The research purpose of this dissertation is to develop a deep learning based automated inspection and classification system for workpiece shape using single-board computer Raspberry Pi, which is used to control conveyor and robotic arm for real-time object detection. First, the images of all workpiece shapes to be classified are made into training samples, and the image classifier based on deep learning is used for training. After completion, the model parameters can be obtained. Secondly, carry out experimental tests. The conveying device controlled by the Raspberry Pi sends the workpiece to the inspection position. This classifier can display the classification results of the workpiece shape in real time. Finally, the Raspberry Pi controls the robotic arm to classify the workpieces, clamp them to the set position, and deliver the workpieces to the destination by the conveying equipment. Through statistics and analysis of experimental data, the classification accuracy rate of the system developed in this dissertation can reach 95%.