Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Appearance settings

tkdrgithub/LeNet-in-Tensorflow

Open more actions menu
 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
10 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Implementation of the LeNet-5 deep neural network model.

LeNet-5 Architecture

Specs

Input Image is 28x28x1 and converted to 32x32x1 as per LeNet requirements.

Convolution layer 1: The output shape should be 28x28x6.

Activation 1: Your choice of activation function.

Pooling layer 1: The output shape should be 14x14x6.

Convolution layer 2: The output shape should be 10x10x16.

Activation 2: Your choice of activation function.

Pooling layer 2: The output shape should be 5x5x16.

Flatten layer: Flatten the output shape of the final pooling layer such that it's 1D instead of 3D.

Fully connected layer 1: This should have 120 outputs.

Activation 3: Your choice of activation function.

Fully connected layer 2: This should have 10 outputs.

Return the result of the 2nd fully connected layer from the LeNet function.

About

Implementation of the LeNet-5 deep neural network model in Tensorflow. https://www.youtube.com/watch?v=ixkpBmKRZDw

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%
Morty Proxy This is a proxified and sanitized view of the page, visit original site.