skeleton extraction in natural images using Python 3.6 and Pytorch 1.0.1

The main objective is to reproduce the algorithm as it is done in the official implementation using Pytorch.

Contents

This repository contains two executable files:

Data preprocessing and augmentation

Download SK-LARGE from the author's page and use their code to perform data augmentation.

Training

Once you have your augmented data, you can try training the algorithm.

First you need to download the VGG16 pretrained model.

mkdir model
wget https://download.pytorch.org/models/vgg16-397923af.pth
mv vgg16-397923af.pth model/vgg16.pth
python main.py

Test

Should you wish to test the algorithm:

python test_results.py

Use the skeval code to preform test.

References

About

A personal PyTorch implementation of DeepSkeleton

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages