Deep Learning

Open-source projects categorized as Deep Learning | Edit details

Top 23 Deep Learning Open-Source Projects

  • GitHub repo tensorflow

    An Open Source Machine Learning Framework for Everyone

    Project mention: Google stock | | 2021-08-01

    Google leads in every layer of the AI stack. Lowest layer is silicon and their TPUs have been setting records with both training and inference at scale. "Google's TPU Pods are Breaking Records — And We Aren't Surprised" Next layer up above the silicon is basically the AI operating system. The most popular today is TensorFlow which is from Google. The second most popular is Pytorch from Facebook. TensorFlow now has over 150K stars on Github. One of the most popular projects on Github. The next layer above the framework is the algorithms. The best way to measure success with algorithms is the papers accepted at the canonical AI organization, NeurlIPS. In 2018, 2019, 2020 and sure will be the same in 2021 has seen Google having the most papers accepted by a large margin. Next layer is data. Which is probably where people most think of Google and Facebook. But Google has the more valuable data. Facebook data is what you want people to think of you. Versus Google has more truthful information. There is probably no more valuable data than search queries you make. It is this very unusual window into who you are. But with Google there is then all their other services. YouTube has the video data. Google Maps the location data. Google Photos is the biggest repository of photos. The list goes on and on. The next layer up is the applications. Search is the biggest AI/ML driven application in the world. Search penetrates 99% of the population of the US and then on top of that Google now has over 92% share. Why Google search share is increasing while competitors like Bing are declining is because of the Google superior AI. Google is now getting 2/3 of queries ending without needing a click. That is up from 50% the year before. "In 2020, Two Thirds of Google Searches Ended Without a Click" BTW, it is clear to me the goal with Google search is ultimately AGI. I believe that is exactly how AGI will happen at some point in the future. That might be 20 years off though. Or longer. This is the past in a way. It is really about new things. I am a techie and love technology and by far the most impressive technology thing I have seen is The car pulls up completely empty. No way to fake the technology when there is no driver or even a backup driver to take over. But as impressive this is the bigger AI/ML breakthrough with Google is the protein folding. Think about this. Did anyone think 25 years ago that advertising would be completely owned by big tech? Of course not. We are going to see big tech eat up one industry after another and AI is going to be a huge part of that. Take transportation. That will go to automation and that takes AI. Same with health.

  • GitHub repo OpenCV

    Open Source Computer Vision Library

    Project mention: First Python Project Tips | | 2021-07-28

    A classmate of mine back in the day made a rig that would automate the deadbolt on their front door. Obviously there are physical security concerns here but it would probably use an embedded board (Arduino or otherwise) and a servo (basis of a lot of robotics). If memory serves, they also tried hooking up a webcam to use OpenCV to do facial recognition as well.

  • SonarSource

    Deliver Clean and Safe Code for your Python Applications. Learn how static code analysis tools have helped the Python community identify (and fix) bugs and vulnerabilities in some prominent open source Python projects. Read More →

  • GitHub repo Keras

    Deep Learning for humans

    Project mention: Here is why Pytorch is more Pythonic than Tensorflow. | | 2021-07-27

    They both implement Artificial Neural Networks the same way. Thanks to Keras we can say that TensorFlow is quite beginner-friendly. Pytorch can be quite intimidating at first partly because you have to define your own training loop. This is great if you are a researcher because you can easily take control of the entire process. With TensorFlow, you can also define your own training loop too which is pretty much the same as PyTorch. As you go deeper into both frameworks you may start seeing the difference between both of them. If you read any article or listen to an expert on deep learning they usually say stuff like PyTorch is more pythonic but how.

  • GitHub repo Pytorch

    Tensors and Dynamic neural networks in Python with strong GPU acceleration

    Project mention: [D] [P] Deep Learning in Rust with GPU on ONNX | | 2021-07-30

    Hey there, thanks for reading ! So, i have not tried the tch crate. I have heard that libtorch is very heavy? -> but, I genuinely think that we need as many bindings as possible for rust as package for ml come and goes and onnx may go rogue at some point.

  • GitHub repo TensorFlow-Examples

    TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)

    Project mention: Keras vs. TensorFlow | | 2021-06-06

    A linear regression model

  • GitHub repo faceswap

    Deepfakes Software For All

    Project mention: Emma Watson | | 2021-05-17 bu uygulamadan yaparsın

  • GitHub repo Caffe

    Caffe: a fast open framework for deep learning.

    Project mention: Can someone please guide me regarding these different face detection models? | | 2021-05-27

    Caffe is a DL framework just like TensorFlow, PyTorch etc. OpenPose is a real-time person detection library, implemented in Caffe and c++. You can find the original paper here and the implementation here.

  • Scout APM

    Scout APM: A developer's best friend. Try free for 14-days. Scout APM uses tracing logic that ties bottlenecks to source code so you know the exact line of code causing performance issues and can get back to building a great product faster.

  • GitHub repo Deep-Learning-Papers-Reading-Roadmap

    Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!

    Project mention: 4 ML Roadmaps to Help You Find Useful Resources to Learn From | | 2021-07-11

    Deep Learning Papers Reading Roadmap

  • GitHub repo Real-Time-Voice-Cloning

    Clone a voice in 5 seconds to generate arbitrary speech in real-time

    Project mention: Voice Cloning Model for AI chatbot | | 2021-07-26

    Hello! I am working on a voice-driven AI chatbot and i want to give the user the option to customize the voice of the chatbot after getting an audio clip from user! now i know about the famous real time voice cloning method

  • GitHub repo DeepFaceLab

    DeepFaceLab is the leading software for creating deepfakes.

    Project mention: Requesting a deep fake of Lara Flynn Boyle in FWWM | | 2021-07-29

    It is surprisingly easy. This is the software I tried to use: DeepFaceLab

  • GitHub repo machine-learning-for-software-engineers

    A complete daily plan for studying to become a machine learning engineer.

    Project mention: Tips Untuk Pemula Dalam Programming Dan Data | | 2020-09-26
  • GitHub repo Tesseract.js

    Pure Javascript OCR for more than 100 Languages 📖🎉🖥

    Project mention: In-Browser OCR | | 2021-07-31
  • GitHub repo openpose

    OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

    Project mention: We built a free, open-source markerless motion capture system during the pandemic. This animation was created with 4x $20US webcams and a gaming PC, details in the comments [OC] | | 2021-07-21

    while I congratulate you for putting together a pipeline, I think it has to be said that the basis of this - the very powerful openpose - has a license that is not completely FOSS. It might be open source but is definitely not free as free beer. So if you consider using this for a fancy project (i.e. marketing an app), you have to get in touch with university of california first

  • GitHub repo data-science-ipython-notebooks

    Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.

    Project mention: Beginner in Python for Data Science | | 2020-12-27

    data science ipython notebooks

  • GitHub repo pytorch-tutorial

    PyTorch Tutorial for Deep Learning Researchers

    Project mention: How to 'practice' pytorch after finishing its basic tutorial? | | 2021-05-09

    I tried to move straight to practicing implementing papers and trying to understand other people's codes but failed miserably. I feel like there was too much of a gap between the basic tutorial and being able to implement ideas into code....hence the question: Is there any resource/way to practice pytorch in general? I did find this and this, but I just wanted to hear what others have gone through to become better at PyTorch up to the point they can build stuff from their own ideas

  • GitHub repo fastai

    The fastai deep learning library

    Project mention: D I Refuse To Use Pytorch Because Its A Facebook | | 2020-12-29

    Also, not a single docstring to document any code in the library -

  • GitHub repo spaCy

    💫 Industrial-strength Natural Language Processing (NLP) in Python

    Project mention: Is it worth learning NPL as a non programmer? | | 2021-07-12

    I did a search for "Python NLP", and the following links seemed relevant/likely to be useful: - RealPython NLP/NLTK tutorial/article - they tend to have quality content - Spacy library - List of top Python NLP libraries - NLP with Python tutorial - Topic modelling on Spanish texts

  • GitHub repo DeepSpeech

    DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

    Project mention: Voice search in firefox | | 2021-07-28

    I think they got rid of the backend to even support it. Mozilla still has the Deepspeech project although it might be slowed down.

  • GitHub repo awesome-deep-learning

    A curated list of awesome Deep Learning tutorials, projects and communities.

  • GitHub repo spleeter

    Deezer source separation library including pretrained models.

    Project mention: I split "That's America To Me" | | 2021-07-31

    Here ya go! It's basically drag and drop! If you're on Linux or Mac, you can use this if you're comfortable with CLI. I've been looking off and on for years, and trying various EQ techniques (to middling results) to make my own stems before landing on this program.

  • GitHub repo CNTK

    Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit (by microsoft)

  • GitHub repo darknet

    YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet ) (by AlexeyAB)

    Project mention: Ask HN: Reinforcement learning for single, lower end graphic cards? | | 2021-07-19

    This is mostly in the realm of computer vision, but I would recommend checking out AlexeyAB's fork of Darknet: It's got decent CUDA acceleration, I personally run a GTX 960M for training.

  • GitHub repo Ray

    An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.

    Project mention: Ray 1.4.0 | | 2021-06-08
NOTE: The open source projects on this list are ordered by number of github stars. The number of mentions indicates repo mentiontions in the last 12 Months or since we started tracking (Dec 2020). The latest post mention was on 2021-08-01.


What are some of the best open-source Deep Learning projects? This list will help you:

Project Stars
1 tensorflow 157,755
2 OpenCV 55,724
3 Keras 52,001
4 Pytorch 49,716
5 TensorFlow-Examples 40,941
6 faceswap 37,920
7 Caffe 31,809
8 Deep-Learning-Papers-Reading-Roadmap 30,219
9 Real-Time-Voice-Cloning 28,184
10 DeepFaceLab 27,519
11 machine-learning-for-software-engineers 25,233
12 Tesseract.js 24,139
13 openpose 21,487
14 data-science-ipython-notebooks 21,389
15 pytorch-tutorial 21,382
16 fastai 21,191
17 spaCy 20,996
18 DeepSpeech 17,766
19 awesome-deep-learning 17,451
20 spleeter 17,074
21 CNTK 17,056
22 darknet 16,864
23 Ray 16,757
SaaSHub - Software Alternatives and Reviews
SaaSHub helps you find the best software and product alternatives