/// <summary>
/// Loads multiple artifacts of interest from the input model file, given the context
/// established by the command line arguments.
/// </summary>
/// <param name="ch">The channel to which to provide output.</param>
/// <param name="wantPredictor">Whether we want a predictor from the model file. If
/// <c>false</c> we will not even attempt to load a predictor. If <c>null</c> we will
/// load the predictor, if present. If <c>true</c> we will load the predictor, or fail
/// noisily if we cannot.</param>
/// <param name="predictor">The predictor in the model, or <c>null</c> if
/// <paramref name="wantPredictor"/> was false, or <paramref name="wantPredictor"/> was
/// <c>null</c> and no predictor was present.</param>
/// <param name="wantTrainSchema">Whether we want the training schema. Unlike
/// <paramref name="wantPredictor"/>, this has no "hard fail if not present" option. If
/// this is <c>true</c>, it is still possible for <paramref name="trainSchema"/> to remain
/// <c>null</c> if there were no role mappings, or pipeline.</param>
/// <param name="trainSchema">The training schema if <paramref name="wantTrainSchema"/>
/// is true, and there were role mappings stored in the model.</param>
/// <param name="pipe">The data pipe constructed from the combination of the
/// model and command line arguments.</param>
protected void LoadModelObjects(
IChannel ch,
bool?wantPredictor, out IPredictor predictor,
bool wantTrainSchema, out RoleMappedSchema trainSchema,
out IDataLoader pipe)
{
// First handle the case where there is no input model file.
// Everything must come from the command line.
using (var file = Host.OpenInputFile(Args.InputModelFile))
using (var strm = file.OpenReadStream())
using (var rep = RepositoryReader.Open(strm, Host))
{
// First consider loading the predictor.
if (wantPredictor == false)
{
predictor = null;
}
else
{
ch.Trace("Loading predictor");
predictor = ModelFileUtils.LoadPredictorOrNull(Host, rep);
if (wantPredictor == true)
{
Host.Check(predictor != null, "Could not load predictor from model file");
}
}
// Next create the loader.
var loaderFactory = Args.Loader;
IDataLoader trainPipe = null;
if (loaderFactory != null)
{
// The loader is overridden from the command line.
pipe = loaderFactory.CreateComponent(Host, new MultiFileSource(Args.DataFile));
if (Args.LoadTransforms == true)
{
Host.CheckUserArg(!string.IsNullOrWhiteSpace(Args.InputModelFile), nameof(Args.InputModelFile));
pipe = LoadTransformChain(pipe);
}
}
else
{
var loadTrans = Args.LoadTransforms ?? true;
pipe = LoadLoader(rep, Args.DataFile, loadTrans);
if (loadTrans)
{
trainPipe = pipe;
}
}
if (Utils.Size(Args.Transforms) > 0)
{
pipe = CompositeDataLoader.Create(Host, pipe, Args.Transforms);
}
// Next consider loading the training data's role mapped schema.
trainSchema = null;
if (wantTrainSchema)
{
// First try to get the role mappings.
var trainRoleMappings = ModelFileUtils.LoadRoleMappingsOrNull(Host, rep);
if (trainRoleMappings != null)
{
// Next create the training schema. In the event that the loaded pipeline happens
// to be the training pipe, we can just use that. If it differs, then we need to
// load the full pipeline from the model, relying upon the fact that all loaders
// can be loaded with no data at all, to get their schemas.
if (trainPipe == null)
{
trainPipe = ModelFileUtils.LoadLoader(Host, rep, new MultiFileSource(null), loadTransforms: true);
}
trainSchema = new RoleMappedSchema(trainPipe.Schema, trainRoleMappings);
}
// If the role mappings are null, an alternative would be to fail. However the idea
// is that the scorer should always still succeed, although perhaps with reduced
// functionality, even when the training schema is null, since not all versions of
// TLC models will have the role mappings preserved, I believe. And, we do want to
// maintain backwards compatibility.
}
}
}
public void TestGreyscaleTransformImages()
{
using (var env = new ConsoleEnvironment())
{
var imageHeight = 150;
var imageWidth = 100;
var dataFile = GetDataPath("images/images.tsv");
var imageFolder = Path.GetDirectoryName(dataFile);
var data = env.CreateLoader("Text{col=ImagePath:TX:0 col=Name:TX:1}", new MultiFileSource(dataFile));
var images = ImageLoaderTransform.Create(env, new ImageLoaderTransform.Arguments()
{
Column = new ImageLoaderTransform.Column[1]
{
new ImageLoaderTransform.Column()
{
Source = "ImagePath", Name = "ImageReal"
}
},
ImageFolder = imageFolder
}, data);
var cropped = ImageResizerTransform.Create(env, new ImageResizerTransform.Arguments()
{
Column = new ImageResizerTransform.Column[1] {
new ImageResizerTransform.Column()
{
Name = "ImageCropped", Source = "ImageReal", ImageHeight = imageHeight, ImageWidth = imageWidth, Resizing = ImageResizerTransform.ResizingKind.IsoCrop
}
}
}, images);
IDataView grey = ImageGrayscaleTransform.Create(env, new ImageGrayscaleTransform.Arguments()
{
Column = new ImageGrayscaleTransform.Column[1] {
new ImageGrayscaleTransform.Column()
{
Name = "ImageGrey", Source = "ImageCropped"
}
}
}, cropped);
var fname = nameof(TestGreyscaleTransformImages) + "_model.zip";
var fh = env.CreateOutputFile(fname);
using (var ch = env.Start("save"))
TrainUtils.SaveModel(env, ch, fh, null, new RoleMappedData(grey));
grey = ModelFileUtils.LoadPipeline(env, fh.OpenReadStream(), new MultiFileSource(dataFile));
DeleteOutputPath(fname);
grey.Schema.TryGetColumnIndex("ImageGrey", out int greyColumn);
using (var cursor = grey.GetRowCursor((x) => true))
{
var bitmapGetter = cursor.GetGetter <Bitmap>(greyColumn);
Bitmap bitmap = default;
while (cursor.MoveNext())
{
bitmapGetter(ref bitmap);
Assert.NotNull(bitmap);
for (int x = 0; x < imageWidth; x++)
{
for (int y = 0; y < imageHeight; y++)
{
var pixel = bitmap.GetPixel(x, y);
// greyscale image has same values for R,G and B
Assert.True(pixel.R == pixel.G && pixel.G == pixel.B);
}
}
}
}
}
Done();
}
[ConditionalFact(typeof(Environment), nameof(Environment.Is64BitProcess))] // x86 fails with "An attempt was made to load a program with an incorrect format."
void TestOldSavingAndLoading()
{
if (!RuntimeInformation.IsOSPlatform(OSPlatform.Windows))
{
return;
}
var modelFile = "squeezenet/00000001/model.onnx";
var samplevector = GetSampleArrayData();
var dataView = ComponentCreation.CreateDataView(Env,
new TestData[] {
new TestData()
{
data_0 = samplevector
}
});
var inputNames = new[] { "data_0" };
var outputNames = new[] { "softmaxout_1" };
var est = new OnnxScoringEstimator(Env, modelFile, inputNames, outputNames);
var transformer = est.Fit(dataView);
var result = transformer.Transform(dataView);
var resultRoles = new RoleMappedData(result);
using (var ms = new MemoryStream())
{
TrainUtils.SaveModel(Env, Env.Start("saving"), ms, null, resultRoles);
ms.Position = 0;
var loadedView = ModelFileUtils.LoadTransforms(Env, dataView, ms);
loadedView.Schema.TryGetColumnIndex(outputNames[0], out int softMaxOut1);
using (var cursor = loadedView.GetRowCursor(col => col == softMaxOut1))
{
VBuffer <float> softMaxValue = default;
var softMaxGetter = cursor.GetGetter <VBuffer <float> >(softMaxOut1);
float sum = 0f;
int i = 0;
while (cursor.MoveNext())
{
softMaxGetter(ref softMaxValue);
var values = softMaxValue.DenseValues();
foreach (var val in values)
{
sum += val;
if (i == 0)
{
Assert.InRange(val, 0.00004, 0.00005);
}
if (i == 1)
{
Assert.InRange(val, 0.003844, 0.003845);
}
if (i == 999)
{
Assert.InRange(val, 0.0029566, 0.0029567);
}
i++;
}
}
Assert.InRange(sum, 1.0, 1.00001);
}
}
}
protected IDataLoader LoadLoader(RepositoryReader rep, string path, bool loadTransforms)
{
return(ModelFileUtils.LoadLoader(Host, rep, new MultiFileSource(path), loadTransforms));
}
public void TestOldSavingAndLoading()
{
var data = new[] {
new TestClass()
{
A = 1, B = 3, C = new float[2] {
1, 2
}, D = new double[2] {
3, 4
}
},
new TestClass()
{
A = float.NaN, B = double.NaN, C = new float[2] {
float.NaN, float.NaN
}, D = new double[2] {
double.NaN, double.NaN
}
},
new TestClass()
{
A = float.NegativeInfinity, B = double.NegativeInfinity, C = new float[2] {
float.NegativeInfinity, float.NegativeInfinity
}, D = new double[2] {
double.NegativeInfinity, double.NegativeInfinity
}
},
new TestClass()
{
A = float.PositiveInfinity, B = double.PositiveInfinity, C = new float[2] {
float.PositiveInfinity, float.PositiveInfinity,
}, D = new double[2] {
double.PositiveInfinity, double.PositiveInfinity
}
},
new TestClass()
{
A = 2, B = 1, C = new float[2] {
3, 4
}, D = new double[2] {
5, 6
}
},
};
var dataView = ML.Data.LoadFromEnumerable(data);
var pipe = ML.Transforms.ReplaceMissingValues(
new MissingValueReplacingEstimator.ColumnOptions("NAA", "A", MissingValueReplacingEstimator.ReplacementMode.Mean),
new MissingValueReplacingEstimator.ColumnOptions("NAB", "B", MissingValueReplacingEstimator.ReplacementMode.Mean),
new MissingValueReplacingEstimator.ColumnOptions("NAC", "C", MissingValueReplacingEstimator.ReplacementMode.Mean),
new MissingValueReplacingEstimator.ColumnOptions("NAD", "D", MissingValueReplacingEstimator.ReplacementMode.Mean));
var result = pipe.Fit(dataView).Transform(dataView);
var resultRoles = new RoleMappedData(result);
using (var ms = new MemoryStream())
{
TrainUtils.SaveModel(Env, Env.Start("saving"), ms, null, resultRoles);
ms.Position = 0;
var loadedView = ModelFileUtils.LoadTransforms(Env, dataView, ms);
}
}
public void TestOldSavingAndLoading(int?gpuDeviceId, bool fallbackToCpu)
{
var modelFile = "squeezenet/00000001/model.onnx";
var samplevector = GetSampleArrayData();
var dataView = ML.Data.LoadFromEnumerable(
new TestData[] {
new TestData()
{
data_0 = samplevector
}
});
var inputNames = new[] { "data_0" };
var outputNames = new[] { "softmaxout_1" };
var est = ML.Transforms.ApplyOnnxModel(outputNames, inputNames, modelFile, gpuDeviceId, fallbackToCpu);
var transformer = est.Fit(dataView);
var result = transformer.Transform(dataView);
var resultRoles = new RoleMappedData(result);
using (var ms = new MemoryStream())
{
TrainUtils.SaveModel(Env, Env.Start("saving"), ms, null, resultRoles);
ms.Position = 0;
var loadedView = ModelFileUtils.LoadTransforms(Env, dataView, ms);
var sofMaxOut1Col = loadedView.Schema[outputNames[0]];
using (var cursor = loadedView.GetRowCursor(sofMaxOut1Col))
{
VBuffer <float> softMaxValue = default;
var softMaxGetter = cursor.GetGetter <VBuffer <float> >(sofMaxOut1Col);
float sum = 0f;
int i = 0;
while (cursor.MoveNext())
{
softMaxGetter(ref softMaxValue);
var values = softMaxValue.DenseValues();
foreach (var val in values)
{
sum += val;
if (i == 0)
{
Assert.InRange(val, 0.00004, 0.00005);
}
if (i == 1)
{
Assert.InRange(val, 0.003844, 0.003845);
}
if (i == 999)
{
Assert.InRange(val, 0.0029566, 0.0029567);
}
i++;
}
}
Assert.InRange(sum, 0.99999, 1.00001);
}
(transformer as IDisposable)?.Dispose();
}
}
public void TestBackAndForthConversionWithoutAlphaNoInterleaveNoOffset()
{
IHostEnvironment env = new MLContext();
const int imageHeight = 100;
const int imageWidth = 130;
var dataFile = GetDataPath("images/images.tsv");
var imageFolder = Path.GetDirectoryName(dataFile);
var data = TextLoader.Create(env, new TextLoader.Options()
{
Columns = new[]
{
new TextLoader.Column("ImagePath", DataKind.TX, 0),
new TextLoader.Column("Name", DataKind.TX, 1),
}
}, new MultiFileSource(dataFile));
var images = new ImageLoadingTransformer(env, imageFolder, ("ImageReal", "ImagePath")).Transform(data);
var cropped = new ImageResizingTransformer(env, "ImageCropped", imageWidth, imageHeight, "ImageReal").Transform(images);
var pixels = new ImagePixelExtractingTransformer(env, "ImagePixels", "ImageCropped").Transform(cropped);
IDataView backToBitmaps = new VectorToImageConvertingTransformer(env, "ImageRestored", "ImagePixels",
imageHeight, imageWidth, ImagePixelExtractingEstimator.ColorBits.Rgb, false, 1, 0).Transform(pixels);
var fname = nameof(TestBackAndForthConversionWithoutAlphaNoInterleaveNoOffset) + "_model.zip";
var fh = env.CreateOutputFile(fname);
using (var ch = env.Start("save"))
TrainUtils.SaveModel(env, ch, fh, null, new RoleMappedData(backToBitmaps));
backToBitmaps = ModelFileUtils.LoadPipeline(env, fh.OpenReadStream(), new MultiFileSource(dataFile));
DeleteOutputPath(fname);
backToBitmaps.Schema.TryGetColumnIndex("ImageRestored", out int bitmapColumn);
backToBitmaps.Schema.TryGetColumnIndex("ImageCropped", out int cropBitmapColumn);
using (var cursor = backToBitmaps.GetRowCursorForAllColumns())
{
var bitmapGetter = cursor.GetGetter <Bitmap>(bitmapColumn);
Bitmap restoredBitmap = default;
var bitmapCropGetter = cursor.GetGetter <Bitmap>(cropBitmapColumn);
Bitmap croppedBitmap = default;
while (cursor.MoveNext())
{
bitmapGetter(ref restoredBitmap);
Assert.NotNull(restoredBitmap);
bitmapCropGetter(ref croppedBitmap);
Assert.NotNull(croppedBitmap);
for (int x = 0; x < imageWidth; x++)
{
for (int y = 0; y < imageHeight; y++)
{
var c = croppedBitmap.GetPixel(x, y);
var r = restoredBitmap.GetPixel(x, y);
Assert.True(c.R == r.R && c.G == r.G && c.B == r.B);
}
}
}
Done();
}
}
/// <summary>
/// Loads a predictor from the model stream. Returns null iff there's no predictor.
/// </summary>
/// <param name="env">The host environment to use.</param>
/// <param name="modelStream">The model stream.</param>
public static IPredictor LoadPredictorOrNull(this IHostEnvironment env, Stream modelStream)
{
Contracts.CheckValue(modelStream, nameof(modelStream));
return(ModelFileUtils.LoadPredictorOrNull(env, modelStream));
}
public void TestBackAndForthConversionWithAlphaNoInterleaveNoOffset()
{
IHostEnvironment env = new MLContext();
const int imageHeight = 100;
var imageWidth = 130;
var dataFile = GetDataPath("images/images.tsv");
var imageFolder = Path.GetDirectoryName(dataFile);
var data = TextLoader.Create(env, new TextLoader.Arguments()
{
Column = new[]
{
new TextLoader.Column("ImagePath", DataKind.TX, 0),
new TextLoader.Column("Name", DataKind.TX, 1),
}
}, new MultiFileSource(dataFile));
var images = ImageLoaderTransform.Create(env, new ImageLoaderTransform.Arguments()
{
Column = new ImageLoaderTransform.Column[1]
{
new ImageLoaderTransform.Column()
{
Source = "ImagePath", Name = "ImageReal"
}
},
ImageFolder = imageFolder
}, data);
var cropped = ImageResizerTransform.Create(env, new ImageResizerTransform.Arguments()
{
Column = new ImageResizerTransform.Column[1] {
new ImageResizerTransform.Column()
{
Source = "ImageReal", Name = "ImageCropped", ImageHeight = imageHeight, ImageWidth = imageWidth, Resizing = ImageResizerTransform.ResizingKind.IsoCrop
}
}
}, images);
var pixels = ImagePixelExtractorTransform.Create(env, new ImagePixelExtractorTransform.Arguments()
{
InterleaveArgb = false,
Column = new ImagePixelExtractorTransform.Column[1] {
new ImagePixelExtractorTransform.Column()
{
Source = "ImageCropped", Name = "ImagePixels", UseAlpha = true
}
}
}, cropped);
IDataView backToBitmaps = new VectorToImageTransform(env, new VectorToImageTransform.Arguments()
{
InterleaveArgb = false,
Column = new VectorToImageTransform.Column[1] {
new VectorToImageTransform.Column()
{
Source = "ImagePixels", Name = "ImageRestored", ImageHeight = imageHeight, ImageWidth = imageWidth, ContainsAlpha = true
}
}
}, pixels);
var fname = nameof(TestBackAndForthConversionWithAlphaNoInterleaveNoOffset) + "_model.zip";
var fh = env.CreateOutputFile(fname);
using (var ch = env.Start("save"))
TrainUtils.SaveModel(env, ch, fh, null, new RoleMappedData(backToBitmaps));
backToBitmaps = ModelFileUtils.LoadPipeline(env, fh.OpenReadStream(), new MultiFileSource(dataFile));
DeleteOutputPath(fname);
backToBitmaps.Schema.TryGetColumnIndex("ImageRestored", out int bitmapColumn);
backToBitmaps.Schema.TryGetColumnIndex("ImageCropped", out int cropBitmapColumn);
using (var cursor = backToBitmaps.GetRowCursor((x) => true))
{
var bitmapGetter = cursor.GetGetter <Bitmap>(bitmapColumn);
Bitmap restoredBitmap = default;
var bitmapCropGetter = cursor.GetGetter <Bitmap>(cropBitmapColumn);
Bitmap croppedBitmap = default;
while (cursor.MoveNext())
{
bitmapGetter(ref restoredBitmap);
Assert.NotNull(restoredBitmap);
bitmapCropGetter(ref croppedBitmap);
Assert.NotNull(croppedBitmap);
for (int x = 0; x < imageWidth; x++)
{
for (int y = 0; y < imageHeight; y++)
{
var c = croppedBitmap.GetPixel(x, y);
var r = restoredBitmap.GetPixel(x, y);
Assert.True(c == r);
}
}
}
}
Done();
}
public void TestOldSavingAndLoading()
{
if (!RuntimeInformation.IsOSPlatform(OSPlatform.Windows))
{
return;
}
var samplevector = getSampleArrayData();
var dataView = ComponentCreation.CreateDataView(Env,
new TestData[] {
new TestData()
{
data_0 = samplevector
}
});
var inputNames = "data_0";
var outputNames = "output_1";
var est = new DnnImageFeaturizerEstimator(Env, m => m.ModelSelector.ResNet18(m.Environment, m.InputColumn, m.OutputColumn), inputNames, outputNames);
var transformer = est.Fit(dataView);
var result = transformer.Transform(dataView);
var resultRoles = new RoleMappedData(result);
using (var ms = new MemoryStream())
{
TrainUtils.SaveModel(Env, Env.Start("saving"), ms, null, resultRoles);
ms.Position = 0;
var loadedView = ModelFileUtils.LoadTransforms(Env, dataView, ms);
loadedView.Schema.TryGetColumnIndex(outputNames, out int softMaxOut1);
using (var cursor = loadedView.GetRowCursor(col => col == softMaxOut1))
{
VBuffer <float> softMaxValue = default;
var softMaxGetter = cursor.GetGetter <VBuffer <float> >(softMaxOut1);
float sum = 0f;
int i = 0;
while (cursor.MoveNext())
{
softMaxGetter(ref softMaxValue);
var values = softMaxValue.DenseValues();
foreach (var val in values)
{
sum += val;
if (i == 0)
{
Assert.InRange(val, 0.0, 0.00001);
}
if (i == 7)
{
Assert.InRange(val, 0.62935, 0.62940);
}
if (i == 500)
{
Assert.InRange(val, 0.15521, 0.155225);
}
i++;
}
}
Assert.InRange(sum, 83.50, 84.50);
}
}
}
public void Run()
{
string template;
using (var stream = Assembly.GetExecutingAssembly().GetManifestResourceStream(CodeTemplatePath))
using (var reader = new StreamReader(stream))
template = reader.ReadToEnd();
var codeProvider = new CSharpCodeProvider();
using (var fs = File.OpenRead(_args.InputModelFile))
{
var transformPipe = ModelFileUtils.LoadPipeline(_host, fs, new MultiFileSource(null), true);
var pred = _host.LoadPredictorOrNull(fs);
IDataView root;
for (root = transformPipe; root is IDataTransform; root = ((IDataTransform)root).Source)
{
;
}
// root is now the loader.
_host.Assert(root is IDataLoader);
// Loader columns.
var loaderSb = new StringBuilder();
for (int i = 0; i < root.Schema.ColumnCount; i++)
{
if (root.Schema.IsHidden(i))
{
continue;
}
if (loaderSb.Length > 0)
{
loaderSb.AppendLine();
}
ColumnType colType = root.Schema.GetColumnType(i);
CodeGenerationUtils.AppendFieldDeclaration(codeProvider, loaderSb, i, root.Schema.GetColumnName(i), colType, true, _args.SparseVectorDeclaration);
}
// Scored example columns.
IDataView scorer;
if (pred == null)
{
scorer = transformPipe;
}
else
{
var roles = ModelFileUtils.LoadRoleMappingsOrNull(_host, fs);
scorer = roles != null
? _host.CreateDefaultScorer(new RoleMappedData(transformPipe, roles, opt : true), pred)
: _host.CreateDefaultScorer(new RoleMappedData(transformPipe, label : null, "Features"), pred);
}
var nonScoreSb = new StringBuilder();
var scoreSb = new StringBuilder();
for (int i = 0; i < scorer.Schema.ColumnCount; i++)
{
if (scorer.Schema.IsHidden(i))
{
continue;
}
bool isScoreColumn = scorer.Schema.GetMetadataTypeOrNull(MetadataUtils.Kinds.ScoreColumnSetId, i) != null;
var sb = isScoreColumn ? scoreSb : nonScoreSb;
if (sb.Length > 0)
{
sb.AppendLine();
}
ColumnType colType = scorer.Schema.GetColumnType(i);
CodeGenerationUtils.AppendFieldDeclaration(codeProvider, sb, i, scorer.Schema.GetColumnName(i), colType, false, _args.SparseVectorDeclaration);
}
// Turn model path into a C# identifier and insert it.
var modelPath = !string.IsNullOrWhiteSpace(_args.ModelNameOverride) ? _args.ModelNameOverride : _args.InputModelFile;
modelPath = CodeGenerationUtils.GetCSharpString(codeProvider, modelPath);
modelPath = string.Format("modelPath = {0};", modelPath);
// Replace values inside the template.
var replacementMap =
new Dictionary <string, string>
{
{ "EXAMPLE_CLASS_DECL", loaderSb.ToString() },
{ "SCORED_EXAMPLE_CLASS_DECL", nonScoreSb.ToString() },
{ "SCORE_CLASS_DECL", scoreSb.ToString() },
{ "MODEL_PATH", modelPath }
};
var classSource = CodeGenerationUtils.MultiReplace(template, replacementMap);
File.WriteAllText(_args.CSharpOutput, classSource);
}
}
public void TestOldSavingAndLoading()
{
var data = new[] {
new TestClass()
{
A = 1, B = 3, C = new float[2] {
1, 2
}, D = new double[2] {
3, 4
}
},
new TestClass()
{
A = float.NaN, B = double.NaN, C = new float[2] {
float.NaN, float.NaN
}, D = new double[2] {
double.NaN, double.NaN
}
},
new TestClass()
{
A = float.NegativeInfinity, B = double.NegativeInfinity, C = new float[2] {
float.NegativeInfinity, float.NegativeInfinity
}, D = new double[2] {
double.NegativeInfinity, double.NegativeInfinity
}
},
new TestClass()
{
A = float.PositiveInfinity, B = double.PositiveInfinity, C = new float[2] {
float.PositiveInfinity, float.PositiveInfinity,
}, D = new double[2] {
double.PositiveInfinity, double.PositiveInfinity
}
},
new TestClass()
{
A = 2, B = 1, C = new float[2] {
3, 4
}, D = new double[2] {
5, 6
}
},
};
var dataView = ComponentCreation.CreateDataView(Env, data);
var pipe = new NAReplaceEstimator(Env,
new NAReplaceTransform.ColumnInfo("A", "NAA", NAReplaceTransform.ColumnInfo.ReplacementMode.Mean),
new NAReplaceTransform.ColumnInfo("B", "NAB", NAReplaceTransform.ColumnInfo.ReplacementMode.Mean),
new NAReplaceTransform.ColumnInfo("C", "NAC", NAReplaceTransform.ColumnInfo.ReplacementMode.Mean),
new NAReplaceTransform.ColumnInfo("D", "NAD", NAReplaceTransform.ColumnInfo.ReplacementMode.Mean));
var result = pipe.Fit(dataView).Transform(dataView);
var resultRoles = new RoleMappedData(result);
using (var ms = new MemoryStream())
{
TrainUtils.SaveModel(Env, Env.Start("saving"), ms, null, resultRoles);
ms.Position = 0;
var loadedView = ModelFileUtils.LoadTransforms(Env, dataView, ms);
}
}
/// <summary>
/// Finalize the test on a transform, calls the transform,
/// saves the data, saves the models, loads it back, saves the data again,
/// checks the output is the same.
/// </summary>
/// <param name="env">environment</param>
/// <param name="outModelFilePath"model filename</param>
/// <param name="transform">transform to test</param>
/// <param name="source">source (view before applying the transform</param>
/// <param name="outData">fist data file</param>
/// <param name="outData2">second data file</param>
/// <param name="startsWith">Check that outputs is the same on disk after outputting the transformed data after the model was serialized</param>
public static void SerializationTestTransform(IHostEnvironment env,
string outModelFilePath, IDataTransform transform,
IDataView source, string outData, string outData2,
bool startsWith = false, bool skipDoubleQuote = false,
bool forceDense = false)
{
// Saves model.
var roles = env.CreateExamples(transform, null);
using (var ch = env.Start("SaveModel"))
using (var fs = File.Create(outModelFilePath))
TrainUtils.SaveModel(env, ch, fs, null, roles);
if (!File.Exists(outModelFilePath))
{
throw new FileNotFoundException(outModelFilePath);
}
// We load it again.
using (var fs = File.OpenRead(outModelFilePath))
{
var tr2 = ModelFileUtils.LoadTransforms(env, source, fs);
if (tr2 == null)
{
throw new Exception(string.Format("Unable to load '{0}'", outModelFilePath));
}
if (transform.GetType() != tr2.GetType())
{
throw new Exception(string.Format("Type mismatch {0} != {1}", transform.GetType(), tr2.GetType()));
}
}
// Checks the outputs.
var saver = env.CreateSaver(forceDense ? "Text{dense=+}" : "Text");
var columns = new int[transform.Schema.Count];
for (int i = 0; i < columns.Length; ++i)
{
columns[i] = i;
}
using (var fs2 = File.Create(outData))
saver.SaveData(fs2, transform, columns);
if (!File.Exists(outModelFilePath))
{
throw new FileNotFoundException(outData);
}
// Check we have the same output.
using (var fs = File.OpenRead(outModelFilePath))
{
var tr = ModelFileUtils.LoadTransforms(env, source, fs);
saver = env.CreateSaver(forceDense ? "Text{dense=+}" : "Text");
using (var fs2 = File.Create(outData2))
saver.SaveData(fs2, tr, columns);
}
var t1 = File.ReadAllLines(outData);
var t2 = File.ReadAllLines(outData2);
if (t1.Length != t2.Length)
{
throw new Exception(string.Format("Not the same number of lines: {0} != {1}", t1.Length, t2.Length));
}
for (int i = 0; i < t1.Length; ++i)
{
if (skipDoubleQuote && (t1[i].Contains("\"\"\t\"\"") || t2[i].Contains("\"\"\t\"\"")))
{
continue;
}
if ((startsWith && !t1[i].StartsWith(t2[i])) || (!startsWith && t1[i] != t2[i]))
{
if (t1[i].EndsWith("\t5\t0:\"\""))
{
var a = t1[i].Substring(0, t1[i].Length - "\t5\t0:\"\"".Length);
a += "\t\"\"\t\"\"\t\"\"\t\"\"\t\"\"";
var b = t2[i];
if ((startsWith && !a.StartsWith(b)) || (!startsWith && a != b))
{
throw new Exception(string.Format("2-Mismatch on line {0}/{3}:\n{1}\n{2}", i, t1[i], t2[i], t1.Length));
}
}
else
{
// The test might fail because one side is dense and the other is sparse.
throw new Exception(string.Format("3-Mismatch on line {0}/{3}:\n{1}\n{2}", i, t1[i], t2[i], t1.Length));
}
}
}
}
public void TestOldSavingAndLoading()
{
//skip running for x86 as this test using too much memory (over 2GB limit on x86)
//and very like to hit memory related issue when running on CI
//TODO: optimized memory usage in related code and enable x86 run
if (!Environment.Is64BitProcess)
{
return;
}
var samplevector = GetSampleArrayData();
var dataView = ML.Data.LoadFromEnumerable(
new TestData[] {
new TestData()
{
data_0 = samplevector
}
});
var inputNames = "data_0";
var outputNames = "output_1";
var est = ML.Transforms.DnnFeaturizeImage(outputNames, m => m.ModelSelector.ResNet18(m.Environment, m.OutputColumn, m.InputColumn), inputNames);
var transformer = est.Fit(dataView);
var result = transformer.Transform(dataView);
var resultRoles = new RoleMappedData(result);
using (var ms = new MemoryStream())
{
TrainUtils.SaveModel(Env, Env.Start("saving"), ms, null, resultRoles);
ms.Position = 0;
var loadedView = ModelFileUtils.LoadTransforms(Env, dataView, ms);
using (var cursor = loadedView.GetRowCursor(loadedView.Schema[outputNames]))
{
VBuffer <float> softMaxValue = default;
var softMaxGetter = cursor.GetGetter <VBuffer <float> >(loadedView.Schema[outputNames]);
float sum = 0f;
int i = 0;
while (cursor.MoveNext())
{
softMaxGetter(ref softMaxValue);
var values = softMaxValue.DenseValues();
foreach (var val in values)
{
sum += val;
if (i == 0)
{
Assert.InRange(val, 0.0, 0.00001);
}
if (i == 7)
{
Assert.InRange(val, 0.62935, 0.62940);
}
if (i == 500)
{
Assert.InRange(val, 0.15521, 0.155225);
}
i++;
}
}
Assert.InRange(sum, 83.50, 84.50);
}
}
}
public void TestBackAndForthConversionWithDifferentOrder()
{
if (RuntimeInformation.IsOSPlatform(OSPlatform.OSX))
{
return;
}
IHostEnvironment env = new MLContext();
const int imageHeight = 100;
const int imageWidth = 130;
var dataFile = GetDataPath("images/images.tsv");
var imageFolder = Path.GetDirectoryName(dataFile);
var data = TextLoader.Create(env, new TextLoader.Options()
{
Columns = new[]
{
new TextLoader.Column("ImagePath", DataKind.String, 0),
new TextLoader.Column("Name", DataKind.String, 1),
}
}, new MultiFileSource(dataFile));
var images = new ImageLoadingTransformer(env, imageFolder, ("ImageReal", "ImagePath")).Transform(data);
var cropped = new ImageResizingTransformer(env, "ImageCropped", imageWidth, imageHeight, "ImageReal").Transform(images);
var pixels = new ImagePixelExtractingTransformer(env, "ImagePixels", "ImageCropped", ImagePixelExtractingEstimator.ColorBits.All, orderOfExtraction: ImagePixelExtractingEstimator.ColorsOrder.ABRG).Transform(cropped);
IDataView backToBitmaps = new VectorToImageConvertingTransformer(env, "ImageRestored", imageHeight, imageWidth, "ImagePixels",
ImagePixelExtractingEstimator.ColorBits.All, orderOfColors: ImagePixelExtractingEstimator.ColorsOrder.ABRG).Transform(pixels);
var fname = nameof(TestBackAndForthConversionWithDifferentOrder) + "_model.zip";
var fh = env.CreateOutputFile(fname);
using (var ch = env.Start("save"))
TrainUtils.SaveModel(env, ch, fh, null, new RoleMappedData(backToBitmaps));
backToBitmaps = ModelFileUtils.LoadPipeline(env, fh.OpenReadStream(), new MultiFileSource(dataFile));
DeleteOutputPath(fname);
using (var cursor = backToBitmaps.GetRowCursorForAllColumns())
{
var bitmapGetter = cursor.GetGetter <Bitmap>(backToBitmaps.Schema["ImageRestored"]);
Bitmap restoredBitmap = default;
var bitmapCropGetter = cursor.GetGetter <Bitmap>(backToBitmaps.Schema["ImageCropped"]);
Bitmap croppedBitmap = default;
while (cursor.MoveNext())
{
bitmapGetter(ref restoredBitmap);
Assert.NotNull(restoredBitmap);
bitmapCropGetter(ref croppedBitmap);
Assert.NotNull(croppedBitmap);
for (int x = 0; x < imageWidth; x++)
{
for (int y = 0; y < imageHeight; y++)
{
var c = croppedBitmap.GetPixel(x, y);
var r = restoredBitmap.GetPixel(x, y);
if (c != r)
{
Assert.False(true);
}
Assert.True(c == r);
}
}
}
}
Done();
}
