Why do you cut "post-processing" in YoloX?

I saw the first guide of translation for YOLOX here Translation procedure for YOLOX - Renesas-wiki - Renesas Confluence

I also saw the second guide for YOLOX here rzv_drp-ai_tvm/how-to/sample_app_v2h/app_yolox_cam at main · renesas-rz/rzv_drp-ai_tvm · GitHub

I have some questions.

1. Does the above first guide is used for the second guide? 

2. In the second guide rzv_drp-ai_tvm/how-to/sample_app_v2h/app_yolox_cam at main · renesas-rz/rzv_drp-ai_tvm · GitHub you give use yolox_VOC.onnx here https://github.com/renesas-rz/rzv_drp-ai_tvm/blob/main/how-to/sample_app_v2h/app_yolox_cam/yolox-S_VOC.onnx (as my understanding, it is the original model) but I saw that when translating model you use the model YoloX-S_VOC_sparse70.onnx. Could you share the model  YoloX-S_VOC_sparse70.onnx please?

$TRANSLATOR/../onnx_models/YoloX-S_VOC_sparse70.onnx \
 -o yolox_cam \
 -t $SDK \
 -d $TRANSLATOR \
 -c $QUANTIZER \
 -s 1,3,640,640 \
 --images $TRANSLATOR/../GettingStarted/tutorials/calibrate_sample/ \
 -v 100

3. In the first guide. Why do you split (Reshape > Concat > Transpose) for original model? I can not catch up your idea. We can keep the original as one block to reduce complexity

4. I know that YOLOX need further processing - Non-max suppression. As my understanding, this part
(Reshape > Concat > Transpose) and Non-max suppression is implemented in .cpp files.
Is that right?
Parents Reply Children
No Data