subhadarship / Kmeans_pytorch
Licence: mit
kmeans using PyTorch
Stars: ✭ 98
Projects that are alternatives of or similar to Kmeans pytorch
Fastpages
An easy to use blogging platform, with enhanced support for Jupyter Notebooks.
Stars: ✭ 2,888 (+2846.94%)
Mutual labels: jekyll, github-pages, jupyter-notebook
Hyperlearn
50% faster, 50% less RAM Machine Learning. Numba rewritten Sklearn. SVD, NNMF, PCA, LinearReg, RidgeReg, Randomized, Truncated SVD/PCA, CSR Matrices all 50+% faster
Stars: ✭ 1,204 (+1128.57%)
Mutual labels: jupyter-notebook, gpu
Jekyll Katex
Jekyll plugin for easy server-side math rendering via KaTeX
Stars: ✭ 73 (-25.51%)
Mutual labels: jekyll, github-pages
Jglovier.github.io
📓 Source for joelglovier.com. Built with Jekyll and hosted on GitHub Pages.
Stars: ✭ 98 (+0%)
Mutual labels: jekyll, github-pages
Jekyll Github Deploy
Jekyll Site Automated Deployer to GitHub Pages
Stars: ✭ 67 (-31.63%)
Mutual labels: jekyll, github-pages
Glove As A Tensorflow Embedding Layer
Taking a pretrained GloVe model, and using it as a TensorFlow embedding weight layer **inside the GPU**. Therefore, you only need to send the index of the words through the GPU data transfer bus, reducing data transfer overhead.
Stars: ✭ 85 (-13.27%)
Mutual labels: jupyter-notebook, gpu
Merlot
Merlot is a Jekyll theme for GitHub Pages
Stars: ✭ 52 (-46.94%)
Mutual labels: jekyll, github-pages
Deep Learning Boot Camp
A community run, 5-day PyTorch Deep Learning Bootcamp
Stars: ✭ 1,270 (+1195.92%)
Mutual labels: jupyter-notebook, gpu
Aiopen
AIOpen是一个按人工智能三要素(数据、算法、算力)进行AI开源项目分类的汇集项目,项目致力于跟踪目前人工智能(AI)的深度学习(DL)开源项目,并尽可能地罗列目前的开源项目,同时加入了一些曾经研究过的代码。通过这些开源项目,使初次接触AI的人们对人工智能(深度学习)有更清晰和更全面的了解。
Stars: ✭ 62 (-36.73%)
Mutual labels: jupyter-notebook, gpu
Dinky
Dinky is a Jekyll theme for GitHub Pages
Stars: ✭ 70 (-28.57%)
Mutual labels: jekyll, github-pages
Memory Efficient Maml
Memory efficient MAML using gradient checkpointing
Stars: ✭ 60 (-38.78%)
Mutual labels: jupyter-notebook, gpu
Covid19 Dashboard
A site that displays up to date COVID-19 stats, powered by fastpages.
Stars: ✭ 1,212 (+1136.73%)
Mutual labels: github-pages, jupyter-notebook
Neumorphism
Neumorphism designed Jekyll theme for personal websites, portfolios and resumes.
Stars: ✭ 96 (-2.04%)
Mutual labels: jekyll, github-pages
Minimal Mistakes
📐 Jekyll theme for building a personal site, blog, project documentation, or portfolio.
Stars: ✭ 8,967 (+9050%)
Mutual labels: jekyll, github-pages
Mzlogin.github.io
Jekyll Themes / GitHub Pages 博客模板 / A template repository for Jekyll based blog
Stars: ✭ 1,060 (+981.63%)
Mutual labels: jekyll, github-pages
Training Material
A collection of code examples as well as presentations for training purposes
Stars: ✭ 85 (-13.27%)
Mutual labels: jupyter-notebook, gpu
K Means using PyTorch
PyTorch implementation of kmeans for utilizing GPU
Getting Started
import torch
import numpy as np
from kmeans_pytorch import kmeans
# data
data_size, dims, num_clusters = 1000, 2, 3
x = np.random.randn(data_size, dims) / 6
x = torch.from_numpy(x)
# kmeans
cluster_ids_x, cluster_centers = kmeans(
X=x, num_clusters=num_clusters, distance='euclidean', device=torch.device('cuda:0')
)
see example.ipynb
for a more elaborate example
Requirements
- PyTorch version >= 1.0.0
- Python version >= 3.6
Installation
install with pip
:
pip install kmeans-pytorch
Installing from source
To install from source and develop locally:
git clone https://github.com/subhadarship/kmeans_pytorch
cd kmeans_pytorch
pip install --editable .
CPU vs GPU
see cpu_vs_gpu.ipynb
for a comparison between CPU and GPU
Notes
- useful when clustering large number of samples
- utilizes GPU for faster matrix computations
- support euclidean and cosine distances (for now)
Credits
- This implementation closely follows the style of this
- Documentation is done using the awesome theme jekyllbook
License
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].