Table of Contents

Class InternVideo2<T>

Namespace
AiDotNet.Video.Understanding
Assembly
AiDotNet.dll

InternVideo2: Scaling Video Foundation Models for Multimodal Video Understanding.

public class InternVideo2<T> : NeuralNetworkBase<T>, INeuralNetworkModel<T>, INeuralNetwork<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>, IInterpretableModel<T>, IInputGradientComputable<T>, IDisposable

Type Parameters

T

The numeric type used for calculations (typically float or double).

Inheritance
InternVideo2<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

InternVideo2 is a state-of-the-art video understanding model that combines: - Video-text contrastive learning - Masked video modeling - Video-text generative learning

For Beginners: InternVideo2 understands video content by analyzing frames and learning relationships between visual content and language. It can: - Classify videos (what's happening?) - Find videos matching text descriptions - Answer questions about video content - Generate video captions

Example usage (native mode for training):

var arch = new NeuralNetworkArchitecture<double>(
    inputType: InputType.ThreeDimensional,
    inputHeight: 224, inputWidth: 224, inputDepth: 3);
var model = new InternVideo2<double>(arch);
model.Train(videoFrames, expectedEmbedding);
var embedding = model.EncodeVideo(videoFrames);

Example usage (ONNX mode for inference only):

var arch = new NeuralNetworkArchitecture<double>(
    inputType: InputType.ThreeDimensional,
    inputHeight: 224, inputWidth: 224, inputDepth: 3);
var model = new InternVideo2<double>(arch, "internvideo2.onnx");
var embedding = model.EncodeVideo(videoFrames);

Reference: "InternVideo2: Scaling Video Foundation Models for Multimodal Video Understanding" https://arxiv.org/abs/2403.15377

Constructors

InternVideo2(NeuralNetworkArchitecture<T>, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>?, ILossFunction<T>?, int, int, int, int, int)

Creates an InternVideo2 model using native layers for training and inference.

public InternVideo2(NeuralNetworkArchitecture<T> architecture, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>? optimizer = null, ILossFunction<T>? lossFunction = null, int embedDim = 768, int numHeads = 12, int numEncoderLayers = 12, int numFrames = 8, int patchSize = 14)

Parameters

architecture NeuralNetworkArchitecture<T>

Architecture for the video encoder.

optimizer IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>

Optional optimizer for training. Default: Adam.

lossFunction ILossFunction<T>

Optional loss function. Default: MSE.

embedDim int

Embedding dimension (default: 768).

numHeads int

Number of attention heads (default: 12).

numEncoderLayers int

Number of encoder layers (default: 12).

numFrames int

Number of frames to process (default: 8).

patchSize int

Patch size for tokenization (default: 14).

Remarks

For Beginners: Create a trainable InternVideo2 model: 

var arch = new NeuralNetworkArchitecture<double>(
    inputType: InputType.ThreeDimensional,
    inputHeight: 224, inputWidth: 224, inputDepth: 3);
var model = new InternVideo2<double>(arch);

InternVideo2(NeuralNetworkArchitecture<T>, string, int)

Creates an InternVideo2 model using a pretrained ONNX model for inference.

public InternVideo2(NeuralNetworkArchitecture<T> architecture, string onnxModelPath, int embedDim = 768)

Parameters

architecture NeuralNetworkArchitecture<T>

The neural network architecture configuration.

onnxModelPath string

Path to the pretrained ONNX model.

embedDim int

Embedding dimension of the model (default: 768).

Remarks

For Beginners: Use this constructor when you have a pretrained model in ONNX format. Training is not supported in ONNX mode. 

var arch = new NeuralNetworkArchitecture<double>(
    inputType: InputType.ThreeDimensional,
    inputHeight: 224, inputWidth: 224, inputDepth: 3);
var model = new InternVideo2<double>(arch, "internvideo2.onnx");
var embedding = model.EncodeVideo(videoFrames);

Exceptions

FileNotFoundException

Thrown if the ONNX model file is not found.

Properties

SupportsTraining

Gets whether training is supported (only in native mode).

public override bool SupportsTraining { get; }

Property Value

bool

Methods

ComputeSimilarity(Tensor<T>, Tensor<T>)

Computes similarity between video and text embeddings.

public T ComputeSimilarity(Tensor<T> videoEmbedding, Tensor<T> textEmbedding)

Parameters

videoEmbedding Tensor<T>

Video embedding from EncodeVideo.

textEmbedding Tensor<T>

Text embedding from a text encoder.

Returns

T

Cosine similarity score.

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.

EncodeVideo(Tensor<T>)

Encodes video frames into an embedding vector.

public Tensor<T> EncodeVideo(Tensor<T> videoFrames)

Parameters

videoFrames Tensor<T>

Video frames tensor [B, C, H, W] or [C, H, W].

Returns

Tensor<T>

Video embedding tensor.

Remarks

For Beginners: This method converts video frames into a fixed-size vector that represents the video content. Similar videos will have similar embeddings.

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.

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> parameters)

Parameters

parameters Vector<T>

The new parameter values to set.

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.

Edit this page