TensorProcessor class
TensorProcessor is a helper class for preprocessing and postprocessing tensors. It could transform a TensorBuffer to another by executing a chain of TensorOperator.
Example Usage:
TensorProcessor processor = TensorProcessorBuilder().add(NormalizeOp(1.0, 2.0)).build();
TensorBuffer anotherTensorBuffer = processor.process(tensorBuffer);
See TensorProcessorBuilder to build a TensorProcessor instance. See SequentialProcessor.process to apply the processor on a TensorBuffer.
- Inheritance
-
- Object
- SequentialProcessor<
TensorBuffer> - TensorProcessor
Properties
- hashCode → int
-
The hash code for this object.
no setterinherited
-
operatorIndex
↔ Map<
String, List< int> > -
The Map between the operator name and the corresponding op indexes in operatorList.
An operator may be added multiple times into this SequentialProcessor.
getter/setter pairinherited
-
operatorList
↔ List<
Operator< TensorBuffer> > -
List of operators added to this SequentialProcessor.
getter/setter pairinherited
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
Methods
-
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
process(
TensorBuffer input) → TensorBuffer -
inherited
-
toString(
) → String -
A string representation of this object.
inherited
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited