Zooming method, chip, storage medium and electronic equipment

The invention provides a zooming method, a chip, a storage medium and electronic equipment. The method is applied to a neural network processing unit, and comprises the following steps: reading input data and a weight tensor; configuring at least one convolution kernel according to the weight tensor; respectively carrying out convolution operation on the input data by utilizing at least one convolution kernel through a multiply-add array of the neural network processing unit; and outputting a result of the convolution operation as scaled data of the input data. According to the method, the scaling operation on the input data can be realized by utilizing the neural network processing unit, and an additional hardware scaling module does not need to be added. 本公开提供缩放方法、芯片、存储介质及电子设备。所述方法应用于神经网络处理单元，并且包括：读取输入数据以及权重张量；根据所述权重张量配置至少一个卷积核；通过所述神经网络处理单元的乘加阵列，利用至少一个所述卷积核对所述输入数据分别进行卷积运算；以及输出所述卷积运算的结果作为所述输入数据的缩放数据。所述方法能够利用神经网络处理单元实现对输入数据的缩放操作，无需增加额外的硬件缩放模块。