Foods are important things to human beings, especially for elderly and diabetics. Tradition nutrition book is not the
effective way for people to use and not cover all kind of foods. Most of the food nutrition in the book focused on Western dishes
not Asian dishes. This research proposed the new way to categorized food dishes and estimate nutritional value using
convolutional neural networks. These networks are transferred in to RaspberryPi 3B platform to simulate limited resources and
calculation power platform likes in a mobile phone. The image of food is captured by the webcam and it is sent to Raspberrypi
3B where CNNs categorize the food dishes and estimate the nutrition value. In this we also used LEDs and slide switches where
switches enable the device to know whether the human is diabetic or not and LED enable the human to take sufficient amount of
food. The networks in Raspberry Pi 3B produce good prediction accuracy but slow speed. PeachPy is introduced to speed up the
network and it can run at 3.3
