Cottonwood 神经网络框架(教学用)

Cottonwood 神经网络框架(教学用)

WE'VE MOVED

This repository is now being hosted on GitLab's servers.

Check it out at https://gitlab.com/brohrer/cottonwood. Install from there. Update from there.

To make the switch on your local machine command line run

git remote set-url origin https://gitlab.com/brohrer/cottonwood.git

or

git remote set-url origin git@gitlab.com:brohrer/cottonwood.git

depending on which protocol you're using.

This repo is being deprecated and will no longer be updated. BTW GitLab is pretty intuitive if you're already familiar with GitHub. Check it out.

--

--

--

--

The Cottonwood Machine Learning Framework

Cottonwood is built to be as flexible as possible, top to bottom. It's designed to minimize the iteration time when running experiments and testing ideas. It's meant to be tweaked. Fork it. Add to it. Customize it to solve the problem at hand. For more of the thought behind it, read the post " Why another framework? and Why did you name it that?

This code is always evolving. I recommend referencing a specific tag whenever you use it in a project. Tags are labeled v1, v2, etc. and the code attached to each one won't change.

If you want to follow along with the construction process for Cottonwood, you can get a step-by-step walkthrough in the e2eML sequence Course 312, Course 313, and Course 314.

Installation

Whether you want to pull Cottonwood into another project, or experiment with ideas of your own, you'll want to clone the repository to your local machine and install it from there.

git clone https://github.com/brohrer/cottonwood.gitpython3 -m pip install -e cottonwood

Try it out

python3

>>> import cottonwood.demo

Here is the cheatsheet for pulling the relevant components into your work.

Versioning

Cottonwood versions are not guaranteed backward compatible. You can select a particular version to work from.

cd cottonwoodgit checkout v14

Examples

See what Cottonwood looks like in action. Feel free to use any of these as a template for a project of your own. They're MIT licensed.

Compress images of the surface of Mars

Contribute to the project

Here are some ideas to get you started.

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。