Example applications
The eIQ TensorFlow Lite library is provided with a set of example applications. For details, see Table 1. The applications demonstrate the usage of the library in several use cases.
Name |
Description |
Availability |
---|---|---|
|
CIFAR-10 classification of 32 × 32 RGB pixel images into 10 categories using a small Convolutional Neural Network (CNN). |
MCX-N947-EVK (no camera and display support) |
|
Keyword spotting application using a neural network for word detection in pre-processed audio input. |
MCX-N947-EVK (no audio support) |
|
Image recognition application using a MobileNet model architecture to classify 128 × 128 RGB pixel images into 1000 categorieswith eIQ Neutron NPU. |
MCX-N947-EVK (no camera and display support) |
|
Image recognition application using a MobileNet model architecture to classify 224 × 224 RGB pixel images into 1000 categorieswith eIQ Neutron NPU. |
MIMXRT700-EVK (no camera and display support) |
|
CIFAR-10 classification of 32 × 32 RGBpixel images into 10 categories using a small Convolutional Neural Network. |
MIMXRT700-EVK (no camera and display support) |
|
Image recognition application using a MobileNet model architecture to classify 128 × 128 RGB pixel images into 1000 categories. |
MIMXRT700-EVK (no camera and display support) |
For details on how to build and run the example applications with supported toolchains, see Getting Started with MCUXpresso SDK User’s Guide (document: MCUXSDKGSUG). When using MCUXpresso IDE, the example applications can be imported through the SDK Import Wizard as shown in Figure 1.
|
|
After building the example application and downloading it to the target, the execution stops in the main function. When the execution resumes, an output message displays on the connected terminal. For example, Figure 2 shows the output of the tflm_label_image_cm7``tflm_label_image
example application printed to the MCUXpresso IDE Console window when semihosting debug console is selected in the SDK Import Wizard.
|
|