Skip to content

ynaka81/DeepPoseComparison

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

77 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Comparison between chainer and pytorch about implementing DeepPose

CircleCI

This repository contains codes for Qiita blog post.

Usage

Dataset preparation

First download and prepare datasets for training by running the following script.

python scripts/dataset.py

Start training

If you want to train model with Chainer, just run:

python scripts/train.py chainer

In the case of PyTorch:

python scripts/train.py pytorch

If you want to run train.py with your own settings, please check the options by python scripts/train.py --help and give customized training settings.

Visualize

Visualizing training time, just run:

python scripts/plot_training_time.py "title of graph"

Visualizing inference time, just run:

python scripts/plot_estimating_time.py 10000 "title of graph"

Install

pip install pyflakes pycodestyle
pip install sphinx
pip install -r requirements.txt

About

DeepPose with chainer and pytorch

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages