All Projects → ndrplz → Small_norb

ndrplz / Small_norb

Licence: mit
Python wrapper to small NORB dataset

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Small norb

Servenet
Service Classification based on Service Description
Stars: ✭ 21 (-47.5%)
Mutual labels:  classification
The Deep Learning With Keras Workshop
An Interactive Approach to Understanding Deep Learning with Keras
Stars: ✭ 34 (-15%)
Mutual labels:  classification
Yannl
Yet another neural network library
Stars: ✭ 37 (-7.5%)
Mutual labels:  classification
Cnn Question Classification Keras
Chinese Question Classifier (Keras Implementation) on BQuLD
Stars: ✭ 28 (-30%)
Mutual labels:  classification
Rnn Theano
使用Theano实现的一些RNN代码,包括最基本的RNN,LSTM,以及部分Attention模型,如论文MLSTM等
Stars: ✭ 31 (-22.5%)
Mutual labels:  classification
Constrained attention filter
(ECCV 2020) Tensorflow implementation of A Generic Visualization Approach for Convolutional Neural Networks
Stars: ✭ 36 (-10%)
Mutual labels:  classification
Text classification
all kinds of text classification models and more with deep learning
Stars: ✭ 7,179 (+17847.5%)
Mutual labels:  classification
Urban Sound Classification
Urban sound source tagging from an aggregation of four second noisy audio clips via 1D and 2D CNN (Xception)
Stars: ✭ 39 (-2.5%)
Mutual labels:  classification
Prediciting Binary Options
Predicting forex binary options using time series data and machine learning
Stars: ✭ 33 (-17.5%)
Mutual labels:  classification
Face Mask Detection
Face masks are crucial in minimizing the propagation of Covid-19, and are highly recommended or even obligatory in many situations. In this project, we develop a pipeline to detect unmasked faces in images. This can, for example, be used to alert people that do not wear a mask when entering a building.
Stars: ✭ 37 (-7.5%)
Mutual labels:  classification
Randwire tensorflow
tensorflow implementation of Exploring Randomly Wired Neural Networks for Image Recognition
Stars: ✭ 29 (-27.5%)
Mutual labels:  classification
Namescoremldemo
🏷 iOS11 demo application for predicting gender from first names.
Stars: ✭ 31 (-22.5%)
Mutual labels:  classification
Ml Classification Algorithms Poverty
A comparative assessment of machine learning classification algorithms applied to poverty prediction
Stars: ✭ 36 (-10%)
Mutual labels:  classification
Bmw Classification Inference Gpu Cpu
This is a repository for an image classification inference API using the Gluoncv framework. The inference REST API works on CPU/GPU. It's supported on Windows and Linux Operating systems. Models trained using our Gluoncv Classification training repository can be deployed in this API. Several models can be loaded and used at the same time.
Stars: ✭ 27 (-32.5%)
Mutual labels:  classification
Ml Classify Text Js
Machine learning based text classification in JavaScript using n-grams and cosine similarity
Stars: ✭ 38 (-5%)
Mutual labels:  classification
Tribuo
Tribuo - A Java machine learning library
Stars: ✭ 882 (+2105%)
Mutual labels:  classification
Satellite imagery analysis
Implementation of different techniques to find insights from the satellite data using Python.
Stars: ✭ 31 (-22.5%)
Mutual labels:  classification
Chemometricstools.jl
A collection of tools for chemometrics and machine learning written in Julia.
Stars: ✭ 39 (-2.5%)
Mutual labels:  classification
Timbl
TiMBL implements several memory-based learning algorithms.
Stars: ✭ 38 (-5%)
Mutual labels:  classification
Mlj.jl
A Julia machine learning framework
Stars: ✭ 982 (+2355%)
Mutual labels:  classification

small_norb

Plug-and-play python wrapper around the small NORB dataset.

Since I saw no plug-and-play python wrappers around the small NORB dataset (which is distributed in binary matrix file format) I made this simple class to encapsule the binary data parsing.

To install requirements: pip install -r requirements.txt

Small NORB Dataset

The small NORB dataset contains images of 50 toys belonging to 5 generic categories: four-legged animals, human figures, airplanes, trucks, and cars. The objects were imaged by two cameras under 6 lighting conditions, 9 elevations (30 to 70 degrees every 5 degrees), and 18 azimuths (0 to 340 every 20 degrees). The training set is composed of 5 instances of each category (instances 4, 6, 7, 8 and 9), and the test set of the remaining 5 instances (instances 0, 1, 2, 3, and 5). The dataset features 24300 train and 24300 test examples.

The dataset is distributed in the form of compressed binary matrices, downloadable through the following links:

Python Wrapper Usage

Once downloaded data have been uncompressed in a small_norb_root directory, usage is as simple as:

     dataset = SmallNORBDataset(dataset_root='small_norb_root')

once initialized, small NORB data will be available in dataset.data['train'] and dataset.data['test'] respectively.

Dataset Exploration

To check that the dataset has been correctly initialized, the method explore_random_examples can be used as follows:

     dataset.explore_random_examples(dataset_split='train')

If everything went well, the output should look like the following:

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].