这是可以用于自动化图像分类过程的可训练工具

这是可以用于自动化图像分类过程的可训练工具。 它希望你提供一些分类的例子(它工作相当不错,只需10个例子)就可以进行培训,然后对数据进行自动分类。

Python 机器学习

访问GitHub主页

共65Star

详细介绍

Smart Categorizer

This is the trainable tool that can be used to automate the categorization process of images. It expects that you provide some categorized examples (it works pretty good given just 10 examples) on which it will be trained on and then it categorize data automatically.

screenshot

Prerequisites

Install

  1. Install tensorflow (GPU or CPU)
  2. Instal requirements: pip install -r requirements.txt

Usage example

python categorize.py --positives=/datasetsA/positives/ --target_data=/dir/containing/images --save_to=/datasets/autoA

Args:

--positives - directory containing positive images to train on

--negatives - (optional) directory containing negative images to train on

--target_data - path to directory containing uncategorized data

--save_to - path to save automatically categorized data

Negatives argument is optional because this code uses some predefined negative pool of images (stored in data folder), but if you provide negative examples the result will probably be more accurate.

推荐源码