{"id":43689,"date":"2023-09-06T07:07:50","date_gmt":"2023-09-06T05:07:50","guid":{"rendered":"https:\/\/www.inovex.de\/?p=43689"},"modified":"2023-09-06T10:54:09","modified_gmt":"2023-09-06T08:54:09","slug":"android-snapdragon-integration-tensor-interpretation-with-kotlin","status":"publish","type":"post","link":"https:\/\/www.inovex.de\/de\/blog\/android-snapdragon-integration-tensor-interpretation-with-kotlin\/","title":{"rendered":"Android Snapdragon Integration & Tensor Interpretation with Kotlin"},"content":{"rendered":"

During a recent tech spike, we had the opportunity to evaluate the integration of the Qualcomm Snapdragon SDK<\/a>\u00a0(SNPE) in an Android\/Kotlin environment. The spike was divided into two segments where we first integrated \u2013 and second, used the Snapdragon SDK for object detection on images. This article helps to understand the complexity of Snapdragon SDK and learn how to convert an output tensor to drawable bounding boxes with Kotlin.<\/p>\n

The following image shows the Snapdragon\u00a0training pipeline for providing the required .dlc files (see [1]). This .dlc file contains the trained model based on the Pascal data set<\/a>\u00a0and needs to be added to the Android project.<\/p>\n

\"depiction
Image [1]: Training pipeline<\/figcaption><\/figure>The underlying story of the tech spike has been:<\/p>\n

\u201cAs a user, I want to detect a cat on an image with an Android app, in order to classify the cat\u201c.<\/p>\n

We did start with a simple Android test app, which loaded a data test set of images and integrated the Snapdragon SDK. The test app should simply get images and detect a cat on it (see [2]).<\/p>\n

\"pictures
Image [2]: Use Case<\/figcaption><\/figure>Therefore we began with a simple app with an instrumented test that loads an image and a trained model. As the spike demands we are supposed to use the Snapdragon SDK. The Snapdragon provides a neural network, which can be fed with an input tensor. In our case, this input tensor is a converted image. Afterward, we can interpret the neural network output tensor, as soon as the neural network responded.<\/p>\n

From here on we are able to integrate the conversion algorithm. Before we go deeper into the algorithm it is recommended to take a moment and refresh some terminology.\u00a0Since the manual conversion of a neural network output tensor requires a specific knowledge of the used terminology, it is recommended to read through the following short glossary:<\/p>\n

Definitions<\/h2>\n

model:<\/p>\n