A short tutorial segment explaining image convolution: a filter (kernel) is slid over an image, and for each pixel the new value is computed by multiplying the pixel and its neighbors with corresponding filter weights (example uses a 3x3 filter). The excerpt frames convolution as a basic image-processing operation commonly used in TensorFlow-style workflows.
So what's convolution, you might ask. Well, if you've ever done any kind of image processing, it usually involves having a filter and passing that filter over the image in order to change the underlying image. The process works a little bit like this. For every pixel, take its value and take a look at the value of its neighbors. If our filter is three by three, then we can take a look at the immediate neighbor so that you have a corresponding three by three grid. Then, to get the new value for the pixel, we simply multiply each neighbor by the corresponding value in the filter. So, for example.
