• State
  • Locked Locked
  • Replies 1 reply
  • Subscribers 98 subscribers
  • Views 215 views
  • Users 0 members are here
Support feedback
Options
Options
Related

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

Original question:

TDA4VL-Q1: [convert edge ai yolov5 model example fail][tidl_j721s2_08_06_00_10]

TDA4VL-Q1: [prototxt question][detection output parameter]

John Feng
Prodigy 230 points
Part Number: TDA4VL-Q1


I have successfully converted the YOLOv5 model's ONNX file to net.bin and IO.bin files, but I have two questions.

Q1: Why is it "name: yolov3" instead of "name: yolov5" when setting up?

Q2: How to configure the detection_output_param in the prototxt file? How should it be adjusted for non-YOLOv5 models or modifications to the detection layer? Is there any documentation available?

Thanks for answer

  • 0
    TI__Mastermind 24041 points

    Hi,

    This param.yaml file are generated as part of model compilation process.

    I am hardly sure, this are changeable, prototxt files are typically used to map post processing layers of OSRT Models to TIDL, so that end to end support is ensured.

    I will reverify this at my end and get back to you