• State
  • Locked Locked
  • Replies 1 reply
  • Subscribers 97 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.

TDA4VM: Performance issues with the maxpool operator

LIU Xiaoyang
Prodigy 70 points
Part Number: TDA4VM

Maxpool operator: The Maxpool operator is used in yolov4 and yolov5, and the kernel size of the operator is 1x1, 5x5, 9x9 and 13x13, but the maximum kernel size described in the official website document is 3X3, so how to adjust this operator's kernel size ?

  • 0
    TI__Genius 17580 points

    Hi,

    This thread also falls in the same category of your other threads, so same response applies here,

    We do support operators beyond the supported on C7x (list) on ARM with our open source run time offering (TFLite, ONNX RT and TVM DLR).

    For most of the open source exchange formats such as Tensorflow, ONNX, tflite, etc., you can use our RT offering and get such operators executed on ARM.

    Thanks,

    Praveen