Depthwise separable convolutional neural network processing architecture/method/system and medium
A convolutional neural network and deep convolution technology, applied in the field of deep separable convolutional neural network processing architecture, processing architecture, can solve the problem of massive data calculation and transmission, consumption of power consumption and data bandwidth, and failure to achieve energy consumption Excellent problems, achieve resource consumption and power consumption balance, increase calculation speed, improve data bandwidth and system operation performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0069] This embodiment provides a depthwise separable convolutional neural network processing architecture, including:
[0070] an on-chip buffer for buffering the input eigenvalues of the convolutional neural network, and the input eigenvalues one by one, read from the off-chip memory of the processing architecture of the depthwise separable convolutional neural network through the host interface and direct memory access Corresponding depth convolution weight value and point-by-point convolution weight value;
[0071] At least one depthwise separable convolution operation engine is in communication connection with the on-chip buffer, and is used for performing depthwise convolution operation on the depthwise separable convolutional neural network to generate an output value of the depthwise convolution; The output value of the depthwise convolution is subjected to a pointwise convolution operation to generate the output value of the pointwise convolution.
[0072] The pr...
Embodiment 2
[0103] This embodiment provides a depthwise separable convolutional neural network processing method, including:
[0104] performing a depthwise convolution operation on the depthwise separable convolutional neural network to generate an output value of the depthwise convolution;
[0105] A pointwise convolution operation is performed on the output value of the depthwise convolution to generate the output value of the pointwise convolution.
[0106] The processing method of the depthwise separable convolutional neural network provided by this embodiment will be described in detail below with reference to the drawings. see Figure 5 , shown as a schematic flowchart of a processing method of a depthwise separable convolutional neural network in an embodiment. like Figure 5 As shown, the processing method of the convolutional neural network specifically includes the following steps:
[0107] S51, read the input feature value of the depthwise separable convolutional neural ne...
Embodiment 3
[0116] This embodiment provides a processing system for a depthwise separable convolutional neural network, including:
[0117] a depthwise convolution module for performing a depthwise convolution operation on the depthwise separable convolutional neural network to generate an output value of the depthwise convolution;
[0118] The point-by-point convolution module is used to perform a point-by-point convolution operation on the output value of the depthwise convolution to generate the output value of the point-by-point convolution.
[0119]The processing system of the depthwise separable convolutional neural network provided by this embodiment will be described in detail below with reference to the drawings. It should be noted that, it should be understood that the following division of each module of the processing system is only a division of logical functions, and in actual implementation, it may be fully or partially integrated into a physical entity, or may be physicall...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More