Skip to main content

Neural network for python

Project description

NNFPY

Welcome to a project I have been working on for a while and have decided to make this a public package

This package is used to create neural networks with 'ease'

Aim

The aim of this program is not to just make neural networks quicker to make but easier to understand, the learning gap for a lot of stuff in programming can be massive, and this package (and hopefully more) should help

We hope to do this with indepth tutorials (eventually when most of the errors are fixed) and non cryptic error messages that you spend hours seaching stackoverflow for the solution, just to find you accidently had a variable containing a string rather than a integer

Example

It compresses a whole neural network down to this:

net = onednet.create([denselayer("relu", 2, 64), denselayer("relu", 64, 2), endlayer("softmax"), timesloss(0.00001)])

data = net.runnet(0.1, 50000, X, y, storedata(), momentum=momentum(0.5), printevery=1000, batchsize=100)

outs = net.predwithout(X, y)

Just to basically describe what has happened in these lines of code:

The first line has created a network with one input layer taking two input values a hidden layer of 64 neurons and an output layer of 2 output

The second line has run the network a 50000 times

The third line shows the predictions and the average cost

Installing

To install excecute the following command

pip install nnfpy

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nnfpy-1.2.0.tar.gz (11.0 kB view details)

Uploaded Source

Built Distribution

nnfpy-1.2.0-py3-none-any.whl (12.1 kB view details)

Uploaded Python 3

File details

Details for the file nnfpy-1.2.0.tar.gz.

File metadata

  • Download URL: nnfpy-1.2.0.tar.gz
  • Upload date:
  • Size: 11.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.7.1 importlib_metadata/4.8.2 pkginfo/1.8.2 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.9

File hashes

Hashes for nnfpy-1.2.0.tar.gz
Algorithm Hash digest
SHA256 514718ad195e13f64f77c0bae3769aa8e52e320c9355294ae9360b3d513bc2e0
MD5 6e9fbf671015bab7f097564cace9cf31
BLAKE2b-256 2b0918cb8dfe778f77c13df081ff2bc4f31ab5e306c1e26ae794b523487248ea

See more details on using hashes here.

File details

Details for the file nnfpy-1.2.0-py3-none-any.whl.

File metadata

  • Download URL: nnfpy-1.2.0-py3-none-any.whl
  • Upload date:
  • Size: 12.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.7.1 importlib_metadata/4.8.2 pkginfo/1.8.2 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.9

File hashes

Hashes for nnfpy-1.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 e128d1a90fcf065c6834a828f762bb2b7e7487b473d2ca782b7b75516ecca445
MD5 c0c6d14f0ff2847264a7a11f0e910a33
BLAKE2b-256 d05325729d26b296528118b793cb3dacc9dbcc4f0d915c20eba3ea3b5b23a3b7

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page