Skip to content

Deploy multiple neural network architectures quickly, view and record performance metrics, record trained weights for application deployment and/or to load into further training sessions later. Video demo in finance AI series on YouTube.

Notifications You must be signed in to change notification settings

flowstateeng/Neural-Network-Performance-Analyzer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MNIST Digits

CuPy GPU-Powered Neural Network Performance Analyzer

This neural network uses your GPU to train on the MNIST dataset and learn to recognize images of hand-written digits.

If you don't have a GPU or don't have CuPy installed on your system, the program will use NumPy instead. The training will run much slower, but it will achieve the same results.

Email john@discefasciendo.com with questions.

Video Demo in my AI Finance series

Enjoy!

Build Status License


Contents


Prerequisites

  • Python
  • NumPy
  • CuPy (if you want to use your GPU)
  • Requests (unless you already have the csv files: train & test)
  • Matplotlib

Installation

git clone https://github.com/chivington/Neural-Network-Performance-Analyzer.git

Usage

From the program folder, just run:

python mnist-nn.py

...and follow the prompts.

For more details, see the Video Demo

Feel free to ask me questions on GitHub or at john@discefasciendo.com

Authors

Contributing

Not currently accepting outside contributors, but feel free to use as you wish.

License

There is no license associated with this content.

About

Deploy multiple neural network architectures quickly, view and record performance metrics, record trained weights for application deployment and/or to load into further training sessions later. Video demo in finance AI series on YouTube.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages