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: custom model compilation using TIDL tools failure

Part Number: TDA4VM

Tool/software:

Hello, I'm trying to compile custom models using TIDL tools.

I downloaded and set up TIDL tools ver 8.6 using docker setup on x86 linux pc.

I want to compile models unzipped by face_landmarks.task from google mediapipe.(you can get face_landmarks.task from https://ai.google.dev/edge/mediapipe/solutions/vision/face_landmarker)

The models are face_detector.tflite and face_landmarks_detector.tflite.

I got "segmentation fault (core dumped)" message when importing the dequantization layer.

Is there any solution or do i need to modify my models?

If i need to modify my models, how can modify tflite models directly? (because of I cannot get the model which is not converted to tflite)

Thank you.