/// <summary>
/// Pick an array element with probability proportional to exp(-cost).
/// </summary>
public static int sample_by_costs(Floatarray costs)
{
Doublearray p = new Doublearray();
p.Copy(costs);
double mincost = NarrayUtil.Min(costs);
p -= mincost;
for (int i = 0; i < p.Length(); i++)
{
p.UnsafePut1d(i, Math.Exp(-p.UnsafeAt1d(i)));
}
double sump = NarrayUtil.Sum(p);
p /= sump;
double choice = rnd.NextDouble();
double s = 0;
for (int i = 0; i < p.Length(); i++)
{
s += p[i];
if (choice < s)
{
return(i);
}
}
// shouldn't happen...
return(costs.Length() - 1);
}
public override float OutputsDense(Floatarray result, Floatarray x_raw)
{
CHECK_ARG(x_raw.Length() == w1.Dim(1), "x_raw.Length() == w1.Dim(1)");
Floatarray z = new Floatarray();
int sparse = PGeti("sparse");
Floatarray y = new Floatarray();
Floatarray x = new Floatarray();
x.Copy(x_raw);
mvmul0(y, w1, x);
y += b1;
for (int i = 0; i < y.Length(); i++)
{
y[i] = sigmoid(y[i]);
}
if (sparse > 0)
{
ClassifierUtil.Sparsify(y, sparse);
}
mvmul0(z, w2, y);
z += b2;
for (int i = 0; i < z.Length(); i++)
{
z[i] = sigmoid(z[i]);
}
result.Copy(z);
//int idx = NarrayUtil.ArgMax(result);
//float val = NarrayUtil.Max(result);
return(Convert.ToSingle(Math.Abs(NarrayUtil.Sum(z) - 1.0)));
}
public static double beam_search(out string result, Intarray inputs, Floatarray costs, OcroFST fst1, OcroFST fst2,
int beam_width)
{
Intarray v1 = new Intarray();
Intarray v2 = new Intarray();
Intarray o = new Intarray();
//fprintf(stderr,"starting beam search\n");
beam_search(v1, v2, inputs, o, costs, fst1, fst2, beam_width);
//fprintf(stderr,"finished beam search\n");
FstUtil.remove_epsilons(out result, o);
return(NarrayUtil.Sum(costs));
}
public static double a_star(out string result, OcroFST fst)
{
result = "";
Intarray inputs = new Intarray();
Intarray vertices = new Intarray();
Intarray outputs = new Intarray();
Floatarray costs = new Floatarray();
if (!a_star(inputs, vertices, outputs, costs, fst))
{
return(1e38);
}
FstUtil.remove_epsilons(out result, outputs);
return(NarrayUtil.Sum(costs));
}
public static double Perplexity(Floatarray weights)
{
Floatarray w = new Floatarray();
w.Copy(weights);
w /= NarrayUtil.Sum(w);
double total = 0.0;
for (int i = 0; i < w.Length(); i++)
{
float value = w[i];
total += value * Math.Log(value);
}
return(Math.Exp(-total));
}
public static double a_star(out string result, OcroFST fst1, OcroFST fst2)
{
result = "";
Intarray inputs = new Intarray();
Intarray v1 = new Intarray();
Intarray v2 = new Intarray();
Intarray outputs = new Intarray();
Floatarray costs = new Floatarray();
if (!a_star_in_composition(inputs, v1, v2, outputs, costs, fst1, fst2))
{
return(1e38);
}
FstUtil.remove_epsilons(out result, outputs);
return(NarrayUtil.Sum(costs));
}
public static double Entropy(Floatarray a)
{
double z = NarrayUtil.Sum(a);
double total = 0.0;
for (int i = 0; i < a.Length(); i++)
{
double p = a[i] / z;
if (p < 1e-8)
{
continue;
}
total += p * Math.Log(p);
}
return(-total);
}
/// <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);
}
public override void Info()
{
bool bak = Logger.Default.verbose;
Logger.Default.verbose = true;
Logger.Default.WriteLine("Linerec");
PPrint();
Logger.Default.WriteLine(String.Format("segmenter: {0}", segmenter.IsEmpty ? "null" : segmenter.Object.Description));
Logger.Default.WriteLine(String.Format("grouper: {0}", grouper.IsEmpty ? "null" : grouper.Object.Description));
Logger.Default.WriteLine(String.Format("counts: {0} {1}", counts.Length(), NarrayUtil.Sum(counts)));
//classifier.Object.Info();
Logger.Default.verbose = bak;
}
