private SampleCollection CreateNextSamples(SampleCollection allNegSamples, double falsePositiveRate, int maxSampleNum)
{
int selectSampleCount = (int)(maxSampleNum / falsePositiveRate);
if (selectSampleCount <= 0)
{
selectSampleCount = allNegSamples.Count;
}
SampleCollection negSamples = allNegSamples.GetNegSamples(selectSampleCount);
int oldNum = negSamples.Count;
negSamples = this.GetPositivePredictedSamples(negSamples);
if (DebugMsg.Debug)
{
string msg = string.Format("选取了{0}个负样本，通过了{1}个，误检率为{2:P5}\r\n",
oldNum, negSamples.Count, (MyFloat)negSamples.Count / oldNum);
DebugMsg.AddMessage(msg, 0);
}
if (negSamples.Count > maxSampleNum)
{
negSamples.TrimExcess(maxSampleNum);
}
GC.Collect();
return(negSamples);
}
public void Train(SampleCollection posSamples,
SampleCollection allNegSamples,
SampleCollection validateSamples,
Size size,
double targetFalsePositiveRate, double maxFalsePositiveRate, double minHitRate)
{
const int startCapacity = 20;
_size = size;
List <StageClassifier> stageClassifier = new List <StageClassifier>(startCapacity);
double hitRate = 1;
double falsePositiveRate = 1;
int stageCount = 0;
int maxSampleNum;
SampleCollection negSamples;
{ //计算使用的负样本数量
double MaxMemoryUse = MemoryInfo.GetFreePhysicalMemory() - 400e6;
if (MaxMemoryUse < 0)
{
MaxMemoryUse = 1.8e9;
}
//MaxMemoryUse = 2.48e9;
//按照内存大小来选取负样本，在充分利用内存的同时防止使用虚拟内存
int weakNum = WeakClassifierManager.Instance.WeakClassifiers.Length;
maxSampleNum = (int)((
MaxMemoryUse
- 1.5e6f //预留150M给程序其它部分
)
/ weakNum / sizeof(MyFloat)) - posSamples.Count;
if (DebugMsg.Debug)
{
string msg = string.Format("\r\n单次使用负样本：{0}，特征数量：{1}，预计消耗内存：{2}M\r\n",
maxSampleNum, weakNum, MaxMemoryUse / 1024 / 1024);
DebugMsg.AddMessage(msg, 0);
}
}
//如果已有分类器，计算当前的性能
if (_classifiers != null && _classifiers.Length > 0)
{
PredictResult result = EvaluateErrorRate(validateSamples);
hitRate = result.HitRate;
falsePositiveRate = result.FalsePositiveRate;
stageCount = _classifiers.Length;
stageClassifier.AddRange(_classifiers);
negSamples = CreateNextSamples(allNegSamples, falsePositiveRate, maxSampleNum);
if (DebugMsg.Debug)
{
string msg = string.Format("载入分类器完成，层数：{0}，当前性能为：\r\n检测率：\t{1:P5}，\t误检率：\t{2:P5}\r\n------\r\n",
stageCount, hitRate, falsePositiveRate);
DebugMsg.AddMessage(msg, 0);
}
}
else
{
negSamples = allNegSamples.GetNegSamples(maxSampleNum);
}
while (falsePositiveRate > targetFalsePositiveRate && negSamples.Count != 0 && posSamples.Count != 0)
{
stageCount++;
if (DebugMsg.Debug)
{
string msg = string.Format("--------------------\r\n开始训练第{0}级分类器，使用的数量为：\r\n正样本：\t{1}\t负样本：\t{2}\r\n目标检测率：\t{3:P5}\t目标误检率：\t{4:P5}\r\n",
stageCount, posSamples.Count, negSamples.Count, minHitRate, maxFalsePositiveRate);
DebugMsg.AddMessage(msg, 0);
}
StageClassifier currentStage = new StageClassifier(stageCount);
PredictResult result = currentStage.Train(posSamples, negSamples, validateSamples,
maxFalsePositiveRate, minHitRate);
falsePositiveRate *= result.FalsePositiveRate;
hitRate *= result.HitRate;
stageClassifier.Add(currentStage);
_classifiers = stageClassifier.ToArray();
if (DebugMsg.Debug)
{
string msg = string.Format("------\r\n第{0}级分类器训练结束，当前性能为：\r\n检测率：\t{1:P5}，\t误检率：\t{2:P5}\r\n弱分类器数量：{3}\r\n目前训练时间总计：{4}\r\n",
stageCount, hitRate, falsePositiveRate, currentStage.WeakClassifierCount, DebugMsg.stopwatch.Elapsed.ToString());
DebugMsg.AddMessage(msg, 0);
}
if (falsePositiveRate > targetFalsePositiveRate)
{
//posSamples = this.CreateNextSamples(posSamples);
validateSamples = this.GetPositivePredictedSamples(validateSamples);
negSamples = CreateNextSamples(allNegSamples, falsePositiveRate, maxSampleNum);
}
this.Save(string.Format(@"D:\ccc{0}.xml", stageCount.ToString()));
}
if (DebugMsg.Debug)
{
DebugMsg.stopwatch.Stop();
string msg = string.Format("\r\n--------------------\r\n全部训练完成，训练时间总计：{0}\r\n",
DebugMsg.stopwatch.Elapsed.ToString());
DebugMsg.AddMessage(msg, 0);
}
this.Save(@"D:\ccc.xml");
}