Ana will discuss our research into this challenge in the context of a face verification CNN which consumes the output of a face detection CNN, and presents approaches for reducing the impact of quantization in such scenarios.
Agenda
- Introduction to the problem
- Accuracy metrics for quantized networks
- Impact of quantisation on a one stage task: Face Detection
- Impact of quantisation on a two stages task: Face Recognition
- Experiments and Results
Learn more about our neural network product range: here
Speaker: Ana Salazar, Direct of Research at IMG Labs, Imagination Technologies
Duration: 18 minutes
Available on Demand