I wanted to modify the processing of the images to see the effect in processing speed or memory requirements.
I started by removing the cv2.IMREAD_GRAYSCALE flag. I expected each image record to be bigger but not the number of items to triple.
When making the fit call I see it report that it has 73500 training samples instead of 24500. I suspect that I would need to change the definition of variable X but I do not know how. Am I guessing right? If that is the case how would I need to redefine X and Y so each sample is made of 3 colors instead of 1.
Thanks,
You must be logged in to post. Please login or register an account.