DPM(Defomable Parts Model) 源码分析-训练（三）

DPM(Defomable Parts Model)原理

首先调用格式：

example:
pascal('person', 2);   % train and evaluate a 2 component person model

pascal_train.m

function model = pascal_train(cls, n) % n=2

% model = pascal_train(cls)
% Train a model using the PASCAL dataset.

globals; 
%----------读取正负样本-----------------------
% pos.im,neg.im存储了图像路径，pos.x1..pos.y2为box,负样本无box
[pos, neg] = pascal_data(cls);

% 按照长宽比，分成等量的两部分? 即将 component label  固定，phase2时，该值为latent variable。  spos为索引
spos = split(pos, n);

% -----------phase 1 : train root filters using warped positives & random negatives-----------
try
  load([cachedir cls '_random']);
catch
% -----------------------------phas 1--------------------------------
% 初始化 rootfilters
  for i=1:n
    models{i} = initmodel(spos{i});
	%---------train-------------
	% model.rootfilters{i}.w
	% model.offsets{i}.w
    models{i} = train(cls, models{i}, spos{i}, neg, 1, 1, 1, 1, 2^28);

  end
  save([cachedir cls '_random'], 'models');
end

% -----------------phase2-------------------------------------------
% :merge models and train using latent detections & hard negatives
try 
  load([cachedir cls '_hard']);
catch
  model = mergemodels(models);
  model = train(cls, model, pos, neg(1:200), 0, 0, 2, 2, 2^28, true, 0.7);
  save([cachedir cls '_hard'], 'model');
end
%----------------phase 3----------------------------------------------
% add parts and update models using latent detections & hard negatives.
try 
  load([cachedir cls '_parts']);
catch
  for i=1:n
    model = addparts(model, i, 6);
  end 
  % use more data mining iterations in the beginning
  model = train(cls, model, pos, neg(1:200), 0, 0, 1, 4, 2^30, true, 0.7);
  model = train(cls, model, pos, neg(1:200), 0, 0, 6, 2, 2^30, true, 0.7, true);
  save([cachedir cls '_parts'], 'model');
end

% update models using full set of negatives.
try 
  load([cachedir cls '_mine']);
catch
  model = train(cls, model, pos, neg, 0, 0, 1, 3, 2^30, true, 0.7, true, ...
                0.003*model.numcomponents, 2);
  save([cachedir cls '_mine'], 'model');
end

% train bounding box prediction
try
  load([cachedir cls '_final']);
catch
 % 论文中说用最小二乘，怎么直接相除了，都不考虑矩阵的奇异性
  model = trainbox(cls, model, pos, 0.7);
  save([cachedir cls '_final'], 'model');
end

initmodel.m

function model = initmodel(pos, sbin, size)

% model = initmodel(pos, sbin, size)
% Initialize model structure.
%
% If not supplied the dimensions of the model template are computed
% from statistics in the postive examples.
% 
% This should be documented! :-)
% model.sbin         8
% model.interval     10
% model.numblocks     phase 1 ：单独训练rootfilter时为2，offset,rootfilter；phase 2，为 4 
% model.numcomponents  1
% model.blocksizes     （1）=1，（2）= root.h*root.w/2*31
% model.regmult        0,1
% model.learnmult      20,1
% model.maxsize        root 的size 
% model.minsize
% model.rootfilters{i}
%   .size  				以sbin为单位，尺寸为综合各样本的h/w，area计算出来的
%   .w
%   .blocklabel        blocklabel是为编号，offset（2）,rootfilter（2）,partfilter（12 or less）,def （12 same as part）虽然意义不同但是放在一起统一编号
% model.partfilters{i}
%   .w
%   .blocklabel
% model.defs{i}
%   .anchor
%   .w
%   .blocklabel
% model.offsets{i}
%   .w               0
%   .blocklabel       1
% model.components{i}
%   .rootindex    1
%   .parts{j}
%     .partindex
%     .defindex
%   .offsetindex    1
%   .dim             2 + model.blocksizes(1) + model.blocksizes(2)
%   .numblocks       2

% pick mode of aspect ratios
h = [pos(:).y2]' - [pos(:).y1]' + 1;
w = [pos(:).x2]' - [pos(:).x1]' + 1;
xx = -2:.02:2;
filter = exp(-[-100:100].^2/400); % e^-25,e^25
aspects = hist(log(h./w), xx); %
aspects = convn(aspects, filter, 'same');
[peak, I] = max(aspects);
aspect = exp(xx(I)); %滤波后最大的h/w，作为最典型的h/w

% pick 20 percentile area
areas = sort(h.*w);
area = areas(floor(length(areas) * 0.2)); % 比它大的，可以缩放，比该尺寸小的呢？
area = max(min(area, 5000), 3000); %限制在 3000-5000

% pick dimensions
w = sqrt(area/aspect