Accelerate image recognition using distributed model training and automated model architecture search

Image recognition models usually require a huge number of images for training. This makes it really hard for data science teams to try new model architecture since they will have to invest long hours into retraining. Automated architecture search requires even mode retraining cycles.

This talk shows how teams can iterate faster by distributing image preparation, model training and automating model architecture search. This talk includes a live demonstration of full training pipeline including image preprocessing, distributed training and automated model architecture search.