Skip to content

Implement LeNet-5 with TensorFlow, trained and evaluated with MNIST. (MNIST data included in Repository)

Notifications You must be signed in to change notification settings

Huhaowen0130/LeNet-5-TensorFlow

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 

Repository files navigation

LeNet-5-TensorFlow

Implement LeNet-5 with TensorFlow, trained and evaluated with MNIST. (MNIST data included in Repository)

Platform

CPU: i7-8700
GPU: GTX-1660
System: Windows 10
Application: Spyder 3.3.6

How to use

Run train.py to train the LeNet with MNIST, eval.py to test.

Files

mnist: MNIST images and labels
environments.yml: my tensorflow environment for this Repository
model.py: original and modified LeNet models
func.py: functions used in train.py and eval.py

Best results in fifty epochs

training accuracy = 0.997, validation accuracy = 0.991, testing accuracy = 0.991

About

Implement LeNet-5 with TensorFlow, trained and evaluated with MNIST. (MNIST data included in Repository)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages