Abstract: A knowledge distillation method for compressing an image segmentation model that is performed in a computing device including one or more processors and a memory storing one or more programs executed by the one or more processors includes training a first image segmentation model including a first image encoder, a first image embedding layer, and a first mask decoder, constructing a second image segmentation model including a second image encoder, a second image embedding layer, and a second mask decoder according to preset constraints, and performing knowledge distillation for the second image embedding layer of the second image segmentation model based on the trained first image segmentation model.

Abstract: The present invention relates to an automatic lathe, and more particularly, to an automatic lathe, which is characterized by comprising opposing type tool posts, and constructing a first tool post (13) and a second tool post (14), which are mounted to the automatic lathe, to be opposing type, mounting a fixed tool and a rotary tool to a third tool post (15) and adding a transferring shaft to the third tool post (15), to thereby mount tools to the opposing type first tool post (13) and the second tool post (14), so that a side surface and a front surface of a workpiece can be machined to enable the machining such as drilling, tapping, end-mill machining, inclination hole machining, wheeling, and the like to be carried out simultaneously, thereby reducing a machining cycle time to increase a production efficiency and maximize a machining efficiency.