method and a system for enabling a CNN with a full connection layer to receive uncertain shape input

Abstract

The invention discloses a method and a system for enabling a CNN with a full connection layer to receive uncertain shape input. According to the method, a variable step pooling layer containing a newfeature map with a fixed size after a coordinate channel is added to the feature map is newly added after convolution pooling of an existing CNN network with a full connection layer, and a coordinateprediction network composed of a plurality of full connection layers and a softmax function layer is added The method comprises the following steps: determining probability distribution vectors of coordinates (X, Y) of central points of feature blocks containing effective pixel areas through a coordinate prediction network, and carrying out different processing according to conditions of transverse dimensions W and longitudinal dimensions H of the feature blocks, so that the network can accept uncertain shape input finally. According to the method, the defect that the CNN with the full connection layer cannot receive the input of the uncertain shape can be effectively overcome, the given CNN with the full connection layer which only can receive the input of the fixed shape can receive theinput of the uncertain shape, other requirements are not changed, and the method has the advantage of good compatibility.

Description

technical field [0001] The invention belongs to the field of model design for deep learning, and in particular relates to a method and system for enabling a given CNN with a fully connected layer that can only accept input of a fixed shape to accept an input of an indeterminate shape. Background technique [0002] In real life, the pictures we can come into contact with are various and varied, some are long strips, some are square, some have high resolution and some have low resolution. These large numbers and various types of pictures have promoted the development of computer vision technology based on convolutional neural network (CNN for short). CNN-based computer vision technology has shown great potential in image classification, object detection and many other recognition tasks, even non-recognition tasks, so the development of basic operators in CNN is more necessary and meaningful. [0003] Many current CNN structures consist of two parts, the convolutional part and...

AI Technical Summary

Problems solved by technology

[0010] The technical problem to be solved by the present invention: Aiming at the above-mentioned problems of the prior art, a method and a system for enabling CNN with a fully connected layer to accept indeterminate shape input are provided. The defect of accepting indeterminate shape input can make a given CNN with a fully connected layer that can only accept fixed shape input can accept indeterminate shape input, and other requirements remain unchanged, which has the advantage of good compatibility

Images