Since the deep learning methods used in current face recognition do not balance well between recognition rate and recognition speed, the present work proposed a face expression recognition model based on multilayer feature fusion with lightweight convolutional networks. The model is tested on two commonly used real expression datasets, FER- 2013 and AffectNet, the accuracy of ms_model_M is 74.35% and 56.67%, respectively, and the accuracy of the traditional MovbliNet model is 74.11% and 56.48% in the tests of these two datasets.