Feature map processing method and related device

An apparatus for processing feature maps, comprising:

• a processor configured to:
• invoke a neural network model, wherein the neural network model comprises a plurality of input adaptation branches and a post-processing part, an output of each of the plurality of input adaptation branches is coupled to an input of the post-processing part, the plurality of input adaptation branches are configured to downsample a feature map, each of the plurality of input adaptation branches has a different downsampling ratio for the feature map;
• input a first feature map to one of the plurality of input adaptation branches, to obtain a second feature map, wherein the one input adaptation branch is determined based on a size of the first feature map and a preset size threshold, the preset size threshold is an upper limit size of an input feature map of the post-processing part, and a size of the second feature map is not greater than the preset size threshold;
• and
• input the second feature map to the post-processing part for post-processing, to obtain a processing result of the first feature map.

A non-transitory computer-readable storage medium, comprising program code, wherein when the program code is executed by a computer, causes the computer to perform a method of processing feature maps, the method comprising:

• invoking a neural network model, wherein the neural network model comprises a plurality of input adaptation branches and a post-processing part, an output of each of the plurality of input adaptation branches is coupled to an input of the post-processing part, the plurality of input adaptation branches are configured to downsample a feature map, each of the plurality of input adaptation branches has a different downsampling ratio for the feature map;
• inputting a first feature map to one of the plurality of input adaptation branches, to obtain a second feature map, wherein the input adaptation branch is determined based on a size of the first feature map and a preset size threshold, the preset size threshold is an upper limit size of an input feature map of the post-processing part, and a size of the second feature map is not greater than the preset size threshold;
• and
• inputting the second feature map to the post-processing part for post-processing, to obtain a processing result of the first feature map.