As one of the core applications of computer vision, object detection has become more important in scenarios requiring high accuracy, but limited computational resources, such as robotics and autonomous vehicles. It is important to note that real-world applications of object detection such as pick-and-place solutions are typically run on a variety of platforms such as embedded system. In this paper, we propose an accurate and efficient object detector using Tensorflow Lite for a pick-and-place application that is able to adapt to a wide range of resource constraints.