Changes between Version 7 and Version 8 of venice/npu


Ignore:
Timestamp:
08/09/2024 07:29:45 PM (8 months ago)
Author:
Blake Stewart
Comment:

Updated benchmark data to show mobilenet

Legend:

Unmodified
Added
Removed
Modified

  • venice/npu

    v7 v8  
    77The NPU operatines up to 2.25 TOPS. Out of the box, this makes Gateworks boards with NPU capabilities powerful for AI applications on the edge.
    88
    9 [[Image(https://trac.gateworks.com/raw-attachment/wiki/venice/npu/gw74xx_npu_benchmark.png)]]
     9[[Image(https://trac.gateworks.com/raw-attachment/wiki/venice/npu/gw74xx_npu_benchmark_new.png)]]
    1010
    1111The easiest way to get started with the NPU is to use a image from the NXP BSP. This image contains the necessary libraries and kernel to interface the NPU with TensorFlow without much configuration. You can either [[https://www.nxp.com/docs/en/user-guide/IMX_YOCTO_PROJECT_USERS_GUIDE.pdf | follow the guide to build their image]] or [[https://www.nxp.com/design/design-center/software/embedded-software/i-mx-software/embedded-linux-for-i-mx-applications-processors:IMXLINUX | download a pre-built one]] (recommended).
    … …  
    184184This data is derived from {{{classifications/sec = 1/(image classification time)}}}
    185185
    186 [[Image(https://trac.gateworks.com/raw-attachment/wiki/venice/npu/gw74xx_npu_benchmark.png)]]
     186[[Image(https://trac.gateworks.com/raw-attachment/wiki/venice/npu/gw74xx_npu_benchmark_new.png)]]
    187187
    188188=== GStreamer Example for Detection