moodoki

dart

[CVPR 2024] DART: Implicit Doppler Tomography for Radar Novel View Synthesis

VILA

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

depth-fm

DepthFM: Fast Monocular Depth Estimation with Flow Matching

equiadapt

Library to make any existing neural network architecture equivariant

open_flamingo

An open-source framework for training large multimodal models.

aiyprojects-raspbian

API libraries, samples, and system images for AIY Projects (Voice Kit and Vision Kit). If you find this helpful, buy me a coffee to help me keep the drivers updated - https://paypal.me/viraniac

Otter

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

gefolki

GeFolki is a coregistration algorithm develop at ONERA in Medusa project

lytro_unlock

Documenting reverse engineering of the original Lytro lightfield camera

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

photon

A DIY incident light meter

dreambooth

galai

Model API for GALACTICA

KataGo

GTP engine and self-play learning in Go

WeightWatcher

The WeightWatcher tool for predicting the accuracy of Deep Neural Networks

stable-diffusion

Latent Text-to-Image Diffusion

goatcounter

Easy web analytics. No tracking of personal data.

STT

🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.

metaseq

Repo for external large-scale work

taming-transformers

Taming Transformers for High-Resolution Image Synthesis

open_clip

An open source implementation of CLIP.

google-research

Google Research

transformers-interpret

Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.

DALLE-pytorch

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

annotated_deep_learning_paper_implementations

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

tilt-brush

colmap

COLMAP - Structure-from-Motion and Multi-View Stereo

SpectralBias

Code for "On the Spectral Bias of Neural Networks", to appear in ICML 2019 (Long Beach, CA).

ios_logger

Application for camera and sensor data logging (iOS)

darktable

darktable is an open source photography workflow application and raw developer