hi
Object detection with yolov5 trained tflite model is not working with NNStreamer 2.2.0-r0. With previous NNStreamer version-2.1.1, I used to get detection boxes while the current versions displays label for the frames. Pipeline on IMX8MPlus:
USE_GPU_INFERENCE=0 gst-launch-1.0 v4l2src device=/dev/video4 ! video/x-raw,width=640,height=480 ! tee name=t t. ! queue max-size-buffers=2 leaky=2 ! imxvideoconvert_g2d ! video/x-raw,width=320,height=320,format=RGBA ! videoconvert ! video/x-raw,format=RGB ! tensor_converter ! tensor_filter framework=tensorflow2-lite model=./my_model-int8.tflite accelerator=true:npu custom=Delegate:External,ExtDelegateLib:/usr/lib/libvx_delegate.so ! other/tensors,num_tensors=1,types=uint8,dimensions=15:6300:1:1,format=static ! tensor_transform mode=arithmetic option=typecast:float32,add:-4.0,mul:0.003975629806518555 ! tensor_decoder mode=bounding_boxes option1=yolov5 option2=./my_model_labels.txt option3=0 option4=640:480 option5=320:320 ! video/x-raw,width=640,height=480,format=RGBA ! mix. t. ! queue max-size-buffers=2 ! imxcompositor_g2d name=mix sink_0::zorder=2 sink_1::zorder=1 ! autovideosink
