TensorflowCatalog.LoadTensorFlowModel Método
Definição
Importante
Algumas informações se referem a produtos de pré-lançamento que podem ser substancialmente modificados antes do lançamento. A Microsoft não oferece garantias, expressas ou implícitas, das informações aqui fornecidas.
Sobrecargas
| LoadTensorFlowModel(ModelOperationsCatalog, String) |
Carregue o modelo tensorFlow na memória. Esse é o método de conveniência que permite que o modelo seja carregado uma vez e posteriormente usá-lo para consultar o esquema e a criação do TensorFlowEstimator uso ScoreTensorFlowModel(String, String, Boolean). O uso dessa API requer dependências adicionais do NuGet no TensorFlow redist, consulte o documento vinculado para obter mais informações. TensorFlowModel também contém referências a recursos não gerenciados que precisam ser liberados com uma chamada explícita para Dispose() ou implicitamente declarando a variável com a sintaxe "using" /> |
| LoadTensorFlowModel(ModelOperationsCatalog, String, Boolean) |
Carregue o modelo tensorFlow na memória. Esse é o método de conveniência que permite que o modelo seja carregado uma vez e posteriormente usá-lo para consultar o esquema e a criação do TensorFlowEstimator uso ScoreTensorFlowModel(String, String, Boolean). O uso dessa API requer dependências adicionais do NuGet no TensorFlow redist, consulte o documento vinculado para obter mais informações. TensorFlowModel também contém referências a recursos não gerenciados que precisam ser liberados com uma chamada explícita para Dispose() ou implicitamente declarando a variável com a sintaxe "using" /> |
LoadTensorFlowModel(ModelOperationsCatalog, String)
Carregue o modelo tensorFlow na memória. Esse é o método de conveniência que permite que o modelo seja carregado uma vez e posteriormente usá-lo para consultar o esquema e a criação do TensorFlowEstimator uso ScoreTensorFlowModel(String, String, Boolean). O uso dessa API requer dependências adicionais do NuGet no TensorFlow redist, consulte o documento vinculado para obter mais informações. TensorFlowModel também contém referências a recursos não gerenciados que precisam ser liberados com uma chamada explícita para Dispose() ou implicitamente declarando a variável com a sintaxe "using" />
public static Microsoft.ML.Transforms.TensorFlowModel LoadTensorFlowModel (this Microsoft.ML.ModelOperationsCatalog catalog, string modelLocation);static member LoadTensorFlowModel : Microsoft.ML.ModelOperationsCatalog * string -> Microsoft.ML.Transforms.TensorFlowModel<Extension()>
Public Function LoadTensorFlowModel (catalog As ModelOperationsCatalog, modelLocation As String) As TensorFlowModelParâmetros
- catalog
- ModelOperationsCatalog
O catálogo da transformação.
- modelLocation
- String
Local do modelo TensorFlow.
Retornos
Exemplos
using System;
using System.IO;
using Microsoft.ML;
using Microsoft.ML.Data;
namespace Samples.Dynamic
{
public static class TextClassification
{
public const int MaxSentenceLength = 600;
/// <summary>
/// Example use of the TensorFlow sentiment classification model.
/// </summary>
public static void Example()
{
// Download an unfrozen (SavedModel format) pre-trained sentiment
// model and return the path to the model directory.
string modelLocation = Microsoft.ML.SamplesUtils.DatasetUtils
.DownloadTensorFlowSentimentModel();
var mlContext = new MLContext();
var data = new[] { new IMDBSentiment() {
Sentiment_Text = "this film was just brilliant casting location " +
"scenery story direction everyone's really suited the part they " +
"played and you could just imagine being there robert is an " +
"amazing actor and now the same being director father came from " +
"the same scottish island as myself so i loved the fact there " +
"was a real connection with this film the witty remarks " +
"throughout the film were great it was just brilliant so much " +
"that i bought the film as soon as it was released for and " +
"would recommend it to everyone to watch and the fly fishing was " +
"amazing really cried at the end it was so sad and you know what " +
"they say if you cry at a film it must have been good and this " +
"definitely was also to the two little boy's that played the of " +
"norman and paul they were just brilliant children are often " +
"left out of the list i think because the stars that play them " +
"all grown up are such a big profile for the whole film but " +
"these children are amazing and should be praised for what " +
"they have done don't you think the whole story was so lovely" +
"because it was true and was someone's life after all that was" +
"shared with us all" } };
var dataView = mlContext.Data.LoadFromEnumerable(data);
// This is the dictionary to convert words into the integer indexes.
var lookupMap = mlContext.Data.LoadFromTextFile(Path.Combine(
modelLocation, "imdb_word_index.csv"),
columns: new[]
{
new TextLoader.Column("Words", DataKind.String, 0),
new TextLoader.Column("Ids", DataKind.Int32, 1),
},
separatorChar: ','
);
// Load the TensorFlow model once.
// - Use it for querying the schema for input and output in the
// model
// - Use it for prediction in the pipeline.
// Unfrozen (SavedModel format) models are loaded by providing the
// path to the directory containing the model file and other model
// artifacts like pre-trained weights.
using var tensorFlowModel = mlContext.Model.LoadTensorFlowModel(
modelLocation);
var schema = tensorFlowModel.GetModelSchema();
var featuresType = (VectorDataViewType)schema["Features"].Type;
Console.WriteLine("Name: {0}, Type: {1}, Shape: (-1, {2})", "Features",
featuresType.ItemType.RawType, featuresType.Dimensions[0]);
var predictionType = (VectorDataViewType)schema["Prediction/Softmax"]
.Type;
Console.WriteLine("Name: {0}, Type: {1}, Shape: (-1, {2})",
"Prediction/Softmax", predictionType.ItemType.RawType,
predictionType.Dimensions[0]);
// The model expects the input feature vector to be a fixed length
// vector.
// In this sample, CustomMappingEstimator is used to resize variable
// length vector to fixed length vector.
// The following ML.NET pipeline
// 1. tokenizes the string into words,
// 2. maps each word to an integer which is an index in the
// dictionary ('lookupMap'),
// 3. Resizes the integer vector to a fixed length vector using
// CustomMappingEstimator ('ResizeFeaturesAction')
// 4. Passes the data to TensorFlow for scoring.
// 5. Retreives the 'Prediction' from TensorFlow and put it into
// ML.NET Pipeline
Action<IMDBSentiment, IntermediateFeatures> ResizeFeaturesAction =
(i, j) =>
{
j.Sentiment_Text = i.Sentiment_Text;
var features = i.VariableLengthFeatures;
Array.Resize(ref features, MaxSentenceLength);
j.Features = features;
};
var model =
mlContext.Transforms.Text.TokenizeIntoWords(
"TokenizedWords",
"Sentiment_Text")
.Append(mlContext.Transforms.Conversion.MapValue(
"VariableLengthFeatures",
lookupMap,
lookupMap.Schema["Words"],
lookupMap.Schema["Ids"],
"TokenizedWords"))
.Append(mlContext.Transforms.CustomMapping(
ResizeFeaturesAction,
"Resize"))
.Append(tensorFlowModel.ScoreTensorFlowModel(
"Prediction/Softmax",
"Features"))
.Append(mlContext.Transforms.CopyColumns(
"Prediction",
"Prediction/Softmax"))
.Fit(dataView);
var engine = mlContext.Model.CreatePredictionEngine<IMDBSentiment,
OutputScores>(model);
// Predict with TensorFlow pipeline.
var prediction = engine.Predict(data[0]);
Console.WriteLine("Number of classes: {0}", prediction.Prediction
.Length);
Console.WriteLine("Is sentiment/review positive? {0}", prediction
.Prediction[1] > 0.5 ? "Yes." : "No.");
Console.WriteLine("Prediction Confidence: {0}", prediction.Prediction[1]
.ToString("0.00"));
///////////////////////////// Expected output //////////////////////////
//
// Name: Features, Type: System.Int32, Shape: (-1, 600)
// Name: Prediction/Softmax, Type: System.Single, Shape: (-1, 2)
//
// Number of classes: 2
// Is sentiment/review positive ? Yes
// Prediction Confidence: 0.65
}
/// <summary>
/// Class to hold original sentiment data.
/// </summary>
public class IMDBSentiment
{
public string Sentiment_Text { get; set; }
/// <summary>
/// This is a variable length vector designated by VectorType attribute.
/// Variable length vectors are produced by applying operations such as
/// 'TokenizeWords' on strings resulting in vectors of tokens of
/// variable lengths.
/// </summary>
[VectorType]
public int[] VariableLengthFeatures { get; set; }
}
/// <summary>
/// Class to hold intermediate data. Mostly used by CustomMapping Estimator
/// </summary>
public class IntermediateFeatures
{
public string Sentiment_Text { get; set; }
[VectorType(MaxSentenceLength)]
public int[] Features { get; set; }
}
/// <summary>
/// Class to contain the output values from the transformation.
/// </summary>
class OutputScores
{
[VectorType(2)]
public float[] Prediction { get; set; }
}
}
}
Aplica-se a
LoadTensorFlowModel(ModelOperationsCatalog, String, Boolean)
Carregue o modelo tensorFlow na memória. Esse é o método de conveniência que permite que o modelo seja carregado uma vez e posteriormente usá-lo para consultar o esquema e a criação do TensorFlowEstimator uso ScoreTensorFlowModel(String, String, Boolean). O uso dessa API requer dependências adicionais do NuGet no TensorFlow redist, consulte o documento vinculado para obter mais informações. TensorFlowModel também contém referências a recursos não gerenciados que precisam ser liberados com uma chamada explícita para Dispose() ou implicitamente declarando a variável com a sintaxe "using" />
public static Microsoft.ML.Transforms.TensorFlowModel LoadTensorFlowModel (this Microsoft.ML.ModelOperationsCatalog catalog, string modelLocation, bool treatOutputAsBatched);static member LoadTensorFlowModel : Microsoft.ML.ModelOperationsCatalog * string * bool -> Microsoft.ML.Transforms.TensorFlowModel<Extension()>
Public Function LoadTensorFlowModel (catalog As ModelOperationsCatalog, modelLocation As String, treatOutputAsBatched As Boolean) As TensorFlowModelParâmetros
- catalog
- ModelOperationsCatalog
O catálogo da transformação.
- modelLocation
- String
Local do modelo TensorFlow.
- treatOutputAsBatched
- Boolean
Se a primeira dimensão da saída for desconhecida, ela deverá ser tratada como lote ou não.
Retornos
Exemplos
using System;
using System.IO;
using Microsoft.ML;
using Microsoft.ML.Data;
namespace Samples.Dynamic
{
public static class TextClassification
{
public const int MaxSentenceLength = 600;
/// <summary>
/// Example use of the TensorFlow sentiment classification model.
/// </summary>
public static void Example()
{
// Download an unfrozen (SavedModel format) pre-trained sentiment
// model and return the path to the model directory.
string modelLocation = Microsoft.ML.SamplesUtils.DatasetUtils
.DownloadTensorFlowSentimentModel();
var mlContext = new MLContext();
var data = new[] { new IMDBSentiment() {
Sentiment_Text = "this film was just brilliant casting location " +
"scenery story direction everyone's really suited the part they " +
"played and you could just imagine being there robert is an " +
"amazing actor and now the same being director father came from " +
"the same scottish island as myself so i loved the fact there " +
"was a real connection with this film the witty remarks " +
"throughout the film were great it was just brilliant so much " +
"that i bought the film as soon as it was released for and " +
"would recommend it to everyone to watch and the fly fishing was " +
"amazing really cried at the end it was so sad and you know what " +
"they say if you cry at a film it must have been good and this " +
"definitely was also to the two little boy's that played the of " +
"norman and paul they were just brilliant children are often " +
"left out of the list i think because the stars that play them " +
"all grown up are such a big profile for the whole film but " +
"these children are amazing and should be praised for what " +
"they have done don't you think the whole story was so lovely" +
"because it was true and was someone's life after all that was" +
"shared with us all" } };
var dataView = mlContext.Data.LoadFromEnumerable(data);
// This is the dictionary to convert words into the integer indexes.
var lookupMap = mlContext.Data.LoadFromTextFile(Path.Combine(
modelLocation, "imdb_word_index.csv"),
columns: new[]
{
new TextLoader.Column("Words", DataKind.String, 0),
new TextLoader.Column("Ids", DataKind.Int32, 1),
},
separatorChar: ','
);
// Load the TensorFlow model once.
// - Use it for querying the schema for input and output in the
// model
// - Use it for prediction in the pipeline.
// Unfrozen (SavedModel format) models are loaded by providing the
// path to the directory containing the model file and other model
// artifacts like pre-trained weights.
using var tensorFlowModel = mlContext.Model.LoadTensorFlowModel(
modelLocation);
var schema = tensorFlowModel.GetModelSchema();
var featuresType = (VectorDataViewType)schema["Features"].Type;
Console.WriteLine("Name: {0}, Type: {1}, Shape: (-1, {2})", "Features",
featuresType.ItemType.RawType, featuresType.Dimensions[0]);
var predictionType = (VectorDataViewType)schema["Prediction/Softmax"]
.Type;
Console.WriteLine("Name: {0}, Type: {1}, Shape: (-1, {2})",
"Prediction/Softmax", predictionType.ItemType.RawType,
predictionType.Dimensions[0]);
// The model expects the input feature vector to be a fixed length
// vector.
// In this sample, CustomMappingEstimator is used to resize variable
// length vector to fixed length vector.
// The following ML.NET pipeline
// 1. tokenizes the string into words,
// 2. maps each word to an integer which is an index in the
// dictionary ('lookupMap'),
// 3. Resizes the integer vector to a fixed length vector using
// CustomMappingEstimator ('ResizeFeaturesAction')
// 4. Passes the data to TensorFlow for scoring.
// 5. Retreives the 'Prediction' from TensorFlow and put it into
// ML.NET Pipeline
Action<IMDBSentiment, IntermediateFeatures> ResizeFeaturesAction =
(i, j) =>
{
j.Sentiment_Text = i.Sentiment_Text;
var features = i.VariableLengthFeatures;
Array.Resize(ref features, MaxSentenceLength);
j.Features = features;
};
var model =
mlContext.Transforms.Text.TokenizeIntoWords(
"TokenizedWords",
"Sentiment_Text")
.Append(mlContext.Transforms.Conversion.MapValue(
"VariableLengthFeatures",
lookupMap,
lookupMap.Schema["Words"],
lookupMap.Schema["Ids"],
"TokenizedWords"))
.Append(mlContext.Transforms.CustomMapping(
ResizeFeaturesAction,
"Resize"))
.Append(tensorFlowModel.ScoreTensorFlowModel(
"Prediction/Softmax",
"Features"))
.Append(mlContext.Transforms.CopyColumns(
"Prediction",
"Prediction/Softmax"))
.Fit(dataView);
var engine = mlContext.Model.CreatePredictionEngine<IMDBSentiment,
OutputScores>(model);
// Predict with TensorFlow pipeline.
var prediction = engine.Predict(data[0]);
Console.WriteLine("Number of classes: {0}", prediction.Prediction
.Length);
Console.WriteLine("Is sentiment/review positive? {0}", prediction
.Prediction[1] > 0.5 ? "Yes." : "No.");
Console.WriteLine("Prediction Confidence: {0}", prediction.Prediction[1]
.ToString("0.00"));
///////////////////////////// Expected output //////////////////////////
//
// Name: Features, Type: System.Int32, Shape: (-1, 600)
// Name: Prediction/Softmax, Type: System.Single, Shape: (-1, 2)
//
// Number of classes: 2
// Is sentiment/review positive ? Yes
// Prediction Confidence: 0.65
}
/// <summary>
/// Class to hold original sentiment data.
/// </summary>
public class IMDBSentiment
{
public string Sentiment_Text { get; set; }
/// <summary>
/// This is a variable length vector designated by VectorType attribute.
/// Variable length vectors are produced by applying operations such as
/// 'TokenizeWords' on strings resulting in vectors of tokens of
/// variable lengths.
/// </summary>
[VectorType]
public int[] VariableLengthFeatures { get; set; }
}
/// <summary>
/// Class to hold intermediate data. Mostly used by CustomMapping Estimator
/// </summary>
public class IntermediateFeatures
{
public string Sentiment_Text { get; set; }
[VectorType(MaxSentenceLength)]
public int[] Features { get; set; }
}
/// <summary>
/// Class to contain the output values from the transformation.
/// </summary>
class OutputScores
{
[VectorType(2)]
public float[] Prediction { get; set; }
}
}
}