Hello, we have trained successfully a YoloV5 and converted it to uint8.
The benchmark
./benchmark_model --graph=model.tflite --external_delegate_path=/usr/lib/libvx_delegate.so --enable_op_profiling=true
benchmark output :
External delegate path: [/usr/lib/libvx_delegate.so]
Loaded model model.tflite
Vx delegate: allowed_builtin_code set to 0.
Vx delegate: error_during_init set to 0.
Vx delegate: error_during_prepare set to 0.
Vx delegate: error_during_invoke set to 0.
EXTERNAL delegate created.
Going to apply 1 delegates one after another.
Explicitly applied EXTERNAL delegate, and the model graph will be completely executed by the delegate.
The input model file size (MB): 1.98869
Shows inference speed of ~66 ms which is not too bad. The output also shows that the inference is completely executed on the npu.
I started to implement the extraction of the bounding box from the prediction of the input image. I used python for a quick evaluation :
If you haven't resolved your issue yet you might need to open a support ticket.
It took me two different tickets but I finally received a patch from NXP support that I applied to op_map.cc in the vx-delegate. That resolved the issue for us and we can now get good results from the NPU that are very close to the CPU results.
Hi @Zhiming_Liu ,
I did as the document suggested.
As a remark, all the models are quantized with the same images. The models (raw - pb and converted tflite from Ultralytics) are also attached.
Regards
Hello @Zhiming_Liu ,
I reply directly in hope someone would help me fix the problem ;).
I m still having no detection inferencing with the NPU. Only the CPU gives me good detections, even when
I convert them with the eIQ tool you suggested.
Thanks, regards Daniel
Hello @Zhiming_Liu,
thanks for the support.
I attach two models, the pb file as the yolov5 unconverted and the efficientdetlite0 already converted.
Both deliver no results with the NPU, only with the CPU.
It is only a person detector, trained with the persons from COCO17 and a little bit of our data. There are three images and the label.txt.
Thanks again for looking into it.
Daniel