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.