Stars
📊 A simple command-line utility for querying and monitoring GPU status
An open-source framework for training large multimodal models.
🚀 Efficient implementations of state-of-the-art linear attention models
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
Simple, safe way to store and distribute tensors
pytorch structural similarity (SSIM) loss
Visualizations of the connections between chaos theory and fractals through the logistic map; made for Veritasium YouTube video
The WeightWatcher tool for predicting the accuracy of Deep Neural Networks
A framework for Privacy Preserving Machine Learning
This is an official implementation of facial landmark detection for our TPAMI paper "Deep High-Resolution Representation Learning for Visual Recognition". https://arxiv.org/abs/1908.07919
A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation
The Qualcomm® AI Hub Models are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.
A collection of stand-alone Python machine learning recipes
Build high-performance AI models with modular building blocks
The Hailo Model Zoo includes pre-trained models and a full building and evaluation environment
Recreate any audio track by rearranging the frames of another video
Search docs.voxel51.com with an LLM!
Code release for "Dropout Reduces Underfitting"
Mode Connectivity and Fast Geometric Ensembles in PyTorch
Attention-based Dropout Layer for Weakly Supervised Object Localization (CVPR 2019 Oral)
NEXT is a machine learning system that runs in the cloud and makes it easy to develop, evaluate, and apply active learning in the real-world. Ask better questions. Get better results. Faster. Autom…
Workspace implementation for Torque Framework CLI.
Repository containing Pytorch code for EKFAC and K-FAC perconditioners.
PyTorch implementation of the REMIND method from our ECCV-2020 paper "REMIND Your Neural Network to Prevent Catastrophic Forgetting"
SensiML's open-source AutoML solution for Edge AI model development