set values to 0. or 1.
hi, in line 84 you wrote as comment:
set the pixels to all be 0. or 1.
but with the following code
cv2.threshold(screen_resized_grayscaled, 1, 255, cv2.THRESH_BINARY)
you set them to 0 or 255. So the input data is not normalized, or? So , if you mostly pipe in zeros, wouldnt then the neurons not all get also zero ? x*W+b ?
https://github.com/DanielSlater/PyGamePlayer/blob/master/examples/deep_q_pong_player.py#L84
Hi Flo, sorry yes the comment is wrong the values will be all 0. or 255. If fact I should probably change the threshold be 0. to 1. I think that may work better... I will need to investigate a little.
Sending most of the neurons input values of 0 is in itself not a problem. If that is what the input it is, that is what it is.