Mixed detection of grape leaf and fruit diseases based on Yolov5s

Aiming at the problem of low degree of automation in the separation of grape disease leaf identification and fruit identification in the cultivation process of grapes, we design a detection program for simultaneous identification of grape disease leaf and fruit. By collecting the disease data of grape leaves and fruits individually or mixed, and transferring the collected pictures to the detection system, YOLOv5s algorithm will automatically recognize the diseases of fruits and leaves in the pictures and feed back the recognized pictures, the training set is 2870 pictures of 7 kinds of diseases. The test set is 711 photos of various diseases. According to the validation test of the test set, the model has an average accuracy of 95.6% for labeling the seven diseases of fruits and leaves respectively, which effectively improves the efficiency of disease recognition in the cultivation process.