Hi everyone,
I am working on implementation of YOLOv4 object detector in LabVIEW 2019 (64-bit) through Deep Learning VIs using Tensorflow .pb Frozen Model. I was able to determine the Output Node Names for the frozen model of YOLOv4 according to the Python script attached below. There is, however, 9903 output nodes printed when running the code, while I am only interested in the class names, detection confidence and bounding boxes coordinates. DL Model Run VI requires Output Node Names as its input wire.
Is there a way how can I reduce the number of output nodes from 9903 to 3 (class names, detection confidence and bounding boxes coordinates) so it can be used in the LabVIEW Deep Learning VI?
Thank you.
