# Benchmarking the Qualcomm Neural Processing SDK for AI vs. TensorFlow on Android

Source: [https://docs.qualcomm.com/doc/80-63442-4/topic/benchmarking-qualcomm-neural-processing-sdk.html](https://docs.qualcomm.com/doc/80-63442-4/topic/benchmarking-qualcomm-neural-processing-sdk.html)

Machine learning inference on edge devices

The [Qualcomm® Neural Processing SDK for AI](https://www.qualcomm.com/developer/software/neural-processing-sdk-for-ai) is
            designed for converting and executing deep neural networks on the Snapdragon® mobile
            platform without connecting to the cloud. The SDK is built for heterogeneous computing
            and running trained neural networks on different cores: CPU, Qualcomm® Adreno™ GPU and
            Qualcomm® Hexagon™ DSP.

Before investing development effort in moving those workloads out of the cloud and onto
            mobile devices, it is worthwhile to run performance benchmarks.

To set up the Qualcomm Neural Processing SDK, download it from the [Tools & Resources page on Qualcomm Developer
                Network](https://qpm.qualcomm.com/#/main/tools/details/qualcomm_neural_processing_sdk). The page includes system requirements and offers instructions for
            setting up the SDK, converting models and building the sample Android application in the
            SDK. (Note that Android NDK version r-11 is required for proper SDK setup.)

## Quantizing a model

The SDK includes utilities for converting existing models to the Deep Learning
                Container (.dlc) format that the Qualcomm(R) Neural Processing Engine (NPE) runtime
                reads. The SDK also includes a utility for quantizing (optimizing) trained models to
                reduce their size and improve efficiency.

Once the model is converted and optimized, devices running the Qualcomm NPE runtime
                can load the .dlc file. The Qualcomm NPE runtime processes the data and generates
                predictions.

## Benchmarking against the TensorFlow framework

The following considerations apply to this benchmark exercise:

1. Machine learning models — Inception-v3 averages about 80 percent confidence. It
                    is a popular neural network in use today and suitable for developers learning
                    about neural networks. AlexNet is trained on more than a million images and can
                    classify into hundreds of object categories (e.g., keyboard, mouse, pencil and
                    many animals).
2. Processor core — Benchmarking takes place on both CPU and GPU. The latter core
                    offers parallel processing and is better suited to detection in images.
3. Framework — The benchmark compares the performance of models generated by the
                    Qualcomm Neural Processing SDK against those generated by TensorFlow, an open
                    source library made for developing and training ML models. (Refer to TensorFlow
                    for instructions on setting up TensorFlow for Android.)
4. Workload — The application under test performs object detection and prediction.
                    It uses the models (Inception-v3 and AlexNet) to detect and process objects in
                    the feed from the camera.

The screenshots below are taken from the applications. Both correctly identify the
                object as a mouse. Note, however, that the app running Qualcomm NPE indicates 89
                percent confidence and 7.52 frames per second. The metrics are more than double
                those of the app running TensorFlow.  
![](data:image/png;base64,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)

## Results of benchmark testing

This type of benchmark testing can tentatively show the relative performance
                improvement achievable using optimization tools on various AI frameworks. The table
                below summarizes the main aspects of the testing, with performance using
                TensorFlow-Inception-v3 on CPU normalized to 1x.

|  | TensorFlow Inception-v3 | Qualcomm NPE Inception-v3 | Qualcomm NPE AlexNet |
| --- | --- | --- | --- |
| Maximum performance with CPU | 1x | 1.5x | 3 - 3.5x |
| Maximum performance with GPU | 3x | 8x | 14x |
| Model format | .pb | .dlc | .dlc |
| Mobile processors supported | QTI (e.g., Snapdragon 8xx) and other (e.g., Exynos 7xxx)<br>                                    platforms | Only QTI (e.g., Snapdragon 8xx) platform | Only QTI (e.g., Snapdragon 8xx) platform |
| Processing also supported on DSP? | No | Yes | Yes |
| API language support | C++, Java, Python, NodeJS | C++, Java | C++, Java |
| Tool kit designed for: | Training and inferencing | Inferencing | Inferencing |

The following graph compares the orange and blue cells in the table:  
![](data:image/png;base64,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)

Thus, when running inference with the Inception-v3 model, the application built on
                the Qualcomm Neural Processing SDK processes more frames per second.

## Next step

The Qualcomm Developer Network is a source for [other projects that use the Qualcomm Neural
                    Processing SDK for AI](https://www.qualcomm.com/developer/software/neural-processing-sdk-for-ai). Developers can use the projects as prototypes in
                their own development efforts.

**Parent Topic:** [Artificial Intelligence, Machine Learning, Android and the Qualcomm Neural Processing SDK for AI](https://docs.qualcomm.com/doc/80-63442-4/topic/artificial-qualcomm-neural-processing-sdk.html)

Last Published: Jun 24, 2024

[Previous Topic
Introduction to the Qualcomm Neural Processing SDK for AI and its components](https://docs.qualcomm.com/bundle/publicresource/80-63442-4/topics/introduction-to-qualcomm-neural-processing-sdk.md) [Next Topic
Bringing up TensorFlow frameworks on the Qualcomm Neural Processing SDK for AI](https://docs.qualcomm.com/bundle/publicresource/80-63442-4/topics/bringing-up-tensorflow-frameworks.md)