Tensor class
TensorFlowLite tensor.
Constructors
-
Tensor(Pointer<
TfLiteTensor> _tensor)
Properties
- data ↔ Uint8List
-
Underlying data buffer as bytes.
getter/setter pair
- hashCode → int
-
The hash code for this object.
no setterinherited
- name → String
-
Name of the tensor element.
no setter
- params → QuantizationParams
-
Quantization Params associated with the model,
only Androidno setter - runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
-
shape
→ List<
int> -
Dimensions of the tensor.
no setter
- type → TfLiteType
-
Data type of the tensor element.
no setter
Methods
-
copyTo(
Object dst) → Object -
getInputShapeIfDifferent(
Object? input) → List< int> ? -
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
numBytes(
) → int - Returns the size, in bytes, of the tensor data.
-
numDimensions(
) → int - Returns number of dimensions
-
numElements(
) → int - Returns the number of elements in a flattened (1-D) view of the tensor.
-
setTo(
Object src) → void -
toString(
) → String -
A string representation of this object.
override
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited
Static Methods
-
computeNumDimensions(
Object? o) → int - Returns the number of dimensions of a multi-dimensional array, otherwise 0.
-
computeNumElements(
List< int> shape) → int - Returns the number of elements in a flattened (1-D) view of the tensor's shape.
-
computeShapeOf(
Object o) → List< int> - Returns shape of an object as an int list
-
dataTypeOf(
Object o) → TfLiteType - Returns data type of given object
-
fillShape(
Object o, int dim, List< int> ? shape) → void - Recursively populates the shape dimensions for a given (multi-dimensional) array)