Unofficial implementation of Perceiver IO

ARC file: A data format for 3D vision researchers and developers

In-Place Activated BatchNorm for Memory-Optimized Training of DNNs

solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning

An out-of-box human parsing representation extractor.

An Alfred workflow to search Notion with instant results

Render Jupyter notebook in the terminal

A biologically inspired method to create sparse, binary word vectors

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT p…

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Flexible Python configuration system. The last one you will ever need.

Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute

FasterAI: A repository for making smaller and faster models with the FastAI library.

Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple

The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

Library for viewing, augmenting, and handling .pose files

Just draw a bounding box and you can remove the object you want to remove.

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

Fawkes, privacy preserving tool against facial recognition systems. More info at https://sandlab.cs.uchicago.edu/fawkes

Real-time microphone noise suppression on Linux.

Basics of 2D and 3D Human Pose Estimation.

Accompanying library for the Record3D iOS app (https://record3d.app/). Allows you to receive RGBD stream from iOS devices with TrueDepth camera(s).

High-Resolution 3D Human Digitization from A Single Image.

3 dimensional spatial transformations

A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run.

2-D Kalman Filter for Tracking a randomly moving object

Data preparation and loader for AMASS