Convolutional neural network accelerator based on FPGA

The invention relates to a convolutional neural network accelerator based on an FPGA, and belongs to the technical field of target detection. In the method, the convolutional neural network accelerator is designed to comprise a host used for sending input image data and weight parameters to a PCIE DMA module and receiving an output result from the PCIE DMA module; and the operation module is used for performing convolution, pooling and logistic regression operation on the image data input from the image data caching module and the weight parameters from the weight data caching module. Through the design of the accelerator, the energy efficiency ratio of hardware is optimized, and the real-time performance and stability of a target detection task are ensured. 本发明涉及一种基于FPGA的卷积神经网络加速器，属于目标检测技术领域。该方法中，将所述卷积神经网络加速器设计为包括：主机：用于将输入图像数据及权重参数发送给PCIE DMA模块，以及从PCIE DMA模块接收输出结果；运算模块：用于对来自图像数据缓存模块的输入的图像数据和来自权重数据缓存模块的权重参数进行卷积、池化以及逻辑回归运算。本发明通过加速器设计，优化了硬件的能效比，保证了目标检测任务的实时性和稳定性。