article thumbnail

ODSC’s AI Weekly Recap: Week of March 8th

ODSC - Open Data Science

You Only Look Once (YOLO) is one of the most well-known computer vision model architectures. gemma.cpp is a lightweight, standalone C++ inference engine for the Gemma foundation models from Google. This repository is an implementation of the paper — YOLOv9. raised $600M from private investors.

article thumbnail

This AI Paper from Google Presents a Set of Optimizations that Collectively Attain Groundbreaking Latency Figures for Executing Large Diffusion Models on Various Devices

Marktechpost

Reformer uses a sparse approximation to reduce computing cost, while other works use low-rank or a combination of approximation techniques. FlashAttention, on the other hand, is a precise attention algorithm that considers hardware configurations to achieve better performance.

professionals

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

article thumbnail

Underwater Trash Detection using Opensource Monk Toolkit

Towards AI

Computer Vision The entire code for this application is available in Monk Object Detection Library’s Application Model Zoo Introduction Underwater Waste is a huge environmental problem affecting aquatic habitat drastically. Last Updated on July 19, 2023 by Editorial Team Author(s): Abhishek Annamraju Originally published on Towards AI.

article thumbnail

Speed is all you need: On-device acceleration of large diffusion models via GPU-aware optimizations

Google Research AI blog

We address this challenge in our work titled “ Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations ” (to be presented at the CVPR 2023 workshop for Efficient Deep Learning for Computer Vision ) focusing on the optimized execution of a foundational LDM model on a mobile GPU.

article thumbnail

The NLP Cypher | 02.14.21

Towards AI

github.com Their core repos consist of SparseML: a toolkit that includes APIs, CLIs, scripts and libraries that apply optimization algorithms such as pruning and quantization to any neural network. DeepSparse: a CPU inference engine for sparse models. Follow their code on GitHub. SparseZoo: a model repo for sparse models.

NLP 94
article thumbnail

The NLP Cypher | 02.14.21

Towards AI

github.com Their core repos consist of SparseML: a toolkit that includes APIs, CLIs, scripts and libraries that apply optimization algorithms such as pruning and quantization to any neural network. DeepSparse: a CPU inference engine for sparse models. Follow their code on GitHub. SparseZoo: a model repo for sparse models.

NLP 52