Create a eIQ (TensorFlow Lite library) demo for i.MX RT6xx

Showing results for 
Show  only  | Search instead for 
Did you mean: 

Create a eIQ (TensorFlow Lite library) demo for i.MX RT6xx

No ratings

Create a eIQ (TensorFlow Lite library) demo for i.MX RT6xx

i.MX RT6xx

The RT6xx is a crossover MCU family is a breakthrough product combining the best of MCU and DSP functionality for ultra-low power secure Machine Learning (ML) / Artificial Intelligence (AI) edge processing, performance-intensive far-field voice and immersive 3D audio playback applications. Fig 1 is the block diagram for the i.MX RT600.
It consists of a Cortex-M33 core that runs up to 300 MHz with 32KB FlexSPI cache and an optional HiFi4 DSP that runs up to 600MHz with 96KB DSP cache and 128KB DSP TCM. It also contains a cryptography engine and DSP/Math accelerator in the PowerQuad co-processor. The device has 4.5MB on-chip SRAM. Key features include the rich audio peripherals, the high-speed USB with PHY and the advanced on-chip security. There is a Flexcomm peripheral that supports the configuration of numerous UARTs, SPI, I2C, I2S, etc.


Fig 1

Create a eIQ (TensorFlow Lite library) demo

In the latest version of SDK for the i.MX RT600, it still doesn't contain the demos about the Machine Learning (ML) / Artificial Intelligence (AI), so it needs the developers to create this kind of demo by themself.
To implement it, port the eIQ demos cross from i.MX RT1050/1060 to i.MX RT685 is the quickest way. The below presents the steps of creating a eIQ (TensorFlow Lite library) demo.

Greate a new C++ project

  • Install SDK library


Fig 2

  • Create a new C++ project using installed SDK Part
    In the MCUXpresso IDE User Guide, Chapter 5 Creating New Projects using installed SDK Part Support presents how to create a new project, please refer to it for details

Porting tensorflow-lite

  • Copy the tensorflow-lite library to the target project
    Copy the TensorFlow-lite library corresponding files to the target project


Fig 3

  • Add the paths for the above files


Fig 4


Fig 5


Fig 6

Porting main code

The main() code is from the post: The “Hello World” of TensorFlow Lite


On the MIMXRT685 EVK Board (Fig 7), we record the input data: x_value and the inferenced output data: y_value via the Serial Port (Fig 8).

2020-04-22_18-00-55.jpgFig 7


Fig 8

In addition, we use Excel to display the received data against our actual values as the below figure shows.


Fig 9

In general, In general, it has replicated the result of the The “Hello World” of TensorFlow Lite


  • In default, the created project doesn't support print float, so it needs to enable this feature by adding below symbols (Fig 10).


Fig 10

  • When a neural network is executed, the results of one layer are fed into subsequent operations and so must be kept around for some time. The lifetimes of these activation layers vary depending on their position in the graph, and the memory size needed for each is controlled by the shape of the array that a layer writes out. These variations mean that it’s necessary to calculate a plan over time to fit all these temporary buffers into as small an area of memory as possible. Currently, this is done when the model is first loaded by the interpreter, so if the area is not big enough, you’ll see a crash event happen.
    Regard to this application demo, the default heap size is 4 KB, obviously, it's not big enough to store the model’s input, output, and intermediate tensors, as the codes will be stuck at hard-fault interrupt function (Fig 11).


Fig 11

So, how large should we allocate the heap area? That’s a good question. Unfortunately, there’s not a simple answer. Different model architectures have different sizes and numbers of input, output, and intermediate tensors, so it’s difficult to know how much memory we’ll need.
The number doesn’t need to be exact—we can reserve more memory than we need—but since microcontrollers have limited RAM, we should keep it as small as possible so there’s space for the rest of our program.
We can do this through trial and error. For this application demo, the code works well after increasing ten times than the previous heap size (Fig 12).


Fig 12

Labels (1)
Tags (1)
Version history
Last update:
‎04-23-2020 03:37 AM
Updated by: