Image processing neural networks with separable convolutional layers

摘要

The neural network system is configured to receive an input image and generate a classification output of the input image. The neural network system includes a separable convolution subnetwork, the separable convolution subnetwork including a plurality of separable convolutional neural network layers arranged in a stack in sequence, each separable convolution The neural network layer is configured to separately apply both the depth-wise convolution and the point-wise convolution while processing the input to the separable convolutional neural network layer to produce a layer output.