Block

ConvBlock

autokeras.ConvBlock(
    kernel_size=None,
    num_blocks=None,
    num_layers=None,
    filters=None,
    max_pooling=None,
    separable=None,
    dropout=None,
    **kwargs
)

Block for vanilla ConvNets.

Arguments

kernel_size int | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None: Int or keras_tuner.engine.hyperparameters.Choice. The size of the kernel. If left unspecified, it will be tuned automatically.
num_blocks int | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None: Int or keras_tuner.engine.hyperparameters.Choice. The number of conv blocks, each of which may contain convolutional, max pooling, dropout, and activation. If left unspecified, it will be tuned automatically.
num_layers int | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None: Int or hyperparameters.Choice. The number of convolutional layers in each block. If left unspecified, it will be tuned automatically.
filters int | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None: Int or keras_tuner.engine.hyperparameters.Choice. The number of filters in the convolutional layers. If left unspecified, it will be tuned automatically.
max_pooling bool | None: Boolean. Whether to use max pooling layer in each block. If left unspecified, it will be tuned automatically.
separable bool | None: Boolean. Whether to use separable conv layers. If left unspecified, it will be tuned automatically.
dropout float | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None: Float or kerastuner.engine.hyperparameters. Choice range Between 0 and 1. The dropout rate after convolutional layers. If left unspecified, it will be tuned automatically.

[source]

DenseBlock

autokeras.DenseBlock(num_layers=None, num_units=None, use_batchnorm=None, dropout=None, **kwargs)

Block for Dense layers.

Arguments

num_layers int | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None: Int or keras_tuner.engine.hyperparameters.Choice. The number of Dense layers in the block. If left unspecified, it will be tuned automatically.
num_units int | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None: Int or keras_tuner.engine.hyperparameters.Choice. The number of units in each dense layer. If left unspecified, it will be tuned automatically.
use_bn: Boolean. Whether to use BatchNormalization layers. If left unspecified, it will be tuned automatically.
dropout float | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None: Float or keras_tuner.engine.hyperparameters.Choice. The dropout rate for the layers. If left unspecified, it will be tuned automatically.

[source]

Merge

autokeras.Merge(merge_type=None, **kwargs)

Merge block to merge multiple nodes into one.

Arguments

merge_type str | None: String. 'add' or 'concatenate'. If left unspecified, it will be tuned automatically.

[source]

ResNetBlock

autokeras.ResNetBlock(version=None, pretrained=None, **kwargs)

Block for ResNet.

Arguments

version str | None: String. 'v1', 'v2'. The type of ResNet to use. If left unspecified, it will be tuned automatically.
pretrained bool | None: Boolean. Whether to use ImageNet pretrained weights. If left unspecified, it will be tuned automatically.

[source]

RNNBlock

autokeras.RNNBlock(
    return_sequences=False, bidirectional=None, num_layers=None, layer_type=None, **kwargs
)

An RNN Block.

Arguments

return_sequences bool: Boolean. Whether to return the last output in the output sequence, or the full sequence. Defaults to False.
bidirectional bool | keras_tuner.src.engine.hyperparameters.hp_types.boolean_hp.Boolean | None: Boolean or keras_tuner.engine.hyperparameters.Boolean. Bidirectional RNN. If left unspecified, it will be tuned automatically.
num_layers int | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None: Int or keras_tuner.engine.hyperparameters.Choice. The number of layers in RNN. If left unspecified, it will be tuned automatically.
layer_type str | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None: String or or keras_tuner.engine.hyperparameters.Choice. 'gru' or 'lstm'. If left unspecified, it will be tuned automatically.

[source]

SpatialReduction

autokeras.SpatialReduction(reduction_type=None, **kwargs)

Reduce the dimension of a spatial tensor, e.g. image, to a vector.

Arguments

reduction_type str | None: String. 'flatten', 'global_max' or 'global_avg'. If left unspecified, it will be tuned automatically.

[source]

TemporalReduction

autokeras.TemporalReduction(reduction_type=None, **kwargs)

Reduce the dim of a temporal tensor, e.g. output of RNN, to a vector.

Arguments

reduction_type str | None: String. 'flatten', 'global_max' or 'global_avg'. If left unspecified, it will be tuned automatically.

[source]

XceptionBlock

autokeras.XceptionBlock(pretrained=None, **kwargs)

Block for XceptionNet.

An Xception structure, used for specifying your model with specific datasets.

The original Xception architecture is from https://arxiv.org/abs/1610.02357. The data first goes through the entry flow, then through the middle flow which is repeated eight times, and finally through the exit flow.

This XceptionBlock returns a similar architecture as Xception except without the last (optional) fully connected layer(s) and logistic regression. The size of this architecture could be decided by HyperParameters, to get an architecture with a half, an identical, or a double size of the original one.

Arguments

pretrained bool | None: Boolean. Whether to use ImageNet pretrained weights. If left unspecified, it will be tuned automatically.

[source]

ImageBlock

autokeras.ImageBlock(block_type=None, normalize=None, augment=None, **kwargs)

Block for image data.

The image blocks is a block choosing from ResNetBlock, XceptionBlock, ConvBlock, which is controlled by a hyperparameter, 'block_type'.

Arguments

block_type str | None: String. 'resnet', 'xception', 'vanilla'. The type of Block to use. If unspecified, it will be tuned automatically.
normalize bool | None: Boolean. Whether to channel-wise normalize the images. If unspecified, it will be tuned automatically.
augment bool | None: Boolean. Whether to do image augmentation. If unspecified, it will be tuned automatically.

[source]

TextBlock

autokeras.TextBlock(**kwargs)

Block for text data.

[source]

ImageAugmentation

autokeras.ImageAugmentation(
    translation_factor=None,
    vertical_flip=None,
    horizontal_flip=None,
    rotation_factor=None,
    zoom_factor=None,
    contrast_factor=None,
    **kwargs
)

Collection of various image augmentation methods.

Arguments

translation_factor float | Tuple[float, float] | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None: A positive float represented as fraction value, or a tuple of 2 representing fraction for translation vertically and horizontally, or a kerastuner.engine.hyperparameters.Choice range of positive floats. For instance, translation_factor=0.2 result in a random translation factor within 20% of the width and height. If left unspecified, it will be tuned automatically.
vertical_flip bool | None: Boolean. Whether to flip the image vertically. If left unspecified, it will be tuned automatically.
horizontal_flip bool | None: Boolean. Whether to flip the image horizontally. If left unspecified, it will be tuned automatically.
rotation_factor float | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None: Float or kerastuner.engine.hyperparameters.Choice range between [0, 1]. A positive float represented as fraction of 2pi upper bound for rotating clockwise and counter-clockwise. When represented as a single float, lower = upper. If left unspecified, it will be tuned automatically.
zoom_factor float | Tuple[float, float] | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None: A positive float represented as fraction value, or a tuple of 2 representing fraction for zooming vertically and horizontally, or a kerastuner.engine.hyperparameters.Choice range of positive floats. For instance, zoom_factor=0.2 result in a random zoom factor from 80% to 120%. If left unspecified, it will be tuned automatically.
contrast_factor float | Tuple[float, float] | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None: A positive float represented as fraction of value, or a tuple of size 2 representing lower and upper bound, or a kerastuner.engine.hyperparameters.Choice range of floats to find the optimal value. When represented as a single float, lower = upper. The contrast factor will be randomly picked between [1.0 - lower, 1.0 + upper]. If left unspecified, it will be tuned automatically.

[source]

Normalization

autokeras.Normalization(axis=-1, **kwargs)

Perform feature-wise normalization on data.

Refer to Normalization layer in keras preprocessing layers for more information.

Arguments

axis int: Integer or tuple of integers, the axis or axes that should be normalized (typically the features axis). We will normalize each element in the specified axis. The default is '-1' (the innermost axis); 0 (the batch axis) is not allowed.

[source]

ClassificationHead

autokeras.ClassificationHead(
    num_classes=None, multi_label=False, loss=None, metrics=None, dropout=None, **kwargs
)

Classification Dense layers.

Use sigmoid and binary crossentropy for binary classification and multi-label classification. Use softmax and categorical crossentropy for multi-class (more than 2) classification. Use Accuracy as metrics by default.

The targets passing to the head would have to be tf.data.Dataset, np.ndarray, pd.DataFrame or pd.Series. It can be raw labels, one-hot encoded if more than two classes, or binary encoded for binary classification.

The raw labels will be encoded to one column if two classes were found, or one-hot encoded if more than two classes were found.

Arguments

num_classes int | None: Int. Defaults to None. If None, it will be inferred from the data.
multi_label bool: Boolean. Defaults to False.
loss str | Callable | tensorflow.keras.losses.Loss | None: A Keras loss function. Defaults to use binary_crossentropy or categorical_crossentropy based on the number of classes.
metrics List[str | Callable | tensorflow.keras.metrics.Metric] | List[List[str | Callable | tensorflow.keras.metrics.Metric]] | Dict[str, str | Callable | tensorflow.keras.metrics.Metric] | None: A list of Keras metrics. Defaults to use 'accuracy'.
dropout float | None: Float. The dropout rate for the layers. If left unspecified, it will be tuned automatically.

[source]

RegressionHead

autokeras.RegressionHead(
    output_dim=None, loss="mean_squared_error", metrics=None, dropout=None, **kwargs
)

Regression Dense layers.

The targets passing to the head would have to be tf.data.Dataset, np.ndarray, pd.DataFrame or pd.Series. It can be single-column or multi-column. The values should all be numerical.

Arguments

output_dim int | None: Int. The number of output dimensions. Defaults to None. If None, it will be inferred from the data.
multi_label: Boolean. Defaults to False.
loss str | Callable | tensorflow.keras.losses.Loss: A Keras loss function. Defaults to use mean_squared_error.
metrics List[str | Callable | tensorflow.keras.metrics.Metric] | List[List[str | Callable | tensorflow.keras.metrics.Metric]] | Dict[str, str | Callable | tensorflow.keras.metrics.Metric] | None: A list of Keras metrics. Defaults to use mean_squared_error.
dropout float | None: Float. The dropout rate for the layers. If left unspecified, it will be tuned automatically.