25 August 2017
Benchmarking of CNNs for Low-Cost, Low-Power Robotics Applications
Introduction
Available benchmarks for object classification and detection using Convolutional Neural Networks (CNNs) focus on evaluating accuracy only. This is reflected in the state-of-the-art
Hardware setup
Three embedded platforms are used for performing inference: Movidius NCS, Raspberry Pi 3, Intel Joule The power consumption is measured by sampling on the power lines using the INA219 power monitor setup at a sampling rate of ~500Hz. For the Raspberry Pi and Joule, Caffe and TensorFlow frameworks are used to perform inference.
Benchmarked networks:
Network | Layers | Operations |
GoogLeNet | 27 | ~5 million |
AlexNet | 11 | ~60 million |
Network in Network | 16 | ~2 million |
VGG_CNN_F | 13 | ~500 thousand |
CIFAR | 9 | ~45 thousand |
Results
Inference Time:
Power Consumption
Conclusion:
The obtained inference times and power consumption show that by using the NCS some networks are up to 4x faster than running on other embedded platforms while keeping a low-power consumption. This is critical for battery powered low-cost robots. Future work includes the addition of more networks for the benchmark on more platforms and the creation of a public database for the obtained results.