Target detection method based on pre-training network and related equipment

The invention relates to the field of artificial intelligence and the field of digital medical treatment, and provides a target detection method based on a pre-training network and related equipment, and the method comprises the steps: obtaining a trained first target detection model which comprises a plurality of pre-training network layers, then each pre-training network layer of the first target detection model is quantized, so that the model parameter of each pre-training network layer in the first target detection model is reduced from the initial precision to the target precision, and the quantized first target detection model is used as a second target detection model; and obtaining a to-be-detected image, and inputting the to-be-detected image into the second target detection model to obtain a prediction result of the to-be-detected image through the second target detection model. According to the embodiment of the invention, under the condition that the target detection precision is ensured, the mode