Jan. 16, 2022, 4:17 p.m. | Aditya Kane

Towards Data Science - Medium towardsdatascience.com

This blog post is about sharing my experience of training 24 RegNet models for tf.keras.applications.

Photo by Paola Blašković on Unsplash

Prologue

tf.keras.applications is a set of built-in models in TensorFlow-Keras. They are pretrained on ImageNet-1k, and are just one function call away. This makes life easier for the ML folks as they have ready-to-go models at their disposal. RegNets are highly efficient and scalable models proposed by Facebook AI Research (FAIR). They are used in works like SEER which …

applications keras open source tensorflow training

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Senior AI & Data Engineer

@ Bertelsmann | Kuala Lumpur, 14, MY, 50400

Analytics Engineer

@ Reverse Tech | Philippines - Remote