• State TI Thinks Resolved
  • Locked Locked
  • Replies 1 reply
  • Answers 1 answer
  • Subscribers 98 subscribers
  • Views 172 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: Neural model reshaping during inference

Danil Stepin
Prodigy 60 points

Part Number: TDA4VM

Hi!

Does TIDL support input reshaping through "black box"?

For example:

I have nn model with input {1, 3, 480, 640}. It is a detection model which has been trained to detect objects with area WxH pixels.

If I provide image with other W/H - does inferer reshape input for basic W/H? If it is possible - how to set it?