TensorData class final

Tensor data for input/output.

Represents a multi-dimensional array of numeric data used as input to or output from model inference.

Example:

final input = TensorData(
  shape: [1, 3, 224, 224],  // NCHW format
  dataType: TensorType.float32,
  data: imageBytes,
  name: 'input_0',
);

Constructors

TensorData({required List<int?> shape, required TensorType dataType, required Uint8List data, String? name})
Creates a new TensorData instance.

Properties

data → Uint8List
The raw bytes of tensor data.
final
dataType → TensorType
The data type of tensor elements.
final
hashCode → int
The hash code for this object.
no setteroverride
name → String?
Optional name for the tensor.
final
runtimeType → Type
A representation of the runtime type of the object.
no setterinherited
shape → List<int?>
The dimensions of the tensor.
final

Methods

noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
toString() → String
A string representation of this object.
override

Operators

operator ==(Object other) → bool
The equality operator.
override