Skip to content
This repository has been archived by the owner on Dec 2, 2022. It is now read-only.

A minimal fully connected neural network/multilayer perceptron library from scratch in C++. Inspired by Keras.

License

Notifications You must be signed in to change notification settings

avramdj/minimal-fcnn-library

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

33 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Minimal FCNN Library

A minimal fully connected neural network/multilayer perceptron library from scratch in C++. Inspired by Keras.

Example

//creating sequential fully connected model
model::Net model;

model.add_layer(in_size);
model.add_layer(16);
model.add_layer(32);
model.add_layer(32);
model.add_layer(16);
model.add_layer(out_size);

float train_rate = 0.1;
float batch_size = 32;
model.compile(train_rate, batch_size);

model.fit(*train_data_in, *train_data_out, 20);

model.evaluate(*train_data_in, *train_data_out);

About

A minimal fully connected neural network/multilayer perceptron library from scratch in C++. Inspired by Keras.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages