Hi, I used the Faster-RCNN model to train the PyTorch model. Conversion to onnx works fine and the model works, but I have dynamic_axes. And hailomz parse doesn’t want to work with this model. I created a yaml file for fasterrcnn_resnet50_fpn, but I am not sure if the configurations are correct. …

Hey @Bogdan_Boryslavskyi , You are correct , I just checked it , you have to export the ONNX with static input shapes and no dynamic axes. That’s the only way Hailo’s ONNX parser will work without throwing the [0,3,0,0] shape error.

Can not parse my onnx model which trained used Faster-RCNN

General

Bogdan_Boryslavskyi April 9, 2025, 10:16am 5

Yes, thanks. I retrain the model with yolo, and it is working now.

Topic		Replies	Views
Onnx to Har parsing error General hailo8 , error	2	448	March 9, 2025
Dataflow compiler (3.28.0) fails to parse fine-tuned yolov10n ONNX model General dfc , raspberry-pi	2	328	July 21, 2024
Parsing ONNX to HAR problem General hailo8	2	350	November 12, 2024
Can not parse yolov8n-pose model General	1	258	August 15, 2024
Convert custom onnx model to har file General dfc , raspberry-pi , hailo8	2	467	September 27, 2024

Can not parse my onnx model which trained used Faster-RCNN

Related topics