For the robot intelligent manufacturing workshop, the intelligent detection of workpiece products is the basis for efficient management and precision detection of production lines, which is of great significance for the reliable operation of intelligent manufacturing unmanned production lines. Therefore, SSD algorithm and migration learning in deep learning is studied to sorting the workpieces in this paper. Firstly, based on the five workpieces of screw, nut, gasket, spring, and gear, the multi-workpiece detection data set of the intelligent production line is constructed. Secondly, the multi-scale features of different workpieces are extracted by deep convolution network SSD. Then, the migration learning method is applied to complete the migration network training of workpiece intelligent detection, so the small data detection accuracy is obtained. Finally, after transfer learning solidifying and pruning the transfer learning training model, It is deployed to the embedded terminal Invidia Jetson Nano to realize the online intelligent detection. The experimental results show that the workpiece detection accuracy reaches 99% based on SSD network migration learning. After the network structure optimization pruning embedded deployment, the workpiece detection accuracy is better than 86%, and the frame rate is more than 7FPS. So the proposed method can realize five kinds of workpieces intelligent detection on unmanned production lines.