The invention relates to the field of deep neural networks and provides a blocked convolution optimization method and a device for a convolution neural network, so as to solve the bottleneck problem of convolution operation in a hardware processing system in the neural network. The optimization method comprises steps: a to-be-blocked convolution layer is selected, and the upper limit of the block size is determined; according to the upper limit of the block size, a block number and the block size of an input feature map are determined; based on the block number, the block size, the size of a convolution kernel, the size of the input feature map and the filling size of an input feature map boundary, the block boundary filling size of a block feature map is calculated; and based on the block number, the block size and the block boundary filling size, a convolution based on the block boundary filling is built to replace the original convolution. The resource constraint problem of the convolution neural network during operation of an embedded hardware platform is greatly alleviated, the burst length is improved maximally when a memory is read and written, the throughput is improved, the time delay is reduced, and the efficiency is improved.