The embodiments of the present disclosure provide a convolution processing method, apparatus, and storage medium of a convolutional neural network, said method comprising: classifying weight values in a sub-convolution kernel of a convolutional neural network; according to the classification result of each of said weight values, generating, for a corresponding weight value, an indicator used for storing a corresponding operation on data and an address used for characterizing the weight value; according to the address of the weight value, obtaining corresponding data to be processed; according to the indicator, performing a convolution operation on the data to be processed to obtain a convolution result.