本文主要是介绍Faster R-CNN代码之 anchors 分析,希望对大家解决编程问题提供一定的参考价值,需要的开发者们随着小编来一起学习吧!
anchors作为产生proposal的rpn中的一个重点内容,在Faster R-CNN中被重点介绍,下面我们来学习一下anchors产生部分代码。我主要将其中的部分重点代码展示出来。代码引用自Shaoqing Ren的Matlab下Faster R-CNN。
首先在Faster R-CNN迭代rpn和Fast R-CNN部分训练的前面,有一个产生anchors 的函数,我们称其产生的为base anchor,函数如下:
function anchors = proposal_generate_anchors(cache_name, varargin)
% anchors = proposal_generate_anchors(cache_name, varargin)
% --------------------------------------------------------
% Faster R-CNN
% Copyright (c) 2015, Shaoqing Ren
% Licensed under The MIT License [see LICENSE for details]
% --------------------------------------------------------%% inputsip = inputParser;ip.addRequired('cache_name', @isstr);% the size of the base anchor ip.addParamValue('base_size', 16, @isscalar);% ratio list of anchorsip.addParamValue('ratios', [0.5, 1, 2], @ismatrix);% scale list of anchorsip.addParamValue('scales', 2.^[3:5], @ismatrix); ip.addParamValue('ignore_cache', false, @islogical);ip.parse(cache_name, varargin{:});opts = ip.Results;%%if ~opts.ignore_cacheanchor_cache_dir = fullfile(pwd, 'output', 'rpn_cachedir', cache_name); mkdir_if_missing(anchor_cache_dir);anchor_cache_file = fullfile(anchor_cache_dir, 'anchors');endtryld = load(anchor_cache_file);anchors = ld.anchors;catchbase_anchor = [1, 1, opts.base_size, opts.base_size];% 围绕[base_anchor]随机ratios抖动ratio_anchors = ratio_jitter(base_anchor, opts.ratios);% 围绕[base_anchor]随机scales抖动anchors = cellfun(@(x) scale_jitter(x, opts.scales), num2cell(ratio_anchors, 2), 'UniformOutput', false);anchors = cat(1, anchors{:});if ~opts.ignore_cachesave(anchor_cache_file, 'anchors');endendend
% 具体ratio_jitter,scale_jitter函数请关注原代码
我在实验过程中设置断点,截取自己生成的anchor数值作为例子,如下:
anchor:9*4
[ -83 -39 100 56 ]
[ -175 -87 192 104 ]
[ -359 -183 376 200 ]
[ -55 -55 72 72 ]
[ -119 -119 136 136 ]
[ -247 -247 264 264 ]
[ -35 -79 52 96 ]
[ -79 -167 96 184 ]
[ -167 -343 184 360 ]
可以看出,生成的9个anchor,前三排基本除去一些随机抖动以外不同scale但是ratio相同,均为[-2, -1, 2, 1],中间三排为[-1, -1, 1, 1],最后三排为[-1, -2, 1, 2]。
根据文章,这里即文章所说的9中anchor,即base anchor。
在rpn训练的过程中,针对每一张样本图像的大小与网络,得到所有anchor。
function [anchors, im_scales] = proposal_locate_anchors(conf, im_size, target_scale, feature_map_size)
% [anchors, im_scales] = proposal_locate_anchors(conf, im_size, target_scale, feature_map_size)
% --------------------------------------------------------
% Faster R-CNN
% Copyright (c) 2015, Shaoqing Ren
% Licensed under The MIT License [see LICENSE for details]
% --------------------------------------------------------
% generate anchors for each scale% only for fcnif ~exist('feature_map_size', 'var')feature_map_size = [];endfunc = @proposal_locate_anchors_single_scale;if exist('target_scale', 'var')[anchors, im_scales] = func(im_size, conf, target_scale, feature_map_size);else[anchors, im_scales] = arrayfun(@(x) func(im_size, conf, x, feature_map_size), ...conf.scales, 'UniformOutput', false);endendfunction [anchors, im_scale] = proposal_locate_anchors_single_scale(im_size, conf, target_scale, feature_map_size)if isempty(feature_map_size)im_scale = prep_im_for_blob_size(im_size, target_scale, conf.max_size);img_size = round(im_size * im_scale);% 没有特征图时候,基于前面计算出的output高和宽,计算output_sizeoutput_size = cell2mat([conf.output_height_map.values({img_size(1)}), conf.output_width_map.values({img_size(2)})]);else%有特征图时候,直接赋值给output_sizeim_scale = prep_im_for_blob_size(im_size, target_scale, conf.max_size);output_size = feature_map_size;end% 针对output的高和宽,产生shift_x,shift_y。% shift_x大小为1*output列数shift_x = [0:(output_size(2)-1)] * conf.feat_stride;% shift_y大小为1*output行数shift_y = [0:(output_size(1)-1)] * conf.feat_stride;[shift_x, shift_y] = meshgrid(shift_x, shift_y);% concat anchors as [channel, height, width], where channel is the fastest dimension.% 这里意思就是对应output每一个像素处,根据conf.anchors(即前面提到的生成的base anchors)产生一系列anchorsanchors = reshape(bsxfun(@plus, permute(conf.anchors, [1, 3, 2]), ...permute([shift_x(:), shift_y(:), shift_x(:), shift_y(:)], [3, 1, 2])), [], 4);% equals to
% anchors = arrayfun(@(x, y) single(bsxfun(@plus, conf.anchors, [x, y, x, y])), shift_x, shift_y, 'UniformOutput', false);
% anchors = reshape(anchors, [], 1);
% anchors = cat(1, anchors{:});end
这篇关于Faster R-CNN代码之 anchors 分析的文章就介绍到这儿,希望我们推荐的文章对编程师们有所帮助!