Top 10 Deep Learning Github Repositories 2018.

Aug. 22, 2018, 2:36 p.m. By: Kirti Bakshi


In this article, we bring you a list of the Top 10 Deep Learning Github Repositories on a trend that has been sorted by the number of stars.

The Top 10 Deep Learning Repositories along with their respective links are:

1. Tensorflow:

TensorFlow, that, within Google's Machine Intelligence Research organization was originally developed by researchers and engineers working on the Google Brain team is an open source software library used for numerical computation making the use of data flow graphs for the purpose of scalable machine learning.

Link: Click Here

2. Keras:

Keras, written in Python is a high-level neural networks API that is capable of running on top of TensorFlow, CNTK, or Theano. It was developed with a focus on enabling fast experimentation that through user friendliness, modularity, and extensibility allows for easy as well as fast prototyping. In short, can be said to be Deep Learning For Humans.

Link: Click Here

3. OpenCV:

OpenCV (Open Source Computer Vision Library) was designed for computational efficiency with its strong focus on real-time applications. Having made its release under a BSD license, it’s free for both academic as well as commercial use. It has C++, Python and Java interfaces and supports iOS, Linux, Android, Windows, and Mac OS. Since it is enabled with OpenCL, it can take advantage of the hardware acceleration of the underlying heterogeneous compute platform

Link: Click Here

4. Caffe:

Caffe is a deep learning framework made keeping in mind expression, speed, and modularity. It is developed by Berkeley AI Research (BAIR)/The Berkeley Vision and Learning Center (BVLC) and community contributors.

Link: Click Here

5. Tensorflow-Examples:

Through examples, this tutorial was designed for easily diving into TensorFlow. For readability, it includes both notebooks as well as a source codes wan ith explanation. It is considered to be suitable for beginners who want to find clear and concise examples about TensorFlow. Besides the traditional 'raw' TensorFlow implementations, the latest TensorFlow API practices can also be found.

Link: Click Here

6. Machine-Learning-For-Software-Engineers:

This is a multi-month study plan for going from a self-taught mobile developer to a machine learning engineer. The main goal was to fad an hands-on approach to studying Machine Learning that for the beginner abstracts most of the Math.

Link: Click Here

7. Deeplearningbook-Chinese:

With the help and proofreading of many netizens, Although there are still many problems, the Chinese version of the book was finally published. Still, at least 90% of the content is readable and accurate. The meaning of the original book Deep Learning was kept as much as possible and they also managed to keep the original book statement.

Link: Click Here

8. Deep-Learning-Papers-Reading-Roadmap:

The construction of the roadmap has been made in accordance with the following four guidelines:

  • From Outline To Detail

  • From Old To State-Of-The-Art

  • From Generic To Specific Areas

  • Focus On State-Of-The-Art

The reader may find many papers that are quite new but really worth reading. The new addition of papers to this roadmap still continues.

Link: Click Here

9. Pytorch:

PyTorch is a Python package that provides the following two high-level features:

  • Tensor computation with strong GPU acceleration

  • Deep neural networks built on a tape-based autograd system

Your favourite Python packages such as NumPy, SciPy and Cython can be reused in order to extend PyTorch as and when needed.

Link: Click Here

10. Awesome-Deep-Learning-Papers:

It presents to you a curated list of the most cited deep learning papers (since 2012).

They believe that regardless of their application domain, there exist classic deep learning papers which are worth reading. So, rather than providing an overwhelming amount of papers, they instead put forward a curated list of the awesome deep learning papers which in certain research domains are considered as must-reads.

Link: Click Here

Find a full list of 200 deep learning Github repositories : Click Here