Skip to content

A simple yet accurate Tensorflow re-implementation of paper 'Identity Mappings in Deep Residual Networks'.

Notifications You must be signed in to change notification settings

Brother-Lee/CIFAR10_ResNet56_v2

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ResNet_v2

A simple yet accurate Tensorflow re-implementation of paper 'Identity Mappings in Deep Residual Networks'.

Achieve 93.37% val accuracy in CIFAR10, which is nearly the same as He's paper.

The pre_trained model would be shared later.

The scripts' structure is simple and easy to read, especially for a tensorflow-beginner.

About

A simple yet accurate Tensorflow re-implementation of paper 'Identity Mappings in Deep Residual Networks'.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages