4 Popular Machine Learning Projects on GitHub | Web Scraping Tool | ScrapeStorm

GitHub is the most active community in the field of computer science. On GitHub, people from different backgrounds share more and more software tools and resource libraries. In it, you can not only get the tools you need, but you can also watch how the code is written and implemented.

 

1. TensorFlow

 

Project address: github.com/tensorflow/t

TensorFlow is an open source software library that uses data flow graphs for numerical calculations. Among them, Tensor represents the transferred data is a tensor (multi-dimensional array), and Flow represents the use of computational graphs for operations. The data flow graph uses a directed graph composed of “node” and “edge” to describe mathematical operations. “Nodes are generally used to represent applied mathematical operations, but can also represent the starting point of data input and the end of output, or the end of reading/writing a persistent variable. Edges represent the input/ Output relationship. These data edges can transmit multi-dimensional data arrays with dynamically adjustable dimensions, that is, tensor.

TensorFlow was originally an open source software library for numerical calculations using data flow graphs, but from the current point of view, it has become a complete framework for building deep learning models. It currently mainly supports TensorFlow, but also supports languages such as C, C++, and Java.

 

2. TuriCreate

Project address: github.com/apple/turicr

TuriCreate is an open source project recently contributed by Apple. It provides easy-to-use creation and deployment methods for machine learning models, including complex tasks such as target detection, human gesture recognition, and recommendation systems.

Perhaps we, as machine learning enthusiasts, will be more familiar with GraphLab Create, a very simple and efficient machine learning library. When TuriCreate, the company that created the library, was acquired by Apple, it caused a lot of repercussions.

TuriCreate is developed for Python, and its strongest feature is to deploy machine learning models to Core ML for the development of applications such as iOS, macOS, watchOS, and tvOS.

 

3. OpenPose

 

Project address: github.com/CMU-Perceptu

OpenPose is a multi-person key point detection library, which can help us detect the location of a person in an image or video in real time. The OpenPose software library is developed and maintained by CMU’s Perceptual Computing Laboratory. It is a very good example of how open source research can be quickly applied and deployed to industry.

One use case of OpenPose is to help solve the problem of activity detection, that is, the actions or activities completed by actors can be captured in real time. Then these key points and their actions can be used to make cartoons. OpenPose not only has a C++ API to enable developers to quickly access it, but it also has a simple command line interface to process images or videos.

 

4. DeepSpeech

Project address: github.com/mozilla/Deep

DeepSpeech is an open source implementation library developed by Baidu, which provides the current state-of-the-art speech-to-text synthesis technology. It is based on TensorFlow and Python, but it can also be bound to NodeJS or run using the command line.

Mozilla has always been the main research force for building DeepSpeech and open source software libraries. Sean White, vice president of technology strategy at Mozilla, wrote in a blog post: “Currently, only a few commercial-quality speech recognition engines are open source, and most of them are dominated by large companies. This reduces the number of startups, researchers and traditional companies customizing specific products and services for their users. However, we have worked with many developers and researchers in the machine learning community to improve the open source library, so DeepSpeech is currently used Sophisticated and cutting-edge machine learning technology creates a speech-to-text engine.”