In view of the problems of large model volume, high computation and unable to deploy to mobile terminal in the blind recognition of modulation mode in traditional convolutional neural network, a modulation recognition method of attention and Ghost convolution neural network (AG- CNN) based on dual attention mechanism and ghost module is proposed. The modulation signal is mapped to complex space, the map points are processed by the normalized point density, and the higher order feature density constellation is obtained. The feature is used as input of AG-CNN model for learning training, the trained model is finally used to identify the unknown signal received by the receiver. The experimental results show that the recognition rate of density constellation map with sampling point of 10 000 is over 99. 95% by AG-CNN model. Compared with CNN model with the same number of layers, the convolution layer parameter is compressed by 6. 01 times and the calculation amount is 6. 76 times. Compared with VGG-16, Inception V3, ResNet-50, Shufflenet, Eficientnet and other convolutional network models, the number of parameters and floating-point operations decreases significantly, and in the case of saving learning parameters and reducing the complexity of the model, it shows excellent classification performance.