NLClassifier class
Classifier API for natural language classification tasks, categorizes string into different classes.
The API expects a TFLite model with the following input/output tensor:
- Input tensor (kTfLiteString) input of the model, accepts a string.
- Output score tensor
(kTfLiteUInt8/kTfLiteInt8/kTfLiteInt16/kTfLiteFloat32/kTfLiteFloat64/kTfLiteBool)
- output scores for each class, if type is one of the Int types, dequantize it, if it is Bool type, convert the values to 0.0 and 1.0 respectively. - can have an optional associated file in metadata for labels, the file should be a plain text file with one label per line, the number of labels should match the number of categories the model outputs. Output label tensor: optional (kTfLiteString) - output classname for each class, should be of the same length with scores. If this tensor is not present, the API uses score indices as classnames. - will be ignored if output score tensor already has an associated label file.
- Optional Output label tensor (kTfLiteString/kTfLiteInt32) - output classname for each class, should be of the same length with scores. If this tensor is not present, the API uses score indices as classnames. - will be ignored if output score tensor already has an associated labe file.
By default the API tries to find the input/output tensors with default configurations in NLClassifierOptions, with tensor name prioritized over tensor index. The option is configurable for different TFLite models.
Properties
Methods
-
classify(
String text) → List< Category> -
Perform classification on a string input
text
, -
delete(
) → void - Deletes NLClassifier Instance.
-
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
Static Methods
-
create(
String modelPath, {NLClassifierOptions? options}) → NLClassifier -
Create NLClassifier from
modelPath
and optionaloptions
. -
createFromAsset(
String assetPath, {NLClassifierOptions? options}) → Future< NLClassifier> -
Create
NLClassifier
directly fromassetPath
and optionaloptions
. -
createFromFile(
File modelFile) → NLClassifier -
Create NLClassifier from
modelFile
. -
createFromFileAndOptions(
File modelFile, NLClassifierOptions options) → NLClassifier -
Create NLClassifier from
modelFile
andoptions
.