Table of Contents

Class PICK<T>

Namespace
AiDotNet.Document.GraphBased
Assembly
AiDotNet.dll

PICK (Processing Key Information Extraction) neural network for document key information extraction.

public class PICK<T> : DocumentNeuralNetworkBase<T>, INeuralNetworkModel<T>, INeuralNetwork<T>, IInterpretableModel<T>, IInputGradientComputable<T>, IDisposable, IFormUnderstanding<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
PICK<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

PICK uses a graph neural network approach to extract key information from documents. It models text segments as nodes and their relationships as edges, enabling better understanding of document structure.

For Beginners: PICK is especially good at: 1. Extracting key-value pairs from invoices and receipts 2. Understanding relationships between text segments 3. Handling complex document layouts 4. Named Entity Recognition in documents

Example usage:

var model = new PICK<float>(architecture);
var result = model.ExtractKeyInfo(documentImage);
foreach (var entity in result.Entities)
    Console.WriteLine($"{entity.Label}: {entity.Text}");

Reference: "PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks" (ICPR 2020) https://arxiv.org/abs/2004.07464

Constructors

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

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

public PICK(NeuralNetworkArchitecture<T> architecture, ITokenizer? tokenizer = null, int numEntityTypes = 14, int imageSize = 512, int maxSequenceLength = 512, int hiddenDim = 256, int numGcnLayers = 2, int numHeads = 8, int vocabSize = 30522, IOptimizer<T, Tensor<T>, Tensor<T>>? optimizer = null, ILossFunction<T>? lossFunction = null)

Parameters

architecture NeuralNetworkArchitecture<T>
tokenizer ITokenizer
numEntityTypes int
imageSize int
maxSequenceLength int
hiddenDim int
numGcnLayers int
numHeads int
vocabSize int
optimizer IOptimizer<T, Tensor<T>, Tensor<T>>
lossFunction ILossFunction<T>

Remarks

Default Configuration (PICK from ICPR 2020): - BERT-based text encoder - 2-layer Graph Convolutional Network - BiLSTM for sequence modeling - CRF decoder for NER - Hidden dimension: 256

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

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

public PICK(NeuralNetworkArchitecture<T> architecture, string onnxModelPath, ITokenizer tokenizer, int numEntityTypes = 14, int imageSize = 512, int maxSequenceLength = 512, int hiddenDim = 256, int numGcnLayers = 2, int numHeads = 8, int vocabSize = 30522, IOptimizer<T, Tensor<T>, Tensor<T>>? optimizer = null, ILossFunction<T>? lossFunction = null)

Parameters

architecture NeuralNetworkArchitecture<T>
onnxModelPath string
tokenizer ITokenizer
numEntityTypes int
imageSize int
maxSequenceLength int
hiddenDim int
numGcnLayers int
numHeads int
vocabSize int
optimizer IOptimizer<T, Tensor<T>, Tensor<T>>
lossFunction ILossFunction<T>

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

SupportedEntityTypes

Gets the supported entity types for extraction.

public IReadOnlyList<string> SupportedEntityTypes { get; }

Property Value

IReadOnlyList<string>

Methods

ApplyDefaultPostprocessing(Tensor<T>)

Applies PICK's industry-standard postprocessing: pass-through (entity extraction outputs are already final).

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

Parameters

modelOutput Tensor<T>

Returns

Tensor<T>

ApplyDefaultPreprocessing(Tensor<T>)

Applies PICK's industry-standard preprocessing: pass-through (PICK works with text + bbox input).

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

Parameters

rawImage Tensor<T>

Returns

Tensor<T>

Remarks

PICK (ICPR 2020) primarily processes text and bounding box features rather than raw images.

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.

DetectCheckboxes(Tensor<T>)

Detects checkboxes and their states in a document.

public IEnumerable<CheckboxResult<T>> DetectCheckboxes(Tensor<T> documentImage)

Parameters

documentImage Tensor<T>

The document image tensor.

Returns

IEnumerable<CheckboxResult<T>>

Collection of detected checkboxes.

DetectSignatures(Tensor<T>)

Detects signatures in a document.

public IEnumerable<SignatureResult<T>> DetectSignatures(Tensor<T> documentImage)

Parameters

documentImage Tensor<T>

The document image tensor.

Returns

IEnumerable<SignatureResult<T>>

Collection of detected signatures.

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.

ExtractFormFields(Tensor<T>)

Extracts form fields from a document image.

public FormFieldResult<T> ExtractFormFields(Tensor<T> documentImage)

Parameters

documentImage Tensor<T>

The document image tensor.

Returns

FormFieldResult<T>

Form field extraction result.

ExtractFormFields(Tensor<T>, double)

Extracts form fields with a custom confidence threshold.

public FormFieldResult<T> ExtractFormFields(Tensor<T> documentImage, double confidenceThreshold)

Parameters

documentImage Tensor<T>

The document image tensor.

confidenceThreshold double

Minimum confidence for field extraction (0-1).

Returns

FormFieldResult<T>

Form field extraction result.

ExtractKeyInfo(Tensor<T>)

Extracts key information entities from a document.

public KeyInfoExtractionResult<T> ExtractKeyInfo(Tensor<T> documentImage)

Parameters

documentImage Tensor<T>

The document image tensor.

Returns

KeyInfoExtractionResult<T>

Key information extraction result.

ExtractKeyValuePairs(Tensor<T>)

Extracts key-value pairs from a document.

public Dictionary<string, string> ExtractKeyValuePairs(Tensor<T> documentImage)

Parameters

documentImage Tensor<T>

The document image tensor.

Returns

Dictionary<string, string>

Dictionary of field names to values.

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