Invention Grant
- Patent Title: Image processing neural networks with separable convolutional layers
-
Application No.: US16338963Application Date: 2017-10-06
-
Publication No.: US11593614B2Publication Date: 2023-02-28
- Inventor: Francois Chollet , Andrew Gerald Howard
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- International Application: PCT/US2017/055581 WO 20171006
- International Announcement: WO2018/067962 WO 20180412
- Main IPC: G06N3/04
- IPC: G06N3/04 ; G06N3/08 ; G06K9/62 ; G06V40/16 ; G06V10/44

Abstract:
A neural network system is configured to receive an input image and to generate a classification output for the input image. The neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.
Public/Granted literature
- US20210027140A1 IMAGE PROCESSING NEURAL NETWORKS WITH SEPARABLE CONVOLUTIONAL LAYERS Public/Granted day:2021-01-28
Information query