Active-Learning

Active Learning Implementation in Python

Dataset

Dataset used is Natural Scenes Detection(Multi Label Image Classification) click here to download dataset. Download the dataset and extract its content. Put “miml data.mat” file and “original” folder in “miml-image-data” folder

Feature Extraction

Each image is represented by a feature vector using the method described in Learning multi-label scene classification

Description

• extract_feature.py: python script to extract features from images
• dataset_294.h5: feature extracted dataset
• model.py: Active Learning with Uncertainty Sampling Implementation

Ipython Notebook

ipython notebook