Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/4383/transcendental
https://github.com/4383/transcendental
Last synced: about 2 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/4383/transcendental
- Owner: 4383
- Created: 2018-05-30T19:39:15.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2023-10-03T21:10:06.000Z (over 1 year ago)
- Last Synced: 2024-12-04T23:15:59.263Z (2 months ago)
- Language: Python
- Size: 14.7 MB
- Stars: 0
- Watchers: 3
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Transcendental (π)
Artificial Intelligence image recognition.
Learn from input data and generate model, predict from previous generated model
## Disclaimer
This is testing project purpose so it's currently in development and features
are minimal don't juge me :)
## Features
- Recognize cats
- Recognize dogs
## Install
```shell
$ pip install transcendental
```
## Usage
### trans-predict
This command allow you to recognize an image passed in argument.
Predict take exactly one argument who is the image to predict
```shell
$ trans-predict --help
usage: trans-predict [-h] image
Recognize cat and dogs
positional arguments:
image an image to analyze
optional arguments:
-h, --help show this help message and exit
$ trans-predict ./image.png
```
### trans-train
This command allow you to train your IA.
This command generate models automaticaly used by predict at launch
Currently in development!
### Requires
- python 2.7+
- keras
- tensorflow
- Pillow
- h5py
## Resources
- https://becominghuman.ai/building-an-image-classifier-using-deep-learning-in-python-totally-from-a-beginners-perspective-be8dbaf22dd8
- https://drive.google.com/drive/folders/1XaFM8BJFligrqeQdE-_5Id0V_SubJAZe
- https://machinelearningmastery.com/save-load-keras-deep-learning-models/
- https://www.quora.com/How-do-artificial-neural-networks-work
- http://torch.ch/blog/2015/11/13/gan.html