YOLO Detection on Grayscale Images
22 views (last 30 days)
I am trying to detect objects in the grayscale images, but I get the following error.
"The input image channel size (1) must be the same as the network's input channel size (3)."
Per documentation, it says the network accpets single channel as well, but what could be the reason for the error?
Sunil Patidar on 10 Nov 2020
It seems to be an issue with the 'trainYOLOV2ObjectDetector' function not being able to accept images that are of size [M x N x 1]. As a workaround you might need to duplicate your grayscale image across all three channels, and use a network that accepts [M x N x 3] sized matrices.