Deep learning defect detection system applied to completion acceptance of power distribution network

The invention provides a deep learning defect detection system applied to completion acceptance of a power distribution network, which comprises a model training module, a synchronous transmission module, an edge detection module and a display report module, and is characterized in that the model training module is used for training a large-scale model and a lightweight model to improve the detection effect of the lightweight model; the synchronous transmission module is used for transmitting lightweight model data to the edge detection module and transmitting a detection result of the edge detection module to the display report module, and the edge detection module detects power equipment in real time based on an edge box. The report display module is used for displaying a detection result of the edge detection module; the system can realize defect identification of distribution network power equipment with wide types at an edge end, and can quickly feed back a detection result on site, so that implementatio