Given an input image of 128x128, and output 29x29. What is the size of the area of the input that is middle pix in output

253 Views Asked by At

Given an input image of 128x128, after putting it through a convolutional neural network the output is 29x29. What is the size of the area (in pixels) of the input that correspond to the middle pixel in the output?

I was thinking it had to do with 128/29 = 4.4. Each pixel in the output corresponds to 4 pixels in the input but that doesn't get me near the right answer.

Thank you!