MachineLearning

MachineLearning

[N] [P] Google Deepmind released an album with

[N] [P] Google Deepmind released an album with "visualizations of AI" to combat stereotypical depictions of glowing brains, blue screens, etc.

[R] Video of experiments from DeepMind's recent “Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning” (OP3 Soccer) project

[R] Video of experiments from DeepMind's recent “Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning” (OP3 Soccer) project

I made a chrome extension to make chatGPT bots from any web content in seconds [P]

I made a chrome extension to make chatGPT bots from any web content in seconds [P]

[R] neural cloth simulation

[R] neural cloth simulation

[R] Speech-to-speech translation for a real-world unwritten language

[R] Speech-to-speech translation for a real-world unwritten language

[R] GANs N' Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!)

[R] GANs N' Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!)

[D] Trying Machine Learning for the first time - What could possibly go wrong?

[D] Trying Machine Learning for the first time - What could possibly go wrong?

[R] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

[R] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

[P] Using Deep Learning to draw and write with your hand and webcam 👆. The model tries to predict whether you want to have 'pencil up' or 'pencil down' (see at the end of the video). You can try it online (link in comments)

[P] Using Deep Learning to draw and write with your hand and webcam 👆. The model tries to predict whether you want to have 'pencil up' or 'pencil down' (see at the end of the video). You can try it online (link in comments)

[P] Tutorial: Prune and quantize YOLOv5 for 12x smaller size and 10x better performance on CPUs

[P] Tutorial: Prune and quantize YOLOv5 for 12x smaller size and 10x better performance on CPUs

[P] Some of you may already know me but I wanted to share this to all who do not know. This is a personal project on video captioning. The model is used to generate captions describing scene/event of a video. Here is a working demo working in realtime. Ch

[P] Some of you may already know me but I wanted to share this to all who do not know. This is a personal project on video captioning. The model is used to generate captions describing scene/event of a video. Here is a working demo working in realtime. Ch

[R] Audio-driven Neural Rendering of Portrait Videos. In this project, we use neural rendering to manipulate the left video using only the voice from the right video. The videos belong to their respective owners and I do not claim any right over them.

[R] Audio-driven Neural Rendering of Portrait Videos. In this project, we use neural rendering to manipulate the left video using only the voice from the right video. The videos belong to their respective owners and I do not claim any right over them.

[P] StyleGAN2-ADA trained on cute corgi images <3

[P] StyleGAN2-ADA trained on cute corgi images <3

[N] AI can turn old photos into moving Images / Link is given in the comments - You can also turn your old photo like this

[N] AI can turn old photos into moving Images / Link is given in the comments - You can also turn your old photo like this

[D] Convolution Neural Network Visualization - Made with Unity 3D and lots of Code / source - stefsietz (IG)

[D] Convolution Neural Network Visualization - Made with Unity 3D and lots of Code / source - stefsietz (IG)

[D] A Demo from 1993 of 32-year-old Yann LeCun showing off the World's first Convolutional Network for Text Recognition

[D] A Demo from 1993 of 32-year-old Yann LeCun showing off the World's first Convolutional Network for Text Recognition

Avatarify lets you port expressions onto another face using just a single image.

Avatarify lets you port expressions onto another face using just a single image.

[P] Exploring Typefaces with Generative Adversarial Networks

[P] Exploring Typefaces with Generative Adversarial Networks

[P]Toonify's latent space exploration with music. (Don't forget to turn on audio:))

[P]Toonify's latent space exploration with music. (Don't forget to turn on audio:))

[P] Cross-Model Interpolations between 5 StyleGanV2 models - furry, FFHQ, anime, ponies, and a fox model

[P] Cross-Model Interpolations between 5 StyleGanV2 models - furry, FFHQ, anime, ponies, and a fox model

[P] ObjectCut - API that removes automatically image backgrounds with DL (objectcut.com)

[P] ObjectCut - API that removes automatically image backgrounds with DL (objectcut.com)

[Project] From books to presentations in 10s with AR + ML

[Project] From books to presentations in 10s with AR + ML

[P] YOLOv4 — The most accurate real-time neural network on MS COCO Dataset

[P] YOLOv4 — The most accurate real-time neural network on MS COCO Dataset

[Project] From books to presentations in 10s with AR + ML

[Project] From books to presentations in 10s with AR + ML

Browse Other Categories