public void FromImageTest_1bpp()
{
foreach (string format in new string[] { Shape.BWHC, Shape.BHWC, Shape.BCHW })
{
Image image = new Image(53, 67, 1, 200, 200);
image.Randomize();
Tensor tensor = ImageExtensions.FromImage(image, null, format, image.Width, image.Height);
Assert.AreEqual(format, tensor.Shape.Format);
Assert.AreEqual(1, tensor.Shape.GetAxis(Axis.B));
Assert.AreEqual(53, tensor.Shape.GetAxis(Axis.X));
Assert.AreEqual(53, tensor.Shape.GetAxis(Axis.X));
Assert.AreEqual(1, tensor.Shape.GetAxis(Axis.C));
for (int x = 0; x < image.Width; x++)
{
for (int y = 0; y < image.Height; y++)
{
float expected = image.GetPixel(x, y);
Assert.AreEqual(expected, tensor[tensor.Shape.Position(0, x, y, 0)], 1e-6f);
}
}
}
}
public void FromImageTest_24to32bpp()
{
foreach (int bpp in new int[] { 24, 32 })
{
foreach (string format in new string[] { Shape.BWHC, Shape.BHWC, Shape.BCHW })
{
Image image = new Image(53, 67, bpp, 200, 200);
image.Randomize();
Tensor tensor = ImageExtensions.FromImage(image, null, format, image.Width, image.Height);
Assert.AreEqual(format, tensor.Shape.Format);
Assert.AreEqual(1, tensor.Shape.GetAxis(Axis.B));
Assert.AreEqual(53, tensor.Shape.GetAxis(Axis.X));
Assert.AreEqual(53, tensor.Shape.GetAxis(Axis.X));
Assert.AreEqual(3, tensor.Shape.GetAxis(Axis.C));
for (int x = 0; x < image.Width; x++)
{
for (int y = 0; y < image.Height; y++)
{
Color color = Color.FromArgb(image.GetPixel(x, y));
float expected1 = (255.0f - color.B) / 255.0f;
Assert.AreEqual(expected1, tensor[tensor.Shape.Position(0, x, y, 0)], 1e-6f);
float expected2 = (255.0f - color.G) / 255.0f;
Assert.AreEqual(expected2, tensor[tensor.Shape.Position(0, x, y, 1)], 1e-6f);
float expected3 = (255.0f - color.R) / 255.0f;
Assert.AreEqual(expected3, tensor[tensor.Shape.Position(0, x, y, 2)], 1e-6f);
}
}
}
}
}
/// <inheritdoc />
/// <exception cref="ArgumentNullException">
/// <paramref name="source"/> is <b>null</b>.
/// </exception>
public Answer Recognize(ImageSource source, CancellationToken cancellationToken)
{
if (source == null)
{
throw new ArgumentNullException(nameof(source));
}
// create input tensor
Tensor x = ImageExtensions.FromImage(
source.Image,
"checkbox",
this.network.InputShape.Format,
this.network.InputShape.GetAxis(Axis.X),
this.network.InputShape.GetAxis(Axis.Y));
// recognize the image
IList <(string Answer, float Probability)> result = this.network.Execute(x).Answers[0];
// create the answer
return(CheckboxReader.CreateAnswer(source, result));
}
private void Test()
{
ClassificationNetwork network = ClassificationNetwork.FromFile(this.options.NetworkFileName);
List <ClassificationResult <string> > results = new List <ClassificationResult <string> >();
using (TestImageProvider <string> dataProvider = this.options.CreateTestImageProvider(network))
{
////Context model = Context.FromRegex(@"\d{1,5}", CultureInfo.InvariantCulture);
////int n = 0;
foreach (TestImage sample in dataProvider.Generate(network.AllowedClasses))
{
Interlocked.Increment(ref this.totalImages);
////sample.Image.Save("e:\\temp\\" + sample.Label + "_" + n.ToString(CultureInfo.InvariantCulture) + ".bmp");
////n++;
////if (n < 171) continue;
this.localTimeCounter.Restart();
Tensor x = ImageExtensions.FromImage(
sample.Image,
null,
Shape.BWHC,
network.InputShape.GetAxis(Axis.X),
network.InputShape.GetAxis(Axis.Y));
IList <IList <(string Answer, float Probability)> > answers = network.Execute(x).Answers;
////(IList<(string Answer, float Probability)> answers, _) = network.ExecuteSequence(x, model);
this.localTimeCounter.Stop();
long duration = this.localTimeCounter.ElapsedMilliseconds;
foreach (IList <(string answer, float probability)> answer in answers)
{
string text = answer.FirstOrDefault().answer;
float prob = answer.FirstOrDefault().probability;
results.Add(new ClassificationResult <string>(
sample.SourceId,
text,
string.Concat(sample.Labels),
prob,
prob >= 0.38f));
this.WriteLine(
null,
"({0})\tFile: {1} ... OK ({2} ms) {3} {4:F4}",
this.totalImages,
sample.SourceId.ToFileName(false),
duration,
text,
prob);
}
/*string answer = answers.Last().FirstOrDefault()?.Answer;
* int prob = (int)(((answers.Last().FirstOrDefault()?.Probability ?? 0.0f) * 100) + 0.5f);
*
* results.Add(new ClassificationResult<string>(
* sample.SourceId,
* answer,
* string.Concat(sample.Labels),
* prob,
* prob >= 0.38f));
*
* ////this.Write(".");
* this.Write(
* null,
* "({0})\tFile: {1} ... OK ({4} ms) {2} {3:F4}",
* this.totalImages,
* sample.SourceId.ToFileName(false),
* duration,
* answer,
* prob);*/
}
}
// write report
ClassificationReport <string> testReport = new ClassificationReport <string>(results);
using (StreamWriter outputFile = File.CreateText(this.options.OutputFileName))
{
ClassificationReportWriter <string> .WriteReport(outputFile, testReport, ClassificationReportMode.All);
}
}
private void Learn(int taskIndex, LearningTask task, CancellationToken cancellationToken)
{
using (StreamWriter logFile = File.CreateText(task.LogFileName))
{
logFile.AutoFlush = true;
try
{
// report starting time
DateTime dateStarted = DateTime.Now;
this.WriteLine(logFile, string.Format(CultureInfo.InvariantCulture, "Started: {0}", dateStarted.ToString("G", CultureInfo.InvariantCulture)));
ClassificationNetwork net = File.Exists(task.Architecture) ?
ClassificationNetwork.FromFile(task.Architecture) :
ClassificationNetwork.FromArchitecture(task.Architecture, task.Classes, task.Classes, task.BlankClass);
// learning
Learn();
net.SaveToFile(task.OutputFileName, NetworkFileFormat.JSON);
// report finish time and processing interval
DateTime dateFinished = DateTime.Now;
this.WriteLine(logFile, string.Empty);
this.WriteLine(logFile, string.Format(CultureInfo.InvariantCulture, "Finished: {0:G}", dateFinished));
this.WriteLine(logFile, string.Format(CultureInfo.InvariantCulture, "Total time: {0:g}", TimeSpan.FromSeconds((dateFinished - dateStarted).TotalSeconds)));
void Learn()
{
this.WriteLine(logFile, "Learning...");
ImageDistortion filter = new ImageDistortion();
Stopwatch timer = new Stopwatch();
this.WriteLine(logFile, " Epochs: {0}", task.Epochs);
this.WriteTrainerParameters(logFile, task.Trainer, task.Algorithm, task.Loss);
this.WriteLine(logFile, "Image distortion:");
this.WriteLine(logFile, " Shift: {0}", task.Shift);
this.WriteLine(logFile, " Rotate: {0}", task.Rotate);
this.WriteLine(logFile, " Scale: {0}", task.Scale);
this.WriteLine(logFile, " Crop: {0}", task.Crop);
Shape shape = net.InputShape;
using (TestImageProvider <string> dataProvider = task.CreateDataProvider(net))
{
using (TestImageProvider <string> testDataProvider = task.CreateTestDataProvider(net))
{
////int n = 0;
for (int epoch = 0; epoch < task.Epochs; epoch++)
{
// run learning
timer.Restart();
TrainingResult result = task.Trainer.RunEpoch(
epoch,
net,
GenerateLearnSamples(dataProvider, epoch),
task.Algorithm,
task.Loss,
cancellationToken);
timer.Stop();
lock (this.logLocker)
{
string s = string.Format(
CultureInfo.InvariantCulture,
"Net: {0}, Epoch: {1}, Time: {2} ms, {3}",
taskIndex,
epoch,
timer.ElapsedMilliseconds,
result);
this.Write(logFile, s);
////this.WriteDebugInformation(logFile);
this.WriteLine(logFile, string.Empty);
}
// run testing
string epochOutputFileName = string.Format(CultureInfo.InvariantCulture, task.EpochFileNameTemplate, epoch);
// save network
net.SaveToFile(epochOutputFileName, NetworkFileFormat.JSON);
// run testing
List <ClassificationResult <string> > results = new List <ClassificationResult <string> >();
if (task.Loss is CTCLoss)
{
Context model = Context.FromRegex(@"\d", CultureInfo.InvariantCulture);
foreach ((TestImage image, string[] labels) in GenerateTestSamples(testDataProvider))
{
if (image.Image.IsAllWhite())
{
results.Add(new ClassificationResult <string>(
image.SourceId,
"0",
string.Concat(labels),
1.0f,
true));
}
else
{
Tensor x = ImageExtensions.FromImage(image.Image, null, Shape.BWHC, shape.GetAxis(Axis.X), shape.GetAxis(Axis.Y));
(string text, float prob) = net.ExecuteSequence(x, model).Answers.FirstOrDefault();
results.Add(new ClassificationResult <string>(
image.SourceId,
text,
string.Concat(labels),
prob,
prob >= 0.38f));
}
}
}
else
{
foreach ((TestImage image, string[] labels) in GenerateTestSamples(testDataProvider))
{
if (image.Image.IsAllWhite())
{
results.Add(new ClassificationResult <string>(
image.SourceId,
"0",
string.Concat(labels),
1.0f,
true));
}
else
{
Tensor x = ImageExtensions.FromImage(image.Image, null, Shape.BWHC, shape.GetAxis(Axis.X), shape.GetAxis(Axis.Y));
foreach (IList <(string answer, float probability)> answer in net.Execute(x).Answers)
{
string text = answer.FirstOrDefault().answer;
float prob = answer.FirstOrDefault().probability;
results.Add(new ClassificationResult <string>(
image.SourceId,
text,
string.Concat(labels),
prob,
prob >= 0.38f));
}
}
}
}
// write report
ClassificationReport <string> testReport = new ClassificationReport <string>(results);
this.Write(logFile, ClassificationReportWriter <string> .WriteReport(testReport, ClassificationReportMode.Summary));
using (StreamWriter outputFile = File.CreateText(Path.ChangeExtension(epochOutputFileName, ".res")))
{
ClassificationReportWriter <string> .WriteReport(outputFile, testReport, ClassificationReportMode.All);
}
}
}
IEnumerable <(Tensor x, string[] labels)> GenerateLearnSamples(TestImageProvider <string> provider, int epoch)
{
return(GenerateSamples(provider)
.Where(x => !x.image.Image.IsAllWhite())
.SelectMany(x =>
{
if (epoch == 0)
{
////x.Image.Save("e:\\temp\\" + x.Id + "_" + n.ToString(CultureInfo.InvariantCulture) + "_.bmp");
}
return filter
.Distort(
x.image.Image,
shape.GetAxis(Axis.X),
shape.GetAxis(Axis.Y),
task.Shift,
task.Rotate && x.image.FontStyle != FontStyle.Italic,
task.Scale,
task.Crop)
.Select(bitmap =>
{
if (epoch == 0)
{
////Interlocked.Increment(ref n);
////bitmap.Save(@"d:\dnn\temp\" + n.ToString(CultureInfo.InvariantCulture) + ".bmp");
////bitmap.Save(@"d:\dnn\temp\" + (n).ToString(CultureInfo.InvariantCulture) + "_" + x.SourceId.Id + ".bmp");
}
return (ImageExtensions.FromImage(bitmap, null, Shape.BWHC, shape.GetAxis(Axis.X), shape.GetAxis(Axis.Y)), x.labels);
});
}));
}
IEnumerable <(TestImage image, string[] labels)> GenerateTestSamples(TestImageProvider <string> provider)
{
return(GenerateSamples(provider)
.AsParallel()
.AsOrdered()
.WithCancellation(cancellationToken)
.WithMergeOptions(ParallelMergeOptions.AutoBuffered));
}
IEnumerable <(TestImage image, string[] labels)> GenerateSamples(TestImageProvider <string> provider)
{
return(provider
.Generate(net.AllowedClasses)
.Select(x =>
{
string[] labels = x.Labels;
if (!(task.Loss is CTCLoss))
{
int b = net.OutputShapes.First().GetAxis(Axis.B);
if (labels.Length == 1 && b > 1)
{
labels = Enumerable.Repeat(labels[0], b).ToArray();
}
}
return (x, labels);
}));
}
}
}
}
finally
{
logFile.Flush();
}
}
}
