KerasCV and KerasNLP: Vision and Language Power-Ups

no code implementations • 30 May 2024 • Matthew Watson, Divyashree Shivakumar Sreepathihalli, Francois Chollet, Martin Gorner, Kiranbir Sodhia, Ramesh Sampath, Tirth Patel, Haifeng Jin, Neel Kovelamudi, Gabriel Rasskin, Samaneh Saadat, Luke Wood, Chen Qian, Jonathan Bischof, Ian Stenbit, Abheesht Sharma, Anshuman Mishra

We present the Keras domain packages KerasCV and KerasNLP, extensions of the Keras API for Computer Vision and Natural Language Processing workflows, capable of running on either JAX, TensorFlow, or PyTorch.

Deep Learning Object Detection Approaches to Signal Identification

no code implementations • 27 Oct 2022 • Luke Wood, Kevin Anderson, Peter Gerstoft, Richard Bell, Raghab Subbaraman, Dinesh Bharadia

Traditionally source identification is solved using threshold based energy detection algorithms.

Object object-detection +1

Efficient Graph-Friendly COCO Metric Computation for Train-Time Model Evaluation

no code implementations • 21 Jul 2022 • Luke Wood, Francois Chollet

Evaluating the COCO mean average precision (MaP) and COCO recall metrics as part of the static computation graph of modern deep learning frameworks poses a unique set of challenges.