faster-rcnn.pytorch - A faster pytorch implementation of faster r-cnn
If you haven't already done so, Install Google Cloud SDK, which includes the gcloud command-line tool used in this quickstart.
Cloud Datalab is a powerful interactive tool created to explore, analyze, transform and visualize data and build machine learning models on Google Cloud Platform.
Recently, while I was doing my research project on Computer Vision using Convolutional Neural Network, I found out that my 8GB RAM laptop is useless. It took me an hour to learn from just 1 epoch. Therefore, rather than spending 1500$ on a new GPU based laptop, I did it for free on Google Cloud.
This post is clearly inspired by this tweet from @fchollet.
NumbaPro was one of the early tools that could compile Python for execution on NVIDIA GPUs. Our goal with NumbaPro was to make cutting-edge GPUs more accessible to Python users, and to improve the performance of numerical code in Python.
Pyculib is a package that provides access to several numerical libraries that are optimized for performance on NVidia GPUs.
Python is one of the most popular programming languages today for science, engineering, data analytics and deep learning applications. However, as an interpreted language, it has been considered too slow for high-performance computing. That has changed with CUDA Python from Continuum Analytics.
estool - Evolution Strategies Tool
A Python implementation of CMA-ES and a few related numerical optimization tools. The Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is a stochastic derivative-free numerical optimization algorithm for difficult (non-convex, ill-conditioned, multi-modal, rugged, noisy) optimization problems in continuous search spaces.
Apache MXNet is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator.
Prerequisites: This article assumes you are familiar with the basics of Python, TensorFlow, and Jupyter notebooks. We won't use any of the advanced TensorFlo...
We love Jupyter Notebooks, the notebook format is an effective way to construct your data narrative. But the in-browser IDE is simply feature free, and hardly provides the same incredible editing power of Atom, VS Code, Sublime or even RStudio. Because of this, the gap between data science and data engineering from a workflow perspective remains wide. Let’s shorten that gap.
Links to the best IPython and Jupyter Notebooks.
This page is a curated collection of Jupyter/IPython notebooks that are notable.
Check out this Jupyter notebook!
ray - A high-performance distributed execution engine
PixieDust now lets you turn charts into standalone web pages
golearn - Machine Learning for Go
Go is a lovely little programming language designed by smart people you can trust and continuously improved by a large and growing open-source community.
Algorithmia makes applications smarter, by building a community around algorithm development, where state of the art algorithms are always live and accessible to anyone.
New from Google. Kind of "Machine Learning for dummies".
A Data Science Framework that you can use anywhere.
The Jupyter Notebook is a web-based interactive computing platform. The notebook combines live code, equations, narrative text, visualizations, interactive dashboards and other media.
Discussion about what is a Notebook and its features. Notebooks are user development interface that are very useful for machine learning professionals.
A list of the 10 best AI and ML tools for developers.
Open source is the best choice for Machine Learning, due to its support communities and wide offer of specific libraries. And of course, they are free.