public override void Clear()
{
data.Clear();
classes.Clear();
nc = 0;
nf = -1;
}
protected virtual void GetLinesOfPage(Intarray lines, int ipage)
{
lines.Clear();
string dirName = String.Format("{0}{1}{2:0000}", prefix, Path.DirectorySeparatorChar, ipage);
DirPattern dpattern = new DirPattern(dirName, @"([0-9][0-9][0-9][0-9])\.png");
if (dpattern.Length > 0)
{
lines.ReserveTo(dpattern.Length);
}
List <int> llist = new List <int>(dpattern.Length);
for (int i = 0; i < dpattern.Length; i++)
{
int k = int.Parse(dpattern[i]);
llist.Add(k);
//lines.Push(k);
}
IEnumerable <int> query = llist.OrderBy(i => i);
foreach (int iline in query)
{
lines.Push(iline);
}
}
public void Clear()
{
_keys.Fill(0);
_keys.Clear();
_values.Fill(0f);
_values.Clear();
_len = 0;
}
/// <summary>
/// Copy one FST to another, preserving only lowest-cost arcs.
/// This is useful for visualization.
/// </summary>
/// <param name="dst">The destination. Will be cleared before copying.</param>
/// <param name="src">The FST to copy.</param>
public static void fst_copy_best_arcs_only(IGenericFst dst, IGenericFst src)
{
dst.Clear();
int n = src.nStates();
for (int i = 0; i < n; i++)
{
dst.NewState();
}
dst.SetStart(src.GetStart());
for (int i = 0; i < n; i++)
{
dst.SetAccept(i, src.GetAcceptCost(i));
Intarray targets = new Intarray(), outputs = new Intarray(), inputs = new Intarray();
Floatarray costs = new Floatarray();
src.Arcs(inputs, targets, outputs, costs, i);
int inlen = inputs.Length();
if (inlen != targets.Length())
{
throw new Exception("ASSERT: inputs.length() == targets.length()");
}
if (inlen != outputs.Length())
{
throw new Exception("ASSERT: inputs.length() == outputs.length()");
}
if (inlen != costs.Length())
{
throw new Exception("ASSERT: inputs.length() == costs.length()");
}
Dictionary <int, int> hash = new Dictionary <int, int>();
for (int j = 0; j < n; j++)
{
int t = targets[j];
int best_so_far = -1;
if (hash.ContainsKey(t))
{
best_so_far = hash[t];
}
if (best_so_far == -1 || costs[j] < costs[best_so_far])
{
hash[t] = j;
}
}
Intarray keys = new Intarray();
//hash.keys(keys);
keys.Clear();
foreach (int key in hash.Keys)
{
keys.Push(key);
}
for (int k = 0; k < keys.Length(); k++)
{
int j = hash[keys[k]];
dst.AddTransition(i, targets[j], outputs[j], costs[j], inputs[j]);
}
}
}
public void Clear()
{
parents.Clear();
inputs.Clear();
outputs.Clear();
v1.Clear();
v2.Clear();
costs.Clear();
}
public void Init(params string[] books)
{
bool retrain = PGetb("retrain");
bool randomize = PGetb("randomize");
string cbookstore = PGet("cbookstore");
bookstores.Clear();
all_lines.Clear();
cseg_variant = "cseg.gt";
text_variant = "gt";
if (retrain)
{
cseg_variant = "cseg";
text_variant = "";
}
int nbooks = books.Length;
bookstores.Resize(nbooks);
int totalNumberOfPages = 0;
for (int i = 0; i < nbooks; i++)
{
bookstores[i] = ComponentCreator.MakeComponent <IBookStore>(cbookstore);
bookstores[i].SetPrefix(books[i].Trim());
Global.Debugf("info", "{0}: {1} pages", books[i], bookstores[i].NumberOfPages());
totalNumberOfPages += bookstores[i].NumberOfPages();
}
//CHECK_ARG(totalNumberOfPages > 0, "totalNumberOfPages > 0");
// compute a list of all lines
Intarray triple = new Intarray(3);
for (int i = 0; i < nbooks; i++)
{
for (int j = 0; j < bookstores[i].NumberOfPages(); j++)
{
for (int k = 0; k < bookstores[i].LinesOnPage(j); k++)
{
triple[0] = i;
triple[1] = j;
triple[2] = k;
NarrayRowUtil.RowPush(all_lines, triple);
}
}
}
Global.Debugf("info", "got {0} lines", all_lines.Dim(0));
// randomly permute it so that we train in random order
if (randomize)
{
Shuffle();
}
index = 0;
}
public void Clear()
{
nbest.Clear();
all_targets1.Clear();
all_targets2.Clear();
all_inputs.Clear();
all_outputs.Clear();
all_costs.Clear();
parent_trails.Clear();
}
protected override void GetLinesOfPage(Intarray lines, int ipage)
{
lines.Clear();
string dirName = String.Format("{0}{1}{2:0000}", prefix, Path.DirectorySeparatorChar, ipage);
//DirPattern dpattern = new DirPattern(dirName, @"([0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F])\.png");
DirPattern dpattern = new DirPattern(dirName, @"([0-9][0-9][0-9][0-9][0-9][0-9])\.png");
if (dpattern.Length > 0)
lines.ReserveTo(dpattern.Length);
for (int i = 0; i < dpattern.Length; i++)
{
int k = int.Parse(dpattern[i]);
lines.Push(k);
}
}
public bool GetCharSegmentation(Intarray image, int book, int page, int line)
{
image.Clear();
bookstores[book].GetCharSegmentation(image, page, line, "gt");
if (image.Length() > 0)
{
return(true);
}
bookstores[book].GetCharSegmentation(image, page, line, "");
if (image.Length() > 0)
{
return(true);
}
return(false);
}
/// <summary>
/// simple interface for line recognizers
/// </summary>
public virtual void SetString(string text, Floatarray costs, Intarray ids)
{
int n = text.Length;
Intarray states = new Intarray();
states.Clear();
for (int i = 0; i < n + 1; i++)
{
states.Push(NewState());
}
for (int i = 0; i < n; i++)
{
AddTransition(states[i], states[i + 1], text[i], costs[i], ids[i]);
}
SetStart(states[0]);
SetAccept(states[n]);
}
protected override void GetLinesOfPage(Intarray lines, int ipage)
{
lines.Clear();
string dirName = String.Format("{0}{1}{2:0000}", prefix, Path.DirectorySeparatorChar, ipage);
//DirPattern dpattern = new DirPattern(dirName, @"([0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F])\.png");
DirPattern dpattern = new DirPattern(dirName, @"([0-9][0-9][0-9][0-9][0-9][0-9])\.png");
if (dpattern.Length > 0)
{
lines.ReserveTo(dpattern.Length);
}
for (int i = 0; i < dpattern.Length; i++)
{
int k = int.Parse(dpattern[i]);
lines.Push(k);
}
}
public static void local_minima(ref Intarray result, Floatarray data, int r, float threshold)
{
int n = data.Length();
result.Clear();
Floatarray lmin = new Floatarray();
local_min(ref lmin, data, r);
for (int i = 1; i < n - 1; i++)
{
if (data[i] <= threshold && data[i] <= lmin[i] &&
data[i] <= data[i - 1] && data[i] < data[i + 1])
{
result.Push(i);
}
}
}
public static void weighted_sample(Intarray samples, Floatarray weights, int n)
{
Floatarray cs = new Floatarray();
cs.Copy(weights);
for (int i = 1; i < cs.Length(); i++)
{
cs[i] += cs[i - 1];
}
cs /= NarrayUtil.Max(cs);
samples.Clear();
for (int i = 0; i < n; i++)
{
float value = (float)DRandomizer.Default.drand();
int where = Binsearch(cs, value);
samples.Push(where);
}
}
public void LoadOldFormat(BinaryReader reader)
{
string magic = BinIO.magic_get(reader, "linerec".Length);
CHECK_ARG(magic == "linerec" || magic == "linerc2", "magic=='linerec' || magic=='linerc2'");
PLoad(reader);
IComponent comp = ComponentIO.load_component(reader);
IModel cmodel = comp as IModel;
classifier.Object = cmodel;
counts.Clear();
if (magic == "linerec")
{
PSet("minsize_factor", 0.0);
}
else if (magic == "linerc2")
{
Narray <int> intcount = counts;
BinIO.narray_read(reader, intcount);
}
}
/// <summary>
/// simple interface for line recognizers
/// </summary>
public virtual void SetString(string text, Floatarray costs, Intarray ids)
{
int n = text.Length;
Intarray states = new Intarray();
states.Clear();
for(int i=0; i<n+1; i++)
states.Push(NewState());
for(int i=0; i<n; i++)
AddTransition(states[i], states[i+1], text[i], costs[i], ids[i]);
SetStart(states[0]);
SetAccept(states[n]);
}
protected virtual void GetLinesOfPage(Intarray lines, int ipage)
{
lines.Clear();
string dirName = String.Format("{0}{1}{2:0000}", prefix, Path.DirectorySeparatorChar, ipage);
DirPattern dpattern = new DirPattern(dirName, @"([0-9][0-9][0-9][0-9])\.png");
if (dpattern.Length > 0)
lines.ReserveTo(dpattern.Length);
List<int> llist = new List<int>(dpattern.Length);
for (int i = 0; i < dpattern.Length; i++)
{
int k = int.Parse(dpattern[i]);
llist.Add(k);
//lines.Push(k);
}
IEnumerable<int> query = llist.OrderBy(i => i);
foreach (int iline in query)
lines.Push(iline);
}
/// <summary>
/// Copy one FST to another, preserving only lowest-cost arcs.
/// This is useful for visualization.
/// </summary>
/// <param name="dst">The destination. Will be cleared before copying.</param>
/// <param name="src">The FST to copy.</param>
public static void fst_copy_best_arcs_only(IGenericFst dst, IGenericFst src)
{
dst.Clear();
int n = src.nStates();
for (int i = 0; i < n; i++)
dst.NewState();
dst.SetStart(src.GetStart());
for(int i = 0; i < n; i++)
{
dst.SetAccept(i, src.GetAcceptCost(i));
Intarray targets = new Intarray(), outputs = new Intarray(), inputs = new Intarray();
Floatarray costs = new Floatarray();
src.Arcs(inputs, targets, outputs, costs, i);
int inlen = inputs.Length();
if (inlen != targets.Length())
throw new Exception("ASSERT: inputs.length() == targets.length()");
if (inlen != outputs.Length())
throw new Exception("ASSERT: inputs.length() == outputs.length()");
if (inlen != costs.Length())
throw new Exception("ASSERT: inputs.length() == costs.length()");
Dictionary< int, int > hash = new Dictionary<int,int>();
for(int j = 0; j < n; j++) {
int t = targets[j];
int best_so_far = -1;
if (hash.ContainsKey(t))
best_so_far = hash[t];
if(best_so_far == -1 || costs[j] < costs[best_so_far])
hash[t] = j;
}
Intarray keys = new Intarray();
//hash.keys(keys);
keys.Clear();
foreach (int key in hash.Keys)
{
keys.Push(key);
}
for(int k = 0; k < keys.Length(); k++) {
int j = hash[keys[k]];
dst.AddTransition(i, targets[j], outputs[j], costs[j], inputs[j]);
}
}
}