GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → jonasrothfuss → fishervector

jonasrothfuss / fishervector

Licence: MIT license
Improved Fisher Vector Implementation- extracts Fisher Vector features from your data

Programming Languages

python
139335 projects - #7 most used programming language

Labels

machine-learningcomputer-visiongaussian-mixture-modelsfisher-vectors

Projects that are alternatives of or similar to fishervector

Numpy Ml
Machine learning, in numpy
Stars: ✭ 11,100 (+11112.12%)
Mutual labels:  gaussian-mixture-models
Clustering-in-Python
Clustering methods in Machine Learning includes both theory and python code of each algorithm. Algorithms include K Mean, K Mode, Hierarchical, DB Scan and Gaussian Mixture Model GMM. Interview questions on clustering are also added in the end.
Stars: ✭ 27 (-72.73%)
Mutual labels:  gaussian-mixture-models
Machine-Learning-and-Pattern-Recognition
Implementation of Machine Learning Algorithms
Stars: ✭ 43 (-56.57%)
Mutual labels:  gaussian-mixture-models
tf-example-models
TensorFlow-based implementation of (Gaussian) Mixture Model and some other examples.
Stars: ✭ 42 (-57.58%)
Mutual labels:  gaussian-mixture-models
OMG Depth Fusion
Probabilistic depth fusion based on Optimal Mixture of Gaussians for depth cameras
Stars: ✭ 52 (-47.47%)
Mutual labels:  gaussian-mixture-models
deepgmr
PyTorch implementation of DeepGMR: Learning Latent Gaussian Mixture Models for Registration (ECCV 2020 spotlight)
Stars: ✭ 97 (-2.02%)
Mutual labels:  gaussian-mixture-models
PyBGMM
Bayesian inference for Gaussian mixture model with some novel algorithms
Stars: ✭ 51 (-48.48%)
Mutual labels:  gaussian-mixture-models
MachineLearning
Implementations of machine learning algorithm by Python 3
Stars: ✭ 16 (-83.84%)
Mutual labels:  gaussian-mixture-models
AI Learning Hub
AI Learning Hub for Machine Learning, Deep Learning, Computer Vision and Statistics
Stars: ✭ 53 (-46.46%)
Mutual labels:  gaussian-mixture-models
kdsb17
Gaussian Mixture Convolutional AutoEncoder applied to CT lung scans from the Kaggle Data Science Bowl 2017
Stars: ✭ 18 (-81.82%)
Mutual labels:  gaussian-mixture-models
bayseg
An unsupervised machine learning algorithm for the segmentation of spatial data sets.
Stars: ✭ 46 (-53.54%)
Mutual labels:  gaussian-mixture-models
android-vad
This VAD library can process audio in real-time utilizing GMM which helps identify presence of human speech in an audio sample that contains a mixture of speech and noise.
Stars: ✭ 64 (-35.35%)
Mutual labels:  gaussian-mixture-models
al-fk-self-supervision
Official PyTorch code for CVPR 2020 paper "Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision"
Stars: ✭ 28 (-71.72%)
Mutual labels:  fisher-vectors

Build Status

Description

The package implements Improved Fisher Vectors as described in [1]. For a more concise description of Fisher Vectors see [2]. The functionality includes:

  • Fitting a Gaussian Mixture Model (GMM)
  • Determining the number of GMM components via BIC
  • Saving and loading the fitted GMM
  • Computing the (Improved) Fisher Vectors based on the fitted GMM

Installation

For intsallation via pip run the following command on your terminal (requires python 3.4 or higher):

$ pip install fishervector

afterwards you should be able to import the package in python:

from fishervector import FisherVectorGMM

First Steps

1. Simulate some data / get your data ready

We randomly sample data just for this tutorial -> use your own data e.g. SIFT features of images

import numpy as np
shape = [300, 20, 32] # e.g. SIFT image features
image_data = np.concatenate([np.random.normal(-np.ones(30), size=shape), np.random.normal(np.ones(30), size=shape)], axis=0)
2. Train the GMM
from fishervector import FisherVectorGMM
fv_gmm = FisherVectorGMM(n_kernels=10).fit(image_data)

Or alternatively fit the GMM using the BIC to determine the number of GMM components automatically:

from fishervector import FisherVectorGMM
fv_gmm = FisherVectorGMM().fit_by_bic(test_data, choices_n_kernels=[2,5,10,20])
3. Computing improved fisher vectors
image_data_test = image_data[:20] # use a fraction of the data to compute the fisher vectors
fv = fv_gmm.predict(image_data_test)

Contributors:

References:

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].