Changes between Version 2 and Version 3 of TPU


Ignore:
Timestamp:
06/18/2020 11:49:02 PM (2 years ago)
Author:
Cale Collins
Comment:

fixed bad spelling

Legend:

Unmodified
Added
Removed
Modified
  • TPU

    v2 v3  
    33The Coral Edge TPU provides a means to perform advanced machine learning tasks in a low power, small form factor package.  This hardware is based on an application specific IC (ASIC) tailored for hardware accelerated AI calculations. 
    44
    5 This TPU is appropreate for an application where identifying an object or pattern is required.  This could be, but is not limited to:
     5This TPU is appropriate for an application where identifying an object or pattern is required.  This could be, but is not limited to:
    66* Object detection
    77* Pose or gesture estimation
     
    1313* Robots
    1414* Voice control/Language Processing
    15 * Monitering devices
    16 
    17 Nearly all industries can benifit from this technology. To name a few more specifically:
     15* Monitoring devices
     16
     17Nearly all industries can benefit from this technology. To name a few more specifically:
    1818* Health Care
    1919* Agrictuture
     
    2323* Automated Kiosk
    2424
    25 For more information about the hardware see these refrences:
     25For more information about the hardware see these references:
    2626* https://coral.ai
    2727* https://en.wikipedia.org/wiki/Tensor_processing_unit
     
    4040== Compiling the kernel
    4141
    42 The Gateworks kernel defconfig for Newport does not include support for video devices.  For the sake of convenience a pre-built image is avaiable for download.  If you would like to create a similar image manually:
     42The Gateworks kernel defconfig for Newport does not include support for video devices.  For the sake of convenience a pre-built image is available for download.  If you would like to create a similar image manually:
    4343
    4444* Acquire the [wiki:/newport/bsp Newport BSP], we will call the directory this repo has been sync'ed to the <BSP> directory. 
    4545* Follow the steps [wiki:/newport/bsp#Modifyingthestand-aloneLinuxKernelieforUbuntu here] to modify the kernel and create and Ubuntu image.
    4646 * In the menuconfig enable the module "USB_VIDEO_CLASS", this will allow you to use a USB webcam with v4l-utils. 
    47  * Complete the procedure detailed in the aformentioned section, build your Bionic image and [wiki:/newport/firmware#UpdateFirmwareviaSerialConsoleandEthernetfromBootloader flash it to your SBC]
     47 * Complete the procedure detailed in the aforementioned section, build your Bionic image and [wiki:/newport/firmware#UpdateFirmwareviaSerialConsoleandEthernetfromBootloader flash it to your SBC]
    4848
    4949== Building and installing the Gasket and Apex modules
     
    5252The source code for the modules can be downloaded here as a tar.gz file:
    5353* https://coral.googlesource.com/linux-imx/+/refs/heads/release-day/drivers/staging/gasket
    54  * Extract this tar into a directory, this dir will be refered to as <the_module_directory>.
     54 * Extract this tar into a directory, this dir will be referred to as <the_module_directory>.
    5555Build the source using the same method as you would for an out of tree module (out of tree = when the module source is not included in the kernel source).
    5656* cd to the <BSP> directory.
     
    7575make -C <BSP>/linux M=$PWD
    7676}}}
    77 This procedure will result in two modueles being created, "apex.ko" and "gasket.ko".  Copy the .ko files to your target board "/lib/modules/<kernel_version>/extra/" folder.  Using SCP may be the simplest way to go about this.
     77This procedure will result in two modules being created, "apex.ko" and "gasket.ko".  Copy the .ko files to your target board "/lib/modules/<kernel_version>/extra/" folder.  Using SCP may be the simplest way to go about this.
    7878
    7979With the modules copied to the board execute the following commands:
     
    8989On reboot verify that "/dev/apex_0" device is present.
    9090
    91 == Installing and configureing Python
     91== Installing and configuring Python
    9292
    9393Python 3.7 is required to run the tenser flow examples.  Other versions can be used, though at the time of writing this wiki 3.7 is the best option when using the Bionic Ubuntu for Newport BSP.
     
    134134}}}
    135135
    136 ***Note:*** If you have chosen not to use Python 3.7 you can find the .whl appropreate for your version here https://www.tensorflow.org/lite/guide/python
     136***Note:*** If you have chosen not to use Python 3.7 you can find the .whl appropriate for your version here https://www.tensorflow.org/lite/guide/python
    137137
    138138Acquire necessary libraries to build the TFlite runtime
     
    149149
    150150
    151 == Download classifcation example, test an infrencing operation
     151== Download Classification example, test an inference operation
    152152
    153153Create a place for the Coral examples to reside.
     
    186186git clone https://github.com/google-coral/examples-camera.git --depth 1
    187187}}}
    188 Download models.  Models are the information that will be feed to the TPU for it to refrence when identifying an object.
     188Download models.  Models are the information that will be feed to the TPU for it to reference when identifying an object.
    189189{{{#!bash
    190190cd examples-camera
     
    196196bash install_requirements.sh
    197197}}}
    198 Adaptations to the existing gstreamer.py will be required for this example to work.  Amodified script is available to download from [http://dev.gateworks.com/fae/gstreamer.py here].
     198Adaptations to the existing gstreamer.py will be required for this example to work.  A modified script is available to download from [http://dev.gateworks.com/fae/gstreamer.py here].
    199199Edit this file line 231 with the IP address of the desktop workstation you will be streaming to.
    200200This is what the edited line will look like.