Class WeightLoader

Namespace

AiDotNet.ComputerVision.Weights

Assembly

AiDotNet.dll

Loads pre-trained model weights from various file formats.

public class WeightLoader

Inheritance

object

WeightLoader

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

For Beginners: This class reads saved neural network weights from files. Deep learning models are trained on massive datasets, and the learned parameters (weights) can be saved and reloaded. This allows you to use pre-trained models without training from scratch.

Supported formats: - PyTorch (.pt, .pth) - Python pickle with tensor data - SafeTensors (.safetensors) - Safe tensor format - NumPy (.npy, .npz) - NumPy array format - ONNX (.onnx) - Open Neural Network Exchange format

Constructors

WeightLoader()

Creates a new weight loader.

public WeightLoader()

Methods

LoadWeights(string)

Loads weights from a file and returns them as a dictionary.

public Dictionary<string, Tensor<float>> LoadWeights(string filePath)

Parameters

filePath string

Path to the weight file.

Returns

Dictionary<string, Tensor<float>>

Dictionary mapping layer names to weight tensors.