• State TI Thinks Resolved
  • Locked Locked
  • Replies 1 reply
  • Answers 1 answer
  • Subscribers 97 subscribers
  • Views 358 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:

TDA2: Usecase inputdata file(inData_OD) and usecase input header file(inHeader_OD) for object detection(Vision SDK_03.03...

TDA2: NEW CNN MODEL SUPPORT

user1916368
Intellectual 560 points
Part Number: TDA2

Hi， dear

             Could tda2x support the open-pose( you can google to find which is a kind of cnn model for pose recognition) demo？  If not， when to support it？ Or any idea for me to improve the current vision TIDL to support the pose model recognition?

 

              Looking forward to your best reply!

             Tks!

  • 0
    TI__Genius 17580 points
    Hi,

    Please refer to TIDL data sheet (TIDeepLearningLibrary_DataSheet.pdf) for supported layers by TIDL.
    If the open pose CNN model has only layers supported TIDL then tda2x can support this model, and we don't have any plans to add new layers for TIDL.

    Thanks,
    Praveen