How to measure performance of your NN models using the Coral Edge TPU

Applicable for STM32MP13x lines, STM32MP15x lines

This article describes how to measure the performance of a neural network model compiled for Coral Edge TPU on STM32MP1x plateform.

1 Installation[edit]

1.1 Installing from the OpenSTLinux AI package repository[edit]

Warning white.png Warning
The software package is provided AS IS, and by downloading it, you agree to be bound to the terms of the software license agreement (SLA0048). The detailed content licenses can be found here.

After having configured the AI OpenSTLinux package you can install X-LINUX-AI components for this application. The minimum package required is the tflite-edgetpu-benchmark, it could be installed directly on your board using the following command:

 apt-get install tflite-edgetpu-benchmark

The model used in this example can be installed from the following package:

 apt-get install tflite-models-coco-ssd-mobilenetv1-edgetpu

2 How to use the Benchmark application[edit]

2.1 Executing with the command line[edit]

The tflite_edgetpu_benchmark application is located in the userfs partition:

/usr/local/bin/coral-edgetpu-2.0.0/tools/tflite_edgetpu_benchmark

It accepts the following input parameters:

Usage: ./tflite-edgetpu-benchmark

        -m --model_file <.tflite file path>:  .tflite model to be executed
        -l --loops <int>:                     provide the number of time the inference will be executed 
                                              (by default nb_loops=1)
        --help:                               show this help

2.2 Testing with COCO SSD MobileNet V1[edit]

The model used for testing is the detect_edgetpu.tflite which is a COCO SSD MobilenetV1. It is a model used for object detection.
On the target, the model is located here:

/usr/local/demo-ai/computer-vision/models/coco_ssd_mobilenet/

To launch the application, use the following command:

   /usr/local/bin/coral-edgetpu-2.0.0/tools/tflite_edgetpu_benchmark -m /usr/local/demo-ai/computer-vision/models/coco_ssd_mobilenet/detect_edgetpu.tflite -l 50

Console output:

model file set to: /usr/local/demo-ai/computer-vision/models/coco_ssd_mobilenet/detect_edgetpu.tflite
This benchmark will execute 50 inference(s)
Bus 002 Device 004: ID 18d1:9302 Google Inc. 
Loaded model /usr/local/demo-ai/computer-vision/models/coco_ssd_mobilenet/detect_edgetpu.tflite
resolved reporter

inferences are running: # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # 

inference time: min=58315us  max=109714us  avg=66009.4us