Face recognition model training method and device, face recognition method and device, equipment and medium

The invention discloses a face recognition model training method and device, a face recognition method and device, equipment and a medium, and the method comprises the steps: inputting a sample image into a first sub-model of an original face recognition model in a model training process, and obtaining a candidate face feature vector; inputting the candidate sample face feature vector, a pre-stored adjacent matrix and a sample attribute feature vector corresponding to the sample image into a second sub-model in the original face recognition model, so that the second sub-model further learns the relationship between the attribute and the face feature; and thus, a more accurate face feature vector is output, and the accuracy of subsequent face recognition is improved. 本申请公开了一种人脸识别模型训练、人脸识别方法、装置、设备及介质，由于本申请在模型训练的过程中，将样本图像输入到原始的人脸识别模型中的第一子模型中，获得候选人脸特征向量，然后将该候选样本人脸特征向量、预先保存的邻接矩阵以及该样本图像对应的样本属性特征向量输入到该原始的人脸识别模型中的第二子模型中，进一步使得该第二子模型对属性以及人脸特征之间的关系进一步学习，进而输出更加准确的人脸特征向量，提高后续人脸识别的准确率。