We present a novel method of CNN inference for a new pixel processor array, implementing a hand-written digit(digits 0-9) classification network with all steps of the process performed on the focal plane itself. The processor array that we deploy (SCAMP-7) has a 256x256 array of processor elements (PE) on a 32x32um pitch. The algorithm runs at over 3000 frames per second (FPS) and over 90% classification accuracy.