README.md
1# PyArmNN Image Classification Sample Application
2
3## Overview
4
5To further explore PyArmNN API, we provide an example for running image classification on an image.
6
7All resources are downloaded during execution, so if you do not have access to the internet, you may need to download these manually. The file `example_utils.py` contains code shared between the examples.
8
9## Prerequisites
10
11##### PyArmNN
12
13Before proceeding to the next steps, make sure that you have successfully installed the newest version of PyArmNN on your system by following the instructions in the README of the PyArmNN root directory.
14
15You can verify that PyArmNN library is installed and check PyArmNN version using:
16```bash
17$ pip show pyarmnn
18```
19
20You can also verify it by running the following and getting output similar to below:
21```bash
22$ python -c "import pyarmnn as ann;print(ann.GetVersion())"
23'32.0.0'
24```
25
26##### Dependencies
27
28Install the dependencies:
29
30```bash
31$ pip install -r requirements.txt
32```
33
34## Perform Image Classification
35
36Perform inference with TFLite model by running the sample script:
37```bash
38$ python tflite_mobilenetv1_quantized.py
39```
40
41Perform inference with ONNX model by running the sample script:
42```bash
43$ python onnx_mobilenetv2.py
44```
45
46The output from inference will be printed as <i>Top N</i> results, listing the classes and probabilities associated with the classified image.
47
README.md.license
1#
2# Copyright © 2020-2022 Arm Ltd and Contributors. All rights reserved.
3# SPDX-License-Identifier: MIT
4#
5