https://github.com/jsmith/tensortools

A simple repository with my Python ML stuff
https://github.com/jsmith/tensortools

Last synced: 11 months ago
JSON representation

A simple repository with my Python ML stuff

• Host: GitHub
• URL: https://github.com/jsmith/tensortools
• Owner: jsmith
• License: mit
• Created: 2018-03-12T19:57:36.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2019-10-22T14:53:49.000Z (over 6 years ago)
• Last Synced: 2025-03-01T18:30:52.545Z (over 1 year ago)
• Language: Python
• Homepage: https://jsmith.github.io/tensortools/
• Size: 1.01 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.txt

Awesome Lists containing this project

README

          
[![Build Status](https://travis-ci.org/jsmith/tensortools.png?branch=master)](https://travis-ci.org/jsmith/tensortools)

[![Docs](https://readthedocs.org/projects/tensortools/badge/?version=latest)](https://tensortools.readthedocs.io/)

# TensorTools

A simple repository which implements common things I use in my ML projects so I don't have to repeat myself. See `examples/` for some examples which use this repository. 

Better API documentation coming ASAP!

# Installation

```bash

pip install tensortools

```

# Example

```python

import tensorflow as tf

import tensortools as tt

import numpy as np

# Generate images with random shapes for object detection

image_generator = tf.generator.Generator()

images = image_generator.generate(n_images=1, height=100, width=100, max_shapes=2)

image = images[0]

tt.image.show(image)

# Some simple ops

vector = tt.ops.flatten(image, has_batch=False)

with tf.Session() as sess:

  vector = sess.run([vector])

# Generate anchors for YOLO algorithm using KMeans

annotations = load_annotations()

anchors = tt.yolo.generate_anchors()

```