The electromagnetic environment of modern battlefield is becoming more and more complex, and there are many kinds of radar emitter. The traditional radar emitter recognition method in closed set environment has low identification accuracy and poor robustness when applied to open set environment. In order to effectively solve the problem of individual emitter open set identification and improve the accuracy of individual emitter identification, an open set identification method of radar emitter based on EfficientNet-WGANomaly is proposed. Firstly, the Short-Time Fourier Transform (STFT) is used to convert the time-frequency feature of the radar emitter signal, and the one-dimensional signal data is converted into two-dimensional image data. The EfficientNet-WGANomaly model is used to perform feature reconstruction and image reconstruction of the converted time-frequency feature. Since the feature and image of unknown signals change greatly after reconstruction, the known signals and unknown signals are screened by using the reconstruction difference of the two parts, and the known signals are classified and identified. Simulation results show that the proposed method can effectively solve the problem of specific radar emitter identification in open set environment.