Wrinkle detection model training method, electronic equipment and storage medium

The embodiment of the invention relates to the technical field of target detection, in particular to a wrinkle detection model training method, electronic equipment and a storage medium, the method obtains an initial wrinkle detection model through pre-training, training is performed on the basis of the initial wrinkle detection model, on one hand, subsequent model convergence can be accelerated,and the training efficiency is improved; and on the other hand, on the basis of the initial wrinkle detection model, the loss function is optimized in a weight adjustment mode, so that the problem ofpoor classification effect caused by unequal category and position proportions is solved, and the trained wrinkle detection model can quickly, accurately and directly classify and position wrinkles. 本发明实施例涉及目标检测技术领域，尤其涉及一种训练皱纹检测模型的方法、电子设备及存储介质，该方法通过预训练获取初始皱纹检测模型，在初始皱纹检测模型的基础上进行训练，一方面，可以加快后续模型收敛，提高训练效率，另一方面，在初始皱纹检测模型的基础上，以调整权重的方式优化损失函数，以解决因类别和位置比例不均等带来的分类效果差的问题，从而，使得训练出的皱纹检测模型能快速准确地直接对皱纹进行分类及定位。