Data augmentation is a set of techniques that expand the diversity of data available for training machine learning models by generating new data from existing data. This talk will introduce different types of data augmentation techniques as well as their uses in various training scenarios. We will explore some built-in augmentation methods in popular ML frameworks like PyTorch and TensorFlow. And we will discuss some tips and tricks that are commonly used to randomly select parameters to avoid having model overfit to a particular dataset.
An Introduction to Data Augmentation Techniques in ML frameworks
Session Speakers
-
Rajy Rawther
PMTS Software Architect, Advanced Micro Devices
Rajy Rawther is a Software Architect at AMD and the lead developer of the MIVisionX toolkit for computer vision and machine learning. She has been with AMD for more than 17 years and has had multiple engineering roles in areas including video codecs, computer vision and machine learning. She has extensive experience in heterogeneous programming languages and performance optimization of machine learning and computer vision algorithms. Lately, her focus is on building efficient pipelines for ML workloads. Rajy has a Master of Engineering degree in System Science and Automation from the Indian Institute of Science and a Bachelor's degree in Electrical and Electronics engineering.
