Efficient inference on IMG Series4 NNAs
February 6, 2023
Research into neural network architectures generally prioritises accuracy over efficiency. Certain papers have investigated efficiency (Tan and Le 2020) (Sandler, et al. 2018), but quite often this is with CPU- or GPU-based rather than accelerator-based inference in mind.
In this original work from Imagination’s AI Research team, many well-known classification networks trained on ImageNet are evaluated. We are not interested in accuracy or cost in their own right, but rather in efficiency, which is a combination of the two. In other words, we want networks that get high accuracy on our IMG Series4 NNAs at as low a cost as possible. We cover:
- identifying ImageNet classification network architectures that give the best accuracy/performance trade-offs on our Series4 NNAs.
- reducing cost dramatically using quantisation-aware training (QAT) and low-precision weights without affecting accuracy.
To read the full article, click here
Related Semiconductor IP
- Post-Quantum Digital Signature IP Core
- Compact Embedded RISC-V Processor
- Power-OK Monitor
- RISC-V-Based, Open Source AI Accelerator for the Edge
- Securyzr™ neo Core Platform
Related Blogs
- Deep learning inference performance on the Yitian 710
- Introducing Cortex-A35: ARM's Most Efficient Application Processor
- Energy Efficient Designs with MIPI
- Automotive Cries for Earlier, More Efficient Testing
Latest Blogs
- Running Optimized PyTorch Models on Cadence DSPs with ExecuTorch
- PCIe 6.x: Synopsys IP Selected as First Gold System for Compliance Testing
- Post-quantum security in platform management: PQShield is ready for SPDM 1.4
- Unleash Real-Time LiDAR Intelligence with Akida On-Chip AI
- Ceva Advancing Real-Time AI with Transformers and Intelligent Quantization