At present,China mainly relies on manu al sorting of garbage,which ha s problems such as low safety factor and low efficiency.Traditional target detection methods are difficult to design features for a wide variety of garbage targets with different shapes,and have poor robustness.In order to ach ieve rapid and accurate garbage identification in natural environments,this paper proposes a lightweight garbag e classification and detection method based on deep learning.This method improves the accuracy of the regress ion frame by introducing the CIOU frame regression loss function;for the deployment of low-power mobile dev ice terminals,a YOLOv3target detection algorithm is proposed based on the feature extraction network of Mobil eNetV3to lighten the algorithm; The GRU structure is added to the YOLO layer,and the multi-gated recurrent neu ral network structure is used to establish memory links for feature maps of different sizes in the YOLO layer,an d to filter and screen the forward fusion process of deep semantic features to make the feature fusion effect bette r; use Transfer learning pre-training is used to improve the feature extraction ability and generalization ability of the model.The text uses the self-made Garbage data set to train and test the improved network.The results show that t he algorithm proposed in this paper has a significant recognition effect,with an average accuracy rate of 90.50%,w hich is higher than the original YOLOv3network′s average accuracy rate of 86.30%,and the detection speed is up to 18frames per second, meeting the needs of real-time detection.Experiments show that the improved ne twork model can effectively reduce the amount of model parameters while ensuring the detection accuracy and speed,which has certain application value.