Robert Cimpeanu, Machine Learning Software Engineer at NXP Semiconductors, presents the “Introduction to Shrinking Models with Quantization-aware Training and Post-training Quantization” tutorial at the May 2025 Embedded Vision Summit.
In this presentation, Cimpeanu explains two neural network quantization techniques, quantization-aware training (QAT) and post-training quantization (PTQ), and explains when to use each. He discusses what needs to be done for efficient implementation of each: for example, QAT requires preparation of models through layer fusion and graph optimization, while PTQ requires a suitable dataset.
Cimpeanu highlights the advantages and limitations of each approach and explores model architectures that benefit from QAT and PTQ. He also presents strategies for combining these techniques and introduces tools such as Brevitas that enable quantization, demonstrating how to optimize neural networks for improved performance and efficiency.
See here for a PDF of the slides.
