Open AronHegedues opened 4 years ago
I believe you need to change the input shape of the blob in lib/pine.py I don't know the dimensions required for Yolov3
In original code in the conversion of the image input into a blob to feed the model
the width and height are 150x150:
blob = cv2.dnn.blobFromImage(frame, 1 / 260, (150, 150),swapRB=False, crop=False)
net.setInput(blob)
layerOutputs = net.forward(ln)
But in most yolov3 models the input size supposed to be a multiple of 32 so try changing it to 160x160 like that
blob = cv2.dnn.blobFromImage(frame, 1 / 260, (160, 160),swapRB=False, crop=False)
I'm trying to use Yolov3 instead of Yolov3-tiny. I downloaded the yolov3.cfg and the yolov3.weights from https://github.com/AlexeyAB/darknet and changed the weights and the config Path
But I get this Traceback:
I would be very happy if someone could suggest a solution.