Table of Contents

Class LayoutLMv3<T>

Namespace
AiDotNet.Document.LayoutAware
Assembly
AiDotNet.dll

LayoutLMv3 neural network for document understanding with unified text and image pre-training.

public class LayoutLMv3<T> : DocumentNeuralNetworkBase<T>, INeuralNetworkModel<T>, INeuralNetwork<T>, IInterpretableModel<T>, IInputGradientComputable<T>, IDisposable, ILayoutDetector<T>, IDocumentQA<T>, IDocumentModel<T>, IFullModel<T, Tensor<T>, Tensor<T>>, IModel<Tensor<T>, Tensor<T>, ModelMetadata<T>>, IModelSerializer, ICheckpointableModel, IParameterizable<T, Tensor<T>, Tensor<T>>, IFeatureAware, IFeatureImportance<T>, ICloneable<IFullModel<T, Tensor<T>, Tensor<T>>>, IGradientComputable<T, Tensor<T>, Tensor<T>>, IJitCompilable<T>

Type Parameters

T

The numeric type used for calculations.

Inheritance
LayoutLMv3<T>
Implements
IFullModel<T, Tensor<T>, Tensor<T>>
IModel<Tensor<T>, Tensor<T>, ModelMetadata<T>>
IParameterizable<T, Tensor<T>, Tensor<T>>
ICloneable<IFullModel<T, Tensor<T>, Tensor<T>>>
IGradientComputable<T, Tensor<T>, Tensor<T>>
Inherited Members
Extension Methods

Remarks

LayoutLMv3 is the third generation of the LayoutLM series from Microsoft Research, featuring unified multimodal pre-training with masked image modeling and masked language modeling on the same architecture.

For Beginners: LayoutLMv3 understands documents by learning from: 1. The text content (what the words say) 2. The visual appearance (what the document looks like) 3. The layout structure (where elements are positioned)

This makes it excellent for:

  • Extracting information from forms and receipts
  • Understanding document structure
  • Answering questions about document content
  • Classifying document types

Example usage (ONNX mode - for inference with pre-trained models):

var model = new LayoutLMv3<float>(architecture, "model.onnx", tokenizer);
var layout = model.DetectLayout(documentImage);

Example usage (Native mode - for training):

var model = new LayoutLMv3<float>(architecture);
model.Train(trainingData, labels);

Reference: "LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking" https://arxiv.org/abs/2204.08387

Constructors

LayoutLMv3(NeuralNetworkArchitecture<T>, ITokenizer?, int, int, int, int, int, int, int, int, IOptimizer<T, Tensor<T>, Tensor<T>>?, ILossFunction<T>?)

Creates a LayoutLMv3 model using native layers for training and inference.

public LayoutLMv3(NeuralNetworkArchitecture<T> architecture, ITokenizer? tokenizer = null, int numClasses = 17, int imageSize = 224, int patchSize = 16, int maxSequenceLength = 512, int hiddenDim = 768, int numLayers = 12, int numHeads = 12, int vocabSize = 50265, IOptimizer<T, Tensor<T>, Tensor<T>>? optimizer = null, ILossFunction<T>? lossFunction = null)

Parameters

architecture NeuralNetworkArchitecture<T>

The neural network architecture.

tokenizer ITokenizer

Tokenizer for text processing (optional, default created if null).

numClasses int

Number of output classes for classification tasks.

imageSize int

Expected input image size (default: 224 from paper).

patchSize int

Vision transformer patch size (default: 16 from paper).

maxSequenceLength int

Maximum sequence length (default: 512).

hiddenDim int

Hidden dimension size (default: 768 for LayoutLMv3-Base).

numLayers int

Number of transformer layers (default: 12 for Base).

numHeads int

Number of attention heads (default: 12 for Base).

vocabSize int

Vocabulary size (default: 50265 for RoBERTa).

optimizer IOptimizer<T, Tensor<T>, Tensor<T>>

Optimizer for training (optional, Adam used if null).

lossFunction ILossFunction<T>

Loss function (optional, CrossEntropy used if null).

Remarks

Default Configuration (LayoutLMv3-Base from ICCV 2022 paper): - Hidden dimension: 768 - Transformer layers: 12 - Attention heads: 12 - Image size: 224×224 - Patch size: 16 - Max sequence length: 512

LayoutLMv3(NeuralNetworkArchitecture<T>, string, ITokenizer, int, int, int, int, int, int, int, IOptimizer<T, Tensor<T>, Tensor<T>>?, ILossFunction<T>?)

Creates a LayoutLMv3 model using a pre-trained ONNX model for inference.

public LayoutLMv3(NeuralNetworkArchitecture<T> architecture, string onnxModelPath, ITokenizer tokenizer, int numClasses = 17, int imageSize = 224, int maxSequenceLength = 512, int hiddenDim = 768, int numLayers = 12, int numHeads = 12, int vocabSize = 50265, IOptimizer<T, Tensor<T>, Tensor<T>>? optimizer = null, ILossFunction<T>? lossFunction = null)

Parameters

architecture NeuralNetworkArchitecture<T>

The neural network architecture.

onnxModelPath string

Path to the ONNX model file.

tokenizer ITokenizer

Tokenizer for text processing.

numClasses int

Number of output classes for classification tasks.

imageSize int

Expected input image size (default: 224).

maxSequenceLength int

Maximum sequence length (default: 512).

hiddenDim int

Hidden dimension size (default: 768).

numLayers int

Number of transformer layers (default: 12).

numHeads int

Number of attention heads (default: 12).

vocabSize int

Vocabulary size (default: 50265 for RoBERTa).

optimizer IOptimizer<T, Tensor<T>, Tensor<T>>

Optimizer for training (optional, Adam used if null).

lossFunction ILossFunction<T>

Loss function (optional, CrossEntropy used if null).

Exceptions

ArgumentNullException

Thrown if onnxModelPath or tokenizer is null.

FileNotFoundException

Thrown if the ONNX model file doesn't exist.

Properties

ExpectedImageSize

Gets the expected input image size (assumes square images).

public int ExpectedImageSize { get; }

Property Value

int

Remarks

Common values: 224 (ViT base), 384, 448, 512, 768, 1024. Input images will be resized to [ImageSize x ImageSize] before processing.

RequiresOCR

Gets whether this model requires OCR preprocessing.

public override bool RequiresOCR { get; }

Property Value

bool

Remarks

Layout-aware models (LayoutLM, etc.) require OCR to provide text and bounding boxes. OCR-free models (Donut, Pix2Struct) process raw pixels directly.

SupportedDocumentTypes

Gets the supported document types for this model.

public override DocumentType SupportedDocumentTypes { get; }

Property Value

DocumentType

SupportedElementTypes

Gets the layout element types this detector can identify.

public IReadOnlyList<LayoutElementType> SupportedElementTypes { get; }

Property Value

IReadOnlyList<LayoutElementType>

Methods

AnswerQuestion(Tensor<T>, string)

Answers a question about a document.

public DocumentQAResult<T> AnswerQuestion(Tensor<T> documentImage, string question)

Parameters

documentImage Tensor<T>

The document image tensor.

question string

The question to answer in natural language.

Returns

DocumentQAResult<T>

The answer with confidence and evidence information.

AnswerQuestion(Tensor<T>, string, int, double)

Answers a question with generation parameters.

public DocumentQAResult<T> AnswerQuestion(Tensor<T> documentImage, string question, int maxAnswerLength, double temperature = 0)

Parameters

documentImage Tensor<T>

The document image tensor.

question string

The question to answer.

maxAnswerLength int

Maximum length of the generated answer.

temperature double

Sampling temperature for generation (0 = deterministic).

Returns

DocumentQAResult<T>

The answer result.

AnswerQuestions(Tensor<T>, IEnumerable<string>)

Answers multiple questions about a document in a batch.

public IEnumerable<DocumentQAResult<T>> AnswerQuestions(Tensor<T> documentImage, IEnumerable<string> questions)

Parameters

documentImage Tensor<T>

The document image tensor.

questions IEnumerable<string>

The questions to answer.

Returns

IEnumerable<DocumentQAResult<T>>

Answers for each question in order.

Remarks

Batching multiple questions is more efficient than calling AnswerQuestion repeatedly because the document encoding can be reused.

ApplyDefaultPostprocessing(Tensor<T>)

Applies LayoutLMv3's industry-standard postprocessing: softmax for classification outputs.

protected override Tensor<T> ApplyDefaultPostprocessing(Tensor<T> modelOutput)

Parameters

modelOutput Tensor<T>

Returns

Tensor<T>

ApplyDefaultPreprocessing(Tensor<T>)

Applies LayoutLMv3's industry-standard preprocessing: ImageNet normalization.

protected override Tensor<T> ApplyDefaultPreprocessing(Tensor<T> rawImage)

Parameters

rawImage Tensor<T>

Returns

Tensor<T>

Remarks

LayoutLMv3 (Microsoft paper) uses ImageNet normalization with mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225]. The unified architecture for multimodal document understanding.

CreateNewInstance()

Creates a new instance of the same type as this neural network.

protected override IFullModel<T, Tensor<T>, Tensor<T>> CreateNewInstance()

Returns

IFullModel<T, Tensor<T>, Tensor<T>>

A new instance of the same neural network type.

Remarks

For Beginners: This creates a blank version of the same type of neural network.

It's used internally by methods like DeepCopy and Clone to create the right type of network before copying the data into it.

DeserializeNetworkSpecificData(BinaryReader)

Deserializes network-specific data that was not covered by the general deserialization process.

protected override void DeserializeNetworkSpecificData(BinaryReader reader)

Parameters

reader BinaryReader

The BinaryReader to read the data from.

Remarks

This method is called at the end of the general deserialization process to allow derived classes to read any additional data specific to their implementation.

For Beginners: Continuing the suitcase analogy, this is like unpacking that special compartment. After the main deserialization method has unpacked the common items (layers, parameters), this method allows each specific type of neural network to unpack its own unique items that were stored during serialization.

DetectLayout(Tensor<T>)

Detects layout regions in a document image.

public DocumentLayoutResult<T> DetectLayout(Tensor<T> documentImage)

Parameters

documentImage Tensor<T>

The document image tensor [batch, channels, height, width].

Returns

DocumentLayoutResult<T>

Layout detection result with regions and their types.

DetectLayout(Tensor<T>, double)

Detects layout regions with a specified confidence threshold.

public DocumentLayoutResult<T> DetectLayout(Tensor<T> documentImage, double confidenceThreshold)

Parameters

documentImage Tensor<T>

The document image tensor.

confidenceThreshold double

Minimum confidence for detected regions (0.0 to 1.0).

Returns

DocumentLayoutResult<T>

Filtered layout detection result.

Remarks

Higher thresholds return fewer but more confident detections. Lower thresholds return more detections but may include false positives.

Dispose(bool)

Disposes of resources used by this model.

protected override void Dispose(bool disposing)

Parameters

disposing bool

True if disposing managed resources.

EncodeDocument(Tensor<T>)

Processes a document image and returns encoded features.

public Tensor<T> EncodeDocument(Tensor<T> documentImage)

Parameters

documentImage Tensor<T>

The document image tensor [batch, channels, height, width] or [channels, height, width].

Returns

Tensor<T>

Encoded document features suitable for downstream tasks.

Remarks

For Beginners: This method converts a document image into a numerical representation (feature vector) that captures the document's content and structure. These features can then be used for tasks like classification, QA, or information extraction.

ExtractFields(Tensor<T>, IEnumerable<string>)

Extracts specific fields from a document using natural language prompts.

public Dictionary<string, DocumentQAResult<T>> ExtractFields(Tensor<T> documentImage, IEnumerable<string> fieldPrompts)

Parameters

documentImage Tensor<T>

The document image tensor.

fieldPrompts IEnumerable<string>

Field names or extraction prompts (e.g., "invoice_number", "total_amount").

Returns

Dictionary<string, DocumentQAResult<T>>

Dictionary mapping field names to their extracted values and confidence.

Remarks

For Beginners: This is a convenient way to extract multiple pieces of information at once. Instead of asking separate questions, you provide a list of field names and the model extracts all of them from the document.

GetModelMetadata()

Gets the metadata for this neural network model.

public override ModelMetadata<T> GetModelMetadata()

Returns

ModelMetadata<T>

A ModelMetaData object containing information about the model.

GetModelSummary()

Gets a summary of the model architecture.

public string GetModelSummary()

Returns

string

A string describing the model's architecture, parameters, and capabilities.

InitializeLayers()

Initializes the layers of the neural network based on the architecture.

protected override void InitializeLayers()

Remarks

For Beginners: This method sets up all the layers in your neural network according to the architecture you've defined. It's like assembling the parts of your network before you can use it.

Predict(Tensor<T>)

Makes a prediction using the neural network.

public override Tensor<T> Predict(Tensor<T> input)

Parameters

input Tensor<T>

The input data to process.

Returns

Tensor<T>

The network's prediction.

Remarks

For Beginners: This is the main method you'll use to get results from your trained neural network. You provide some input data (like an image or text), and the network processes it through all its layers to produce an output (like a classification or prediction).

SerializeNetworkSpecificData(BinaryWriter)

Serializes network-specific data that is not covered by the general serialization process.

protected override void SerializeNetworkSpecificData(BinaryWriter writer)

Parameters

writer BinaryWriter

The BinaryWriter to write the data to.

Remarks

This method is called at the end of the general serialization process to allow derived classes to write any additional data specific to their implementation.

For Beginners: Think of this as packing a special compartment in your suitcase. While the main serialization method packs the common items (layers, parameters), this method allows each specific type of neural network to pack its own unique items that other networks might not have.

Train(Tensor<T>, Tensor<T>)

Trains the neural network on a single input-output pair.

public override void Train(Tensor<T> input, Tensor<T> expectedOutput)

Parameters

input Tensor<T>

The input data.

expectedOutput Tensor<T>

The expected output for the given input.

Remarks

This method performs one training step on the neural network using the provided input and expected output. It updates the network's parameters to reduce the error between the network's prediction and the expected output.

For Beginners: This is how your neural network learns. You provide: - An input (what the network should process) - The expected output (what the correct answer should be)

The network then:

  1. Makes a prediction based on the input
  2. Compares its prediction to the expected output
  3. Calculates how wrong it was (the loss)
  4. Adjusts its internal values to do better next time

After training, you can get the loss value using the GetLastLoss() method to see how well the network is learning.

UpdateParameters(Vector<T>)

Updates the network's parameters with new values.

public override void UpdateParameters(Vector<T> gradients)

Parameters

gradients Vector<T>

Remarks

For Beginners: During training, a neural network's internal values (parameters) get adjusted to improve its performance. This method allows you to update all those values at once by providing a complete set of new parameters.

This is typically used by optimization algorithms that calculate better parameter values based on training data.

ValidateInputShape(Tensor<T>)

Validates that an input tensor has the correct shape for this model.

public void ValidateInputShape(Tensor<T> documentImage)

Parameters

documentImage Tensor<T>

The tensor to validate.

Exceptions

ArgumentException

Thrown if the tensor shape is invalid.

Edit this page