NormalizeOp class

Normalizes a TensorBuffer with given mean and stddev: output = (input - mean) / stddev.

Implemented types

• TensorOperator

Implementers

• DequantizeOp
• QuantizeOp

Constructors

NormalizeOp(double mean, double stddev)

Initializes a NormalizeOp. When being called, it creates a new TensorBuffer, which satisfies:

NormalizeOp.multipleChannels(List<double> mean, List<double> stddev)

Initializes a NormalizeOp. When being called, it creates a new TensorBuffer, which satisfies:

Properties

hashCode → int

The hash code for this object.

no setter, inherited

isIdentityOp ↔ bool

getter/setter pair

mean ↔ List<double>

getter/setter pair

numChannels ↔ int

getter/setter pair

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

stddev ↔ List<double>

getter/setter pair

Methods

apply(TensorBuffer input) → TensorBuffer

Applies the defined normalization on given input tensor and returns the result.

override

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited