Khoa 🔥 Profile picture
AppStore App of the Day @PastePalApp 🏆 Also made @GetAlmighty @wwdctogether @ChatJoyAI @CodelimeHQ @ShipmunkApp @IndieGoodies

Nov 1, 2021, 22 tweets

Have you started leveraging the power of ML in your apps?

While browsing through GitHub for inspirations, I've bookmarked these awesome 20+ open-source machine learning projects

Bring magic to your apps 🧵

⚡️ TensorFlow

The latest version of TensorFlow supports Keras, which is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano.

There are also interfaces for Javascript and Swift.

tensorflow.org

⚡️ scikit-learn

Scikit-learn has simple and efficient tools for data mining and data analysis, built on NumPy, SciPy, and Matplotlib.

It’s a popular choice to use alongside TensorFlow because of its simplicity and handy functions. scikit-learn.org

⚡️ MXNet

Besides TensorFlow, Keras, and Scikit-learn, there is also the MXNet deep learning framework from Apache. There is a model zoo you can visit for many models implemented in MXNet. github.com/apache/incubat…

⚡️ PyTorch

PyTorch is a Python package that provides two high-level features: Tensor computation (like NumPy) with strong GPU acceleration and deep neural networks built on a tape-based autograd system. github.com/pytorch/pytorch

⚡️ magenta

Magenta is a research project exploring the role of machine learning in the process of creating art and music github.com/tensorflow/mag…

⚡️ style2paints

This project is aimed to colorize line art.

The AI can paint on a sketch according to a given color style, create its own color style to paint on a sketch or transfer another illustration’s style. github.com/lllyasviel/sty…

⚡️ Image-to-image translation in PyTorch

This project has two components—CycleGAN and pix2pix—which contain PyTorch implementations for both unpaired and paired image-to-image translation github.com/junyanz/pytorc…

⚡️ Deep voice conversion

We have some style transfer tools for images and video, but what about voice? Deep voice conversation is a perfect example of this capability. github.com/andabi/deep-vo…

⚡️ StarGAN in PyTorch

It goes beyond style transfer to convert source images by applying different hairstyles, skin types, ages, gender, and different moods. github.com/yunjey/StarGAN

⚡️ Face detection

This may not sound intriguing because now we can do this easily with the help of Core ML or ML Kit on iOS and Android.

But a deeper look shows how awesome this is. Not only can it detect faces, but also emotions and genders. github.com/oarriaga/face_…

⚡️ Deep universal probabilistic programming

Opportunities range from matching riders to drivers, to suggesting optimal routes, finding sensible pool combinations, and even creating the next generation of intelligent vehicles

⚡️ Detectron

Detectron is Facebook AI Research’s software system that implements state-of-the-art object detection algorithms, including Mask R-CNN.

It’s written in Python and powered by the Caffe2 deep learning framework. github.com/facebookresear…

⚡️ Fast Style Transfer

Implemented with a TensorFlow CNN, this is maybe one of the best examples of image style transfer, and as its name suggests, it’s done pretty fast

⚡️ Face recognition

This tool provides simple APIs for facial recognition. It can find facial features and can guess who is in a given photo. github.com/ageitgey/face_…

⚡️ Deep photo style transfer

Another fantastic style transfer project. This repo contains code and a research paper: Deep Photo Style Transfer.

It provides simple APIs to play with merging style and source images. github.com/luanfujun/deep…

⚡️ Fast Text

fastText is a library for efficient learning of word representations and sentence classification. github.com/facebookresear…

⚡️ AirSim

AirSim is a simulator for drones, cars, and more built on Unreal Engine.

It’s open-sourced, cross-platform, and it supports hardware-in-loop with popular flight controllers github.com/Microsoft/AirS…

⚡️ Image restoration

Machine learning can do more than we can imagine. With Deep Image Prior, it’s about fixing images with neural networks—but without learning. github.com/DmitryUlyanov/…

⚡️ Open Pose

Open Pose represents the first real-time, multi-person system to jointly detect human body, hand, facial, and foot key points (in total 135 keypoints) on single images.

It can detect feet, bodies, faces, and hands. github.com/CMU-Perceptual…

⚡️ EmojiIntelligence

This is fairly simple compared to many projects on this list, but it’s a good starting point for learning how a neural network works.

The implementation is in pure Swift without any libraries, and it’s easy to follow. github.com/BilalReffas/Em…

If you like this thread, please consider

❤️ Like
🔁 Retweet for others to see.
👋 Follow me @onmyway133 for more sharing about app development.

Share this Scrolly Tale with your friends.

A Scrolly Tale is a new way to read Twitter threads with a more visually immersive experience.
Discover more beautiful Scrolly Tales like this.

Keep scrolling