The invention discloses a power transmission line target defect identification and intelligent diagnosis method based on an SSD neural network, and belongs to the technical field of power transmissionline faults. The method comprises the steps of obtaining and preprocessing data parameters; constructing a convolutional neural network model based on the feature pyramid by using a multi-scale detection structure; compressing the neural network model by combining network deletion with parameter sharing; testing and evaluating the acquired data through the compressed neural network model; and obtaining an electric line target defect identification and diagnosis result. According to the technical scheme provided by the embodiment of the invention, the neural network model is constructed and trained for accurately identifying various defects of the power transmission line, and meanwhile, intelligent diagnosis and spatial positioning of coarse-grained defects and fine-grained defects are realized based on a heterogeneous high-performance hardware architecture of the FPGA.