Alzheimer’s (AD) is typical dementia, which is progressive and irreversible. Usually, the clinical diagnosis of patients is at a later stage, so early diagnosis can control the patient\'s condition in time. The stage diagnosis of AD is a multi-classification task. The doctor is usually diagnosing the patient\'s condition by 3D brain magnetic resonance imaging (MRI). However, because the 3D MRI structures of adjacent stages are almost similar, the multi-class diagnosis of AD becomes difficult. Therefore, there is a need to enhance the ability to extract more discriminative features from 3D MRI, promoting more accurate diagnosis. In addition, not only the entire MRI changes but also local areas in the MRI. Therefore, it is necessary to pay attention to changes in the entire image and local areas and to fuse features of different scales. In this paper, we propose an innovative convolutional network architecture for feature extraction and feature fusion. The proposed model has been tested on the neuroimaging project (ADNI) dataset and achieved an accuracy of 88.33%, which is nearly 2% higher than the latest research.