Skip to content
forked from psycharo-zz/cpm

Convolutional Pose Machines in TensorFlow

Notifications You must be signed in to change notification settings

harrisonford/cpm

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

cpm - harrisonford's fork

Forked from this project called cpm which comes as a well greeted attempt to use Tensorflow in this convolutional pose model made originally in Caffe (yuck).

In my fork I contribute with some healthy practices, such as adding a requirements file in case you want to run the jupyter notebook on Binder or make a virtual environment easily using pip.

Getting Started

As promised, you can run this on binder. TODO: NOT YET! Sorry.

Binder

For the code to run we need to download the pre-trained structures, which are not inside this code because they tend to weight a ton. You can have them stored on your PC or also have them in a cloud somewhere. TODO: Where will I save the models? psycharo made them available through his drive here.

Installing

It's highly advised to make your own virtual environment with pip, you can follow the steps listed in their docs here.

Contributing

I'm alone and single for now.

Authors

License

Original work has the following license: "ACADEMIC OR NON-PROFIT ORGANIZATION NONCOMMERCIAL RESEARCH USE ONLY".

So we'll agree to that (see their license).

Acknowledgments - Tips fedora

About

Convolutional Pose Machines in TensorFlow

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 93.1%
  • Python 6.9%