Leucorrhea cell detection method integrating double-flow weighted network and space attention mechanism

The invention discloses a leucorrhea cell detection method integrating a double-flow weighted network and a space attention mechanism, relates to the field of medical image processing, and mainly solves the problem of false detection or missing detection caused by subjective factors of doctors in the field of traditional leucorrhea cell detection by improving a yolov5 model. Comprising the following steps: firstly, carrying out Mosaic data enhancement on a leucorrhea cell image, and carrying out class label smoothing on a data set; extracting features of the image by using a backbone network combining a residual idea and a CSPNet idea (cross-stage local network); after the image features are extracted, using a top-up and bottom-down double-flow weighting network to reinforce the image features; sending the image features into a detection network, fusing a space attention mechanism, detecting the leucorrhea cell image, and generating a bounding box and a category to which the bounding box belongs so as to impr