My question is same as the title.
I follow this sample for RZ/V2L https://github.com/renesas-rz/rzv_ai_sdk/tree/main/R01_object_detection it only provides object object model. I want to reporduce all steps and check model archiecture in this sample. I can generate yolov3.onnx model from other repos but I am not sure it is same as the one in this example.. Could you share yolov3.onnx for this example. Thank you.
Hi AnhOi,My apologies, we cannot provide the requested model.Thank you.Kind Regards.
Hi PT_Renesas
I only want to check the shape of 3 outputs from renesas's yolov3, because I could not find 3 nodes with same shape of YOLOv3 as Renesas mentioned.
In this link https://github.com/renesas-rz/rzv_ai_sdk/tree/main/R01_object_detection you said that
Input size: 1x3x416x416Output1 size: 1x13x13x255Output2 size: 1x26x26x255Output3 size: 1x52x52x255
I follow this repo to convert from darknet to yolov3 https://github.com/zldrobit/onnx_tflite_yolov3 and visualize onnx model by Neutron but I did not see 3 nodes correspond with your above shape.
From my point of view, it is hard for user to follow guideline and customize for other problem. I think that if renesas can not provide model for specific dataset, you can provide general guide to create model (reproduce architecture). I think that it is better for users.
Thank you.