public static OutputVector operator /(OutputVector outvector, float val)
{
OutputVector res = outvector;
res._values = res._values / val;
return(res);
}
public int Classify(Floatarray v)
{
OutputVector p = new OutputVector();
XOutputs(p, v);
return(p.ArgMax());
}
protected override float Outputs(OutputVector result, Floatarray v)
{
result.Clear();
charclass.Object.XOutputs(result, v);
CHECK_ARG(result.nKeys() > 0, "result.nKeys() > 0");
if (PGetb("junk") && !DisableJunk && !junkclass.IsEmpty)
{
result.Normalize();
OutputVector jv = new OutputVector();
junkclass.Object.XOutputs(jv, v);
for (int i = 0; i < result.nKeys(); i++)
{
result.Values[i] *= jv.Value(0);
}
result[jc()] = jv.Value(1);
}
if (PGeti("ul") > 0 && !ulclass.IsEmpty)
{
throw new Exception("ulclass not implemented");
}
return(0.0f);
}
public float Outputs(Floatarray p, Floatarray x)
{
OutputVector ov = new OutputVector();
float cost = XOutputs(ov, x);
p.Clear();
p.Copy(ov.AsArray());
return(cost);
}
protected override float Outputs(OutputVector result, Floatarray v)
{
Floatarray outar = new Floatarray();
float cost = OutputsDense(outar, v);
result.Clear();
for (int i = 0; i < outar.Length(); i++)
result[i2c[i]] = outar[i];
return cost;
}
protected override float Outputs(OutputVector result, Floatarray v)
{
Floatarray outar = new Floatarray();
float cost = OutputsDense(outar, v);
result.Clear();
for (int i = 0; i < outar.Length(); i++)
{
result[i2c[i]] = outar[i];
}
return(cost);
}
/// <summary>
/// Run recognize
/// </summary>
/// <param name="ov">network output</param>
/// <param name="v">values can be 0..1 or 0..255, see RequireUByteInput property</param>
/// <returns></returns>
public float XOutputs(OutputVector ov, Floatarray v)
{
if (!_extractor.IsEmpty)
{
Floatarray temp = new Floatarray();
_extractor.Object.Extract(temp, v);
return(Outputs(ov, temp));
}
else
{
return(Outputs(ov, v));
}
}
protected override float Outputs(OutputVector result, Floatarray v)
{
result.Clear();
charclass.Object.XOutputs(result, v);
CHECK_ARG(result.nKeys() > 0, "result.nKeys() > 0");
if (PGetb("junk") && !DisableJunk && !junkclass.IsEmpty)
{
result.Normalize();
OutputVector jv = new OutputVector();
junkclass.Object.XOutputs(jv, v);
for (int i = 0; i < result.nKeys(); i++)
result.Values[i] *= jv.Value(0);
result[jc()] = jv.Value(1);
}
if (PGeti("ul") > 0 && !ulclass.IsEmpty)
{
throw new Exception("ulclass not implemented");
}
return 0.0f;
}
/// <summary>
/// This is a weird, optional method that exposes character segmentation
/// for those line recognizers that have it segmentation contains colored pixels,
/// and a transition in the transducer of the form * --- 1/eps --> * --- 2/a --> *
/// means that pixels with color 1 and 2 together form the letter "a"
/// </summary>
public override double RecognizeLine(Intarray segmentation_, IGenericFst result, Bytearray image_)
{
double rate = 0.0;
CHECK_ARG(image_.Dim(1) < PGeti("maxheight"),
String.Format("input line too high ({0} x {1})", image_.Dim(0), image_.Dim(1)));
CHECK_ARG(image_.Dim(1) * 1.0 / image_.Dim(0) < PGetf("maxaspect"),
String.Format("input line has bad aspect ratio ({0} x {1})", image_.Dim(0), image_.Dim(1)));
bool use_reject = PGetb("use_reject") && !DisableJunk;
//Console.WriteLine("IMG: imin:{0} imax:{1}", NarrayUtil.ArgMin(image_), NarrayUtil.ArgMax(image_));
Bytearray image = new Bytearray();
image.Copy(image_);
SetLine(image_);
if (PGeti("invert") > 0)
NarrayUtil.Sub(NarrayUtil.Max(image), image);
segmentation_.Copy(segmentation);
Bytearray available = new Bytearray();
Floatarray cp = new Floatarray();
Floatarray ccosts = new Floatarray();
Floatarray props = new Floatarray();
OutputVector p = new OutputVector();
int ncomponents = grouper.Object.Length();
int minclass = PGeti("minclass");
float minprob = PGetf("minprob");
float space_yes = PGetf("space_yes");
float space_no = PGetf("space_no");
float maxcost = PGetf("maxcost");
// compute priors if possible; fall back on
// using no priors if no counts are available
Floatarray priors = new Floatarray();
bool use_priors = PGeti("use_priors") > 0;
if (use_priors)
{
if (counts.Length() > 0)
{
priors.Copy(counts);
priors /= NarrayUtil.Sum(priors);
}
else
{
if (!counts_warned)
Global.Debugf("warn", "use_priors specified but priors unavailable (old model)");
use_priors = false;
counts_warned = true;
}
}
EstimateSpaceSize();
for (int i = 0; i < ncomponents; i++)
{
Rect b;
Bytearray mask = new Bytearray();
grouper.Object.GetMask(out b, ref mask, i, 0);
Bytearray cv = new Bytearray();
grouper.Object.ExtractWithMask(cv, mask, image, i, 0);
//ImgIo.write_image_gray("extrmask_image.png", cv);
Floatarray v = new Floatarray();
v.Copy(cv);
v /= 255.0f;
float ccost = classifier.Object.XOutputs(p, v);
if (use_reject && classifier.Object.HigherOutputIsBetter)
{
ccost = 0;
float total = p.Sum();
if (total > 1e-11f)
{
//p /= total;
}
else
p.Values.Fill(0.0f);
}
int count = 0;
Global.Debugf("dcost", "output {0}", p.Keys.Length());
for (int index = 0; index < p.Keys.Length(); index++)
{
int j = p.Keys[index];
if (j < minclass) continue;
if (j == reject_class) continue;
float value = p.Values[index];
if (value <= 0.0f) continue;
if (value < minprob) continue;
float pcost = classifier.Object.HigherOutputIsBetter ? (float)-Math.Log(value) : value;
Global.Debugf("dcost", "{0} {1} {2}", j, pcost + ccost, (j > 32 ? (char)j : '_'));
float total_cost = pcost + ccost;
if (total_cost < maxcost)
{
if (use_priors)
{
total_cost -= (float)-Math.Log(priors[j]);
}
grouper.Object.SetClass(i, j, total_cost);
count++;
}
}
Global.Debugf("dcost", "");
if (count == 0)
{
float xheight = 10.0f;
if (b.Height() < xheight / 2 && b.Width() < xheight / 2)
{
grouper.Object.SetClass(i, (int)'~', high_cost / 2);
}
else
{
grouper.Object.SetClass(i, (int)'#', (b.Width() / xheight) * high_cost);
}
}
if (grouper.Object.PixelSpace(i) > space_threshold)
{
Global.Debugf("spaces", "space {0}", grouper.Object.PixelSpace(i));
grouper.Object.SetSpaceCost(i, space_yes, space_no);
}
}
grouper.Object.GetLattice(result);
return rate;
}
protected virtual float Outputs(OutputVector ov, Floatarray temp)
{
throw new NotImplementedException();
}
public int Classify(Floatarray v)
{
OutputVector p = new OutputVector();
XOutputs(p, v);
return p.ArgMax();
}
protected virtual float Outputs(OutputVector ov, Floatarray temp)
{
throw new NotImplementedException();
}
/// <summary>
/// Run recognize
/// </summary>
/// <param name="ov">network output</param>
/// <param name="v">values can be 0..1 or 0..255, see RequireUByteInput property</param>
/// <returns></returns>
public float XOutputs(OutputVector ov, Floatarray v)
{
if (!_extractor.IsEmpty)
{
Floatarray temp = new Floatarray();
_extractor.Object.Extract(temp, v);
return Outputs(ov, temp);
}
else
return Outputs(ov, v);
}
public float Outputs(Floatarray p, Floatarray x)
{
OutputVector ov = new OutputVector();
float cost = XOutputs(ov, x);
p.Clear();
p.Copy(ov.AsArray());
return cost;
}
/// <summary>
/// This is a weird, optional method that exposes character segmentation
/// for those line recognizers that have it segmentation contains colored pixels,
/// and a transition in the transducer of the form * --- 1/eps --> * --- 2/a --> *
/// means that pixels with color 1 and 2 together form the letter "a"
/// </summary>
public override double RecognizeLine(Intarray segmentation_, IGenericFst result, Bytearray image_)
{
double rate = 0.0;
CHECK_ARG(image_.Dim(1) < PGeti("maxheight"),
String.Format("input line too high ({0} x {1})", image_.Dim(0), image_.Dim(1)));
CHECK_ARG(image_.Dim(1) * 1.0 / image_.Dim(0) < PGetf("maxaspect"),
String.Format("input line has bad aspect ratio ({0} x {1})", image_.Dim(0), image_.Dim(1)));
bool use_reject = PGetb("use_reject") && !DisableJunk;
//Console.WriteLine("IMG: imin:{0} imax:{1}", NarrayUtil.ArgMin(image_), NarrayUtil.ArgMax(image_));
Bytearray image = new Bytearray();
image.Copy(image_);
SetLine(image_);
if (PGeti("invert") > 0)
{
NarrayUtil.Sub(NarrayUtil.Max(image), image);
}
segmentation_.Copy(segmentation);
Bytearray available = new Bytearray();
Floatarray cp = new Floatarray();
Floatarray ccosts = new Floatarray();
Floatarray props = new Floatarray();
OutputVector p = new OutputVector();
int ncomponents = grouper.Object.Length();
int minclass = PGeti("minclass");
float minprob = PGetf("minprob");
float space_yes = PGetf("space_yes");
float space_no = PGetf("space_no");
float maxcost = PGetf("maxcost");
// compute priors if possible; fall back on
// using no priors if no counts are available
Floatarray priors = new Floatarray();
bool use_priors = PGeti("use_priors") > 0;
if (use_priors)
{
if (counts.Length() > 0)
{
priors.Copy(counts);
priors /= NarrayUtil.Sum(priors);
}
else
{
if (!counts_warned)
{
Global.Debugf("warn", "use_priors specified but priors unavailable (old model)");
}
use_priors = false;
counts_warned = true;
}
}
EstimateSpaceSize();
for (int i = 0; i < ncomponents; i++)
{
Rect b;
Bytearray mask = new Bytearray();
grouper.Object.GetMask(out b, ref mask, i, 0);
Bytearray cv = new Bytearray();
grouper.Object.ExtractWithMask(cv, mask, image, i, 0);
//ImgIo.write_image_gray("extrmask_image.png", cv);
Floatarray v = new Floatarray();
v.Copy(cv);
v /= 255.0f;
float ccost = classifier.Object.XOutputs(p, v);
if (use_reject && classifier.Object.HigherOutputIsBetter)
{
ccost = 0;
float total = p.Sum();
if (total > 1e-11f)
{
//p /= total;
}
else
{
p.Values.Fill(0.0f);
}
}
int count = 0;
Global.Debugf("dcost", "output {0}", p.Keys.Length());
for (int index = 0; index < p.Keys.Length(); index++)
{
int j = p.Keys[index];
if (j < minclass)
{
continue;
}
if (j == reject_class)
{
continue;
}
float value = p.Values[index];
if (value <= 0.0f)
{
continue;
}
if (value < minprob)
{
continue;
}
float pcost = classifier.Object.HigherOutputIsBetter ? (float)-Math.Log(value) : value;
Global.Debugf("dcost", "{0} {1} {2}", j, pcost + ccost, (j > 32 ? (char)j : '_'));
float total_cost = pcost + ccost;
if (total_cost < maxcost)
{
if (use_priors)
{
total_cost -= (float)-Math.Log(priors[j]);
}
grouper.Object.SetClass(i, j, total_cost);
count++;
}
}
Global.Debugf("dcost", "");
if (count == 0)
{
float xheight = 10.0f;
if (b.Height() < xheight / 2 && b.Width() < xheight / 2)
{
grouper.Object.SetClass(i, (int)'~', high_cost / 2);
}
else
{
grouper.Object.SetClass(i, (int)'#', (b.Width() / xheight) * high_cost);
}
}
if (grouper.Object.PixelSpace(i) > space_threshold)
{
Global.Debugf("spaces", "space {0}", grouper.Object.PixelSpace(i));
grouper.Object.SetSpaceCost(i, space_yes, space_no);
}
}
grouper.Object.GetLattice(result);
return(rate);
}
private void DoTestRecognize(LenetClassifier classifier)
{
OutputVector ov = new OutputVector();
Floatarray v = new Floatarray();
Bytearray ba = new Bytearray(1, 1);
ImgIo.read_image_gray(ba, testPngFileName);
NarrayUtil.Sub(255, ba);
v.Copy(ba);
v /= 255.0;
classifier.XOutputs(ov, v);
Console.WriteLine("Featured output class '{0}', score '{1}'", (char)ov.Key(ov.BestIndex), ov.Value(ov.BestIndex));
}