The invention discloses a personalized capsule wardrobe creating method and device and a capsule wardrobe. The method comprises the steps of receiving and preprocessing a multi-modal data set ; inputting the relative data of the preprocessed samples according to different modalities into a pre-trained multi-path neural network; according to the pre-trained neural network and the multi-layer perceptron, extracting the characteristic data of different modes respectively, and obtaining the hierarchical Hash representations of different modes; constructing similarity matrixes of the preprocessed samples on different levels according to the level labels, and evaluating the semantic similarity among the samples according to the inner product of the Hash representation trained by the median of each level of similarity matrix; adopting the hierarchical labels with different granularities, analyzing the influence of the hierarchical comparison on the neural network performance, and determiningthe optimal hierarchical ratio; obtaining a Hash code according to each layer of Hash representation; and training the dual-path neural network, carrying out optimization training on the dual-path neural network by using an SCD gradient descent method, and establishing a deep cross-mode hash model based on a hierarchical tag for cross-mode search.