5 Replies Latest reply on Apr 8, 2021 7:25 PM by jomoenginer

    ssd_inception_v2 model and tensorflow on Ultra96v2 (petalinux 2020.2, Vitis AI-1.3)



         I am facing the following problems:


      1. When I try to run the tfssd application provided in V1.3 sample for Ultra96V2 board by the below link

      "https://www.hackster.io/AlbertaBeef/vitis-ai-1-3-flow-for-avnet-vitis-platforms-cd0c51 ", i dont get any detection or bounding boxes in either image or video?


      2. I have compiled the ssd_inception_v2 model  and trying to build python application for object detection using this model, something similar to the face detection application developed by Mario
      "https://www.hackster.io/AlbertaBeef/face-detection-and-tracking-in-python-on-ultra96-v2-02d104 "

      The problem is model-zoo template uses tensorflow for pre and post-processing, while tensorflow is not available on Ultra96V2 petalinux image (petalinux 2020.2, Vitis AI 1.3)


      3. Can I install tensorflow on Ultra96V2?


      Any help or suggestions for achieving this.