1

I am trying to replicate the working of TFLITE_DETECTION_POSTPROCESS layer for a custom object detection model.

Does anyone has any reference for TFLITE_DETECTION_POSTPROCESS layer implementation in python?

I have this file detection_postprocess as reference from tensorflow repository, but it is hard to understand this without running.

Any comparable resource will be of great help. Thanks :)

Improve this question
1
  • To replicate the TFLITE_DETECTION_POSTPROCESS layer for an SSD model, you must implement SSD Box Decoding (Center-Size format with standard scale factors like 10.0 and 5.0) and then apply multi-class Non-Maximum Suppression (NMS) to the resulting absolute box coordinates and scores. Commented Nov 25 at 4:54
Related questions
1
Tensorflow2 Object Detection Counting API for tutorial
0
Error Android Object Detection App with model from tflite Model-maker
1
Tensorflow Object Detection Performance Drop in Android
Load 7 more related questions Show fewer related questions

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.