Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.

This series will take you on a journey from the fundamentals of NLP and Computer Vision to the cutting edge of Vision-Language Models.

AICI: Prompts as (Wasm) Programs

Simple and readable code for training and sampling from diffusion models

Label Studio is a multi-type data labeling and annotation tool with standardized output format

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions

🔵 Application core of BIIGLE

A new markup-based typesetting system that is powerful and easy to learn.

Quickly rewrite git repository history (filter-branch replacement)

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

OpenMMLab Self-Supervised Learning Toolbox and Benchmark

Official Code of ICCV 2021 Paper: Learning to Cut by Watching Movies

A PyTorch implementation of Connected Components Labeling

Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge network

Robust Speech Recognition via Large-Scale Weak Supervision

Official repo for the paper "Make Some Noise: Reliable and Efficient Single-Step Adversarial Training" (https://arxiv.org/abs/2202.01181)

FFCV: Fast Forward Computer Vision (and other ML workloads!)

Self-labelling via simultaneous clustering and representation learning. (ICLR 2020)

Open-source simulator for autonomous driving research.

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Domain Adaptive Faster R-CNN in PyTorch

Datasets, Transforms and Models specific to Computer Vision

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

Face recognition for identification case study based on OpenFace