Skip to content

ImageClassifier

[source]

ImageClassifier class

autokeras.ImageClassifier(
    num_classes=None,
    multi_label=False,
    loss=None,
    metrics=None,
    project_name="image_classifier",
    max_trials=100,
    directory=None,
    objective="val_loss",
    tuner=None,
    overwrite=True,
    seed=None,
    **kwargs
)

AutoKeras image classification class.

Arguments

  • num_classes Optional[int]: Int. Defaults to None. If None, it will be inferred from the data.
  • multi_label bool: Boolean. Defaults to False.
  • loss Union[str, Callable]: A Keras loss function. Defaults to use 'binary_crossentropy' or 'categorical_crossentropy' based on the number of classes.
  • metrics Union[List[Union[str, Callable]], List[List[Union[str, Callable]]], Dict[str, Union[str, Callable]], None]: A list of Keras metrics. Defaults to use 'accuracy'.
  • project_name str: String. The name of the AutoModel. Defaults to 'image_classifier'.
  • max_trials int: Int. The maximum number of different Keras Models to try. The search may finish before reaching the max_trials. Defaults to 100.
  • directory Union[str, pathlib.Path, None]: String. The path to a directory for storing the search outputs. Defaults to None, which would create a folder with the name of the AutoModel in the current directory.
  • objective str: String. Name of model metric to minimize or maximize, e.g. 'val_accuracy'. Defaults to 'val_loss'.
  • tuner Union[str, Type[autokeras.engine.tuner.AutoTuner]]: String or subclass of AutoTuner. If string, it should be one of 'greedy', 'bayesian', 'hyperband' or 'random'. It can also be a subclass of AutoTuner. If left unspecified, it uses a task specific tuner, which first evaluates the most commonly used models for the task before exploring other models.
  • overwrite bool: Boolean. Defaults to True. If False, reloads an existing project of the same name if one is found. Otherwise, overwrites the project.
  • seed Optional[int]: Int. Random seed.
  • **kwargs: Any arguments supported by AutoModel.

[source]

fit method

ImageClassifier.fit(
    x=None, y=None, epochs=None, callbacks=None, validation_split=0.2, validation_data=None, **kwargs
)

Search for the best model and hyperparameters for the AutoModel.

It will search for the best model based on the performances on validation data.

Arguments

  • x Union[numpy.ndarray, tensorflow.data.Dataset, None]: numpy.ndarray or tensorflow.Dataset. Training data x. The shape of the data should be (samples, width, height) or (samples, width, height, channels).
  • y Union[numpy.ndarray, tensorflow.data.Dataset, None]: numpy.ndarray or tensorflow.Dataset. Training data y. It can be raw labels, one-hot encoded if more than two classes, or binary encoded for binary classification.
  • epochs Optional[int]: Int. The number of epochs to train each model during the search. If unspecified, by default we train for a maximum of 1000 epochs, but we stop training if the validation loss stops improving for 10 epochs (unless you specified an EarlyStopping callback as part of the callbacks argument, in which case the EarlyStopping callback you specified will determine early stopping).
  • callbacks Optional[List[tensorflow.keras.callbacks.Callback]]: List of Keras callbacks to apply during training and validation.
  • validation_split Optional[float]: Float between 0 and 1. Defaults to 0.2. Fraction of the training data to be used as validation data. The model will set apart this fraction of the training data, will not train on it, and will evaluate the loss and any model metrics on this data at the end of each epoch. The validation data is selected from the last samples in the x and y data provided, before shuffling. This argument is not supported when x is a dataset. The best model found would be fit on the entire dataset including the validation data.
  • validation_data Union[tensorflow.data.Dataset, Tuple[Union[numpy.ndarray, tensorflow.data.Dataset], Union[numpy.ndarray, tensorflow.data.Dataset]], None]: Data on which to evaluate the loss and any model metrics at the end of each epoch. The model will not be trained on this data. validation_data will override validation_split. The type of the validation data should be the same as the training data. The best model found would be fit on the training dataset without the validation data.
  • **kwargs: Any arguments supported by keras.Model.fit.

[source]

predict method

ImageClassifier.predict(x, **kwargs)

Predict the output for a given testing data.

Arguments

  • x: Any allowed types according to the input node. Testing data.
  • **kwargs: Any arguments supported by keras.Model.predict.

Returns

A list of numpy.ndarray objects or a single numpy.ndarray. The predicted results.


[source]

evaluate method

ImageClassifier.evaluate(x, y=None, **kwargs)

Evaluate the best model for the given data.

Arguments

  • x: Any allowed types according to the input node. Testing data.
  • y: Any allowed types according to the head. Testing targets. Defaults to None.
  • **kwargs: Any arguments supported by keras.Model.evaluate.

Returns

Scalar test loss (if the model has a single output and no metrics) or list of scalars (if the model has multiple outputs and/or metrics). The attribute model.metrics_names will give you the display labels for the scalar outputs.


[source]

export_model method

ImageClassifier.export_model()

Export the best Keras Model.

Returns

tf.keras.Model instance. The best model found during the search, loaded with trained weights.