DataComp for Language Models

Language models scale reliably with over-training and on downstream tasks

Optimized library for large-scale extraction of frames and audio from video.

Quiet Light theme for iTerm2

A jq clone focussed on correctness, speed, and simplicity

A customizable, cross-platform tool for parsing WhatsApp chat databases from Android and iOS/iPadOS backups. Supports Android .crypt12, .crypt14, .crypt15, and the latest database formats. Outputs …

A repository for research on medium sized language models.

[ICCV 2023] VPD is a framework that leverages the high-level and low-level knowledge of a pre-trained text-to-image diffusion model to downstream visual perception tasks.

Code for downloading and using the TAO dataset: http://taodataset.org/

[CVPR 2022] Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer

Line-by-line profiling for Python

1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking

🎞️ An intuitive CLI for processing video, powered by FFmpeg

A General Toolbox for Identifying Object Detection Errors

ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."

Intuitive find & replace CLI (sed alternative)

Implementation of "Tracking without bells and whistles” and the multi-object tracking "Tracktor"

A syntax-highlighting pager for git, diff, grep, and blame output

📊 Benchmark multiple object trackers (MOT) in Python

Simple, online, and realtime tracking of multiple objects in a video sequence.

ripgrep recursively searches directories for a regex pattern while respecting your gitignore

Python API for LVIS Dataset

A set of neural network modules, which are small fully connected layers operating in semantic concept space. These modules are configured through a gating function conditioned on the task to produc…

Boost LaTeX typesetting efficiency with preview, compile, autocomplete, colorize, and more.

Never use print for debugging again

[ECCV 2018] Video Object Detection with an Aligned Spatial-Temporal Memory

A repository of common methods, datasets, and tasks for video research

RoIAlign & crop_and_resize for PyTorch

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