iejMac

video2dataset

Easily create large video dataset from video urls

video2numpy

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

clip-video-encode

Easily compute clip embeddings from video frames

GPTReview

Get OpenAI GPT models to review your PR's

encoder-distill

Align embedding spaces of PyTorch encoders with common input types.

nanoH264

compressing videos

stalingrad

our deep learning framework

TTTArena

Arena for testing different solutions to Tic-Tac-Toe 5

driving-sim

🚗 Data-powered driving simulator

leancoder

Proving math theorems in Lean using the DreamCoder algorithm.

gotMotion

code for simple video motion estimations methods.

open_lm

A repository for research on medium sized language models.

salmon

🐟

webvid

Large-scale text-video dataset. 10 million captioned short videos.

AdventOfCode

Advent of Code

commavq

commaVQ is a dataset of compressed driving video

config

My configs

depth10k

10k images for unsupervised depthnets

GamesOfLife

Gaze

Visualize Torch Models

iejmac.github.io

image-rectification

laion.ai

Megatron-LM

Ongoing research training transformer models at scale

MoVQGAN

MoVQGAN - model for the image encoding and reconstruction

open_clip

An open source implementation of CLIP.

open_ml

Generic template for ML projects

openpilot

openpilot is an open source driver assistance system. openpilot performs the functions of Automated Lane Centering and Adaptive Cruise Control for over 85 supported car makes and models.

ScriptWriter

Neural network that fills in blank spaces in movie scripts

torchgeo

TorchGeo: datasets, transforms, and models for geospatial data