
This SDK has been patched by Embedded Artists for the iMXRT1062 Developer's Kit.
The SDK was released on 2022-11-18 and is based on NXP's 2.12.1 SDK (SDK_2_12_1_MIMXRT1062xxxxA.zip).

This is what has been patched:
* Set CPU speed according to Commercial/Industrial CPU
* Correction of the VDD_SOC_IN voltage.
* Flash settings (speed, algorithm, size, driver) to work with the 4MB OctalSPI ATXP032
* LWIP projects - added reading of the MAC address from the onboard I2C EEPROM
* Added an I2C driver for the gpio expander (PCA6416) and code to use it
* Modified pin muxing
* SEMC projects - changed algorithm for memory test and now test entire 32MB instead of only 4KB
* Adjusted the USB interface number for USB Host examples (it is different for host and device examples)
* Added a software_reset() function in board.c/.h to issue a JEDEC reset before NVIC_SystemReset()
* Changed the Wi-Fi examples to use the Embedded Artists 1XK M.2 Module (EAR00385) as default
* Many of the projects have been updated to use a more complete pin_mux.c file where all
  necessary pins have been initialized. The SDK examples used to only configure the pins
  that they use (and often not every pin) and most of the time the configuration was only
  for MUX:ing and not the PAD settings (pull up/down/none, drive strength and slew).
* Embedded Wizard project 'ew_gui_smart_thermostat' was incorrectly setup for EVKB
* Changed the default display to RK043FN02H as it is the one mounted on the Developer's Kits

This has been added:
* New WDOG examples that work
* I2C probe example
* Example to show the use of software_reset()

This has been removed:
* All projects for the EVK - only keeping EVKB which is then patched
* The original WDOG and RTWDOG examples as those were not working

Important things to note:
* Read section "8 - Known Issues" in docs/MCUXpresso SDK Release Notes for EVK-MIMXRT1060.pdf
  to see known issues with the current version of the SDK.
* For Iperf examples, set compiler optimization to -O3 or similar to improve performance.
* If the hardware seems unresponsive and the debugger cannot connect/flash/erase the current program
  then the most likely cause is the running program preventing the access. To stop the currently
  running program and regain control:
  1) Press and hold down the ISP_ENABLE button (SW1)
  2) Press and hold down the RESET button (SW3)
  3) Let go of the RESET button
  4) Wait an extra second or two
  5) Release the ISP_ENABLE button
  6) The hardware is now in a mode where programming/erasing it should work

Connectors:
* J22 (micro USB) is the default UART and unless specified otherwise it is setup for 115200 8/N/1


!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
THIS PROJECT IS NOT DIRECTLY COMPATIBLE WITH THE HARDWARE AND WILL NOT WORK.

This project uses too much FLASH, i.e. above 4Mb. Building the release target
does not help.
!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!



Everything below this line is the original content of the readme file.
=======================================================================



DeepViewRT image detection example

Content
-------
1. Introduction
2. Directory structure
3. eIQ inference with DeepView RT Example
4. Documentation
5. Library configuration
6. Release notes
7. Limitations
8. Application execution

1. Introduction
---------------
This "Image Detection" example shows the demonstration of using DeepViewRT API to do image detection
on an IMXRT platform. The application could identify multiple objects in a single image and outputs
the result via UART console. The result is including detected object name and bounding box array.

2. Directory structure
--------------------------------------
<MCUXpresso-SDK-root>
|-- boards
|   -- <board>
|      -- eiq_examples                         - Example build projects
|         -- deepviewrt_image_detection        - Identify multiple objects in a single image.
|
|-- middleware
    -- eiq
       -- deepviewrt
          -- include                   - DeepviewRT library header files
          -- lib                       - DeepviewRT library binaries

3. eIQ Inference with DeepView RT example
-----------------------------------------
3.1 Introduction
    The package contains modelrunner example applications using
    the DeepView RT library. The build projects can be found in
    the /boards/<board>/eiq_examples/deepviewrt* folders.

3.2 Toolchains supported
    - MCUXpresso IDE
    - IAR Embedded Workbench for ARM
    - Keil uVision MDK
    - ArmGCC - GNU Tools ARM Embedded

3.3 Supported board and settings
    - evkmimxrt1170:
      No special settings are required.
    - evkmimxrt1060:
      No special settings are required.
    - evkbimxrt1050:
      No special settings are required.
    - evkmimxrt1160:
      No special settings are required.

4. Documentation
----------------
    https://www.nxp.com/design/software/development-software/eiq-ml-development-environment:EIQ

5. Library configuration
------------------------
5.1. Stack memory configuration
     During the library compilation, based on the stack memory configuration,
     the EIGEN_STACK_ALLOCATION_LIMIT macro definition can be set to the maximum
     size of temporary objects that can be allocated on the stack
     (they will be dynamically allocated instead). A high number may cause stack
     overflow. A low number may decrease object allocation performance.

6. Release notes
----------------
DeepView RT supports only a subset of operators available in TensorFlow.
The eIQ toolkit can convert Tensorflow model to RTM model, please refer to
eIQ toolkit about model conversion.

7. Limitations
--------------
* N/A

8. Application execution
------------------------------

Prepare the Demo
================
1.  Connect a USB cable between the PC host and the OpenSDA(or USB to Serial) USB port on the target board.
2.  Open a serial terminal on PC for OpenSDA serial(or USB to Serial) device with these settings:
    - 115200 baud rate
    - 8 data bits
    - No parity
    - One stop bit
    - No flow control
3.  Insert the Ethernet Cable into the target board's RJ45 port and connect it to a router (or other DHCP server capable device).
4.  Download the program to the target board.
5.  Either press the reset button on your board or launch the debugger in your IDE to begin running the demo.

Running the demo
================
The log below shows the output of the demo in the terminal window (compiled with MCUX):

begin post-processing
         Class ID = [1][person]
:        Class ID = [2][bicycle]
[...]
:        Class ID = [16][bird]
:        Class ID = [17][cat]
:        Class ID = [18][dog]
:        Class ID = [19][horse]
                Predicted bounding box[0]: 0.316 0.061 0.900 0.408 (0.966182)
                Predicted bounding box[1]: 0.070 0.323 0.890 0.657 (0.909269)
                Predicted bounding box[2]: 0.475 0.628 0.798 0.845 (0.812548)
                Predicted bounding box[3]: 0.468 0.837 0.821 0.998 (0.778532)
         Class ID = [20][sheep]
:        Class ID = [21][cow]
:        Class ID = [24][zebra]
[...]
:        Class ID = [90][toothbrush]
: decode img takes 54000 us, inference takes 2378000 us


