The invention discloses a neural network updating method and device and electronic equipment. The method comprises the following steps: inputting a first image set with label information into a firstdeep neural network, and determining a cross entropy loss value of the first image set based on the first deep neural network; Inputting the second image set without the label information into a firstdeep neural network and a second deep neural network respectively, and determining a consistency loss value of the second image set, the first deep neural network and the second deep neural network having the same network structure; Updating parameters of the first deep neural network based on the cross entropy loss value and the consistency loss value; And updating the parameters of the second deep neural network based on the updated parameters of the first deep neural network. In this way, domain adaptation between the image set with the label information and the image set without the labelinformation can be achieved by integrating the first deep neural network and the second deep neural network of the same structure.