The invention discloses a cell classification method and system based on a deep residual network. The method includes: acquiring a data set of cell images, wherein the data set includes a first data set and a second data set; using the deep residual network for training on the first data set, and transferring the trained network to the second data set to carry out training to obtain a target network; and inputting a to-be-classified cell image into the target network to obtain a feature map, analyzing the feature map, and outputting a classification result of the cell image. According to the method, the residual network is utilized for training on the data set, a method of transfer learning is combined, a network structure which can carry out automatic classification is created, the problem that biomedical image data sets are smaller is effectively solved, occurrence of over-fitting cases is avoided, workloads are reduced, work efficiency is improved, and a correctness rate of automatic cell classification is also effectively improved.