In this demo, we present a CNN-based dish detection and calorie estimation system, DeepCalorieCam, running on iOS. The proposed app can estimate the calorie after detecting dishes from the video stream captured from the built-in camera of an iPhone. For dish detection, we implemented the network proposed as a real-time object detection network called YOLOv2 by Redmon et al. For food calorie estimation, we implemented the multi-task CNN proposed as a simultaneous estimation of food categories and calories by Ege et al. For the deep learning framework, we use Keras (backend TensorFlow) to train and convert the model for CoreML to use it. For more information, please refer to the following project page.