Keras 2 API documentation / Keras Applications / EfficientNet B0 to B7

EfficientNet B0 to B7

[source]

EfficientNetB0 function

tf_keras.applications.EfficientNetB0(
    include_top=True,
    weights="imagenet",
    input_tensor=None,
    input_shape=None,
    pooling=None,
    classes=1000,
    classifier_activation="softmax",
    **kwargs
)

Instantiates the EfficientNetB0 architecture.

Reference

This function returns a TF-Keras image classification model, optionally loaded with weights pre-trained on ImageNet.

For image classification use cases, see this page for detailed examples.

For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

Note: each TF-Keras Application expects a specific kind of input preprocessing. For EfficientNet, input preprocessing is included as part of the model (as a Rescaling layer), and thus tf.keras.applications.efficientnet.preprocess_input is actually a pass-through function. EfficientNet models expect their inputs to be float tensors of pixels with values in the [0-255] range.

Arguments

  • include_top: Whether to include the fully-connected layer at the top of the network. Defaults to True.
  • weights: One of None (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. Defaults to 'imagenet'.
  • input_tensor: Optional TF-Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
  • input_shape: Optional shape tuple, only to be specified if include_top is False. It should have exactly 3 inputs channels.
  • pooling: Optional pooling mode for feature extraction when include_top is False. Defaults to None.
    • None means that the output of the model will be the 4D tensor output of the last convolutional layer.
    • avg means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor.
    • max means that global max pooling will be applied.
  • classes: Optional number of classes to classify images into, only to be specified if include_top is True, and if no weights argument is specified. 1000 is how many ImageNet classes there are. Defaults to 1000.
  • classifier_activation: A str or callable. The activation function to use on the "top" layer. Ignored unless include_top=True. Set classifier_activation=None to return the logits of the "top" layer. Defaults to 'softmax'. When loading pretrained weights, classifier_activation can only be None or "softmax".

Returns

A keras.Model instance.


[source]

EfficientNetB1 function

tf_keras.applications.EfficientNetB1(
    include_top=True,
    weights="imagenet",
    input_tensor=None,
    input_shape=None,
    pooling=None,
    classes=1000,
    classifier_activation="softmax",
    **kwargs
)

Instantiates the EfficientNetB1 architecture.

Reference

This function returns a TF-Keras image classification model, optionally loaded with weights pre-trained on ImageNet.

For image classification use cases, see this page for detailed examples.

For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

Note: each TF-Keras Application expects a specific kind of input preprocessing. For EfficientNet, input preprocessing is included as part of the model (as a Rescaling layer), and thus tf.keras.applications.efficientnet.preprocess_input is actually a pass-through function. EfficientNet models expect their inputs to be float tensors of pixels with values in the [0-255] range.

Arguments

  • include_top: Whether to include the fully-connected layer at the top of the network. Defaults to True.
  • weights: One of None (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. Defaults to 'imagenet'.
  • input_tensor: Optional TF-Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
  • input_shape: Optional shape tuple, only to be specified if include_top is False. It should have exactly 3 inputs channels.
  • pooling: Optional pooling mode for feature extraction when include_top is False. Defaults to None.
    • None means that the output of the model will be the 4D tensor output of the last convolutional layer.
    • avg means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor.
    • max means that global max pooling will be applied.
  • classes: Optional number of classes to classify images into, only to be specified if include_top is True, and if no weights argument is specified. 1000 is how many ImageNet classes there are. Defaults to 1000.
  • classifier_activation: A str or callable. The activation function to use on the "top" layer. Ignored unless include_top=True. Set classifier_activation=None to return the logits of the "top" layer. Defaults to 'softmax'. When loading pretrained weights, classifier_activation can only be None or "softmax".

Returns

A keras.Model instance.


[source]

EfficientNetB2 function

tf_keras.applications.EfficientNetB2(
    include_top=True,
    weights="imagenet",
    input_tensor=None,
    input_shape=None,
    pooling=None,
    classes=1000,
    classifier_activation="softmax",
    **kwargs
)

Instantiates the EfficientNetB2 architecture.

Reference

This function returns a TF-Keras image classification model, optionally loaded with weights pre-trained on ImageNet.

For image classification use cases, see this page for detailed examples.

For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

Note: each TF-Keras Application expects a specific kind of input preprocessing. For EfficientNet, input preprocessing is included as part of the model (as a Rescaling layer), and thus tf.keras.applications.efficientnet.preprocess_input is actually a pass-through function. EfficientNet models expect their inputs to be float tensors of pixels with values in the [0-255] range.

Arguments

  • include_top: Whether to include the fully-connected layer at the top of the network. Defaults to True.
  • weights: One of None (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. Defaults to 'imagenet'.
  • input_tensor: Optional TF-Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
  • input_shape: Optional shape tuple, only to be specified if include_top is False. It should have exactly 3 inputs channels.
  • pooling: Optional pooling mode for feature extraction when include_top is False. Defaults to None.
    • None means that the output of the model will be the 4D tensor output of the last convolutional layer.
    • avg means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor.
    • max means that global max pooling will be applied.
  • classes: Optional number of classes to classify images into, only to be specified if include_top is True, and if no weights argument is specified. 1000 is how many ImageNet classes there are. Defaults to 1000.
  • classifier_activation: A str or callable. The activation function to use on the "top" layer. Ignored unless include_top=True. Set classifier_activation=None to return the logits of the "top" layer. Defaults to 'softmax'. When loading pretrained weights, classifier_activation can only be None or "softmax".

Returns

A keras.Model instance.


[source]

EfficientNetB3 function

tf_keras.applications.EfficientNetB3(
    include_top=True,
    weights="imagenet",
    input_tensor=None,
    input_shape=None,
    pooling=None,
    classes=1000,
    classifier_activation="softmax",
    **kwargs
)

Instantiates the EfficientNetB3 architecture.

Reference

This function returns a TF-Keras image classification model, optionally loaded with weights pre-trained on ImageNet.

For image classification use cases, see this page for detailed examples.

For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

Note: each TF-Keras Application expects a specific kind of input preprocessing. For EfficientNet, input preprocessing is included as part of the model (as a Rescaling layer), and thus tf.keras.applications.efficientnet.preprocess_input is actually a pass-through function. EfficientNet models expect their inputs to be float tensors of pixels with values in the [0-255] range.

Arguments

  • include_top: Whether to include the fully-connected layer at the top of the network. Defaults to True.
  • weights: One of None (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. Defaults to 'imagenet'.
  • input_tensor: Optional TF-Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
  • input_shape: Optional shape tuple, only to be specified if include_top is False. It should have exactly 3 inputs channels.
  • pooling: Optional pooling mode for feature extraction when include_top is False. Defaults to None.
    • None means that the output of the model will be the 4D tensor output of the last convolutional layer.
    • avg means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor.
    • max means that global max pooling will be applied.
  • classes: Optional number of classes to classify images into, only to be specified if include_top is True, and if no weights argument is specified. 1000 is how many ImageNet classes there are. Defaults to 1000.
  • classifier_activation: A str or callable. The activation function to use on the "top" layer. Ignored unless include_top=True. Set classifier_activation=None to return the logits of the "top" layer. Defaults to 'softmax'. When loading pretrained weights, classifier_activation can only be None or "softmax".

Returns

A keras.Model instance.


[source]

EfficientNetB4 function

tf_keras.applications.EfficientNetB4(
    include_top=True,
    weights="imagenet",
    input_tensor=None,
    input_shape=None,
    pooling=None,
    classes=1000,
    classifier_activation="softmax",
    **kwargs
)

Instantiates the EfficientNetB4 architecture.

Reference

This function returns a TF-Keras image classification model, optionally loaded with weights pre-trained on ImageNet.

For image classification use cases, see this page for detailed examples.

For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

Note: each TF-Keras Application expects a specific kind of input preprocessing. For EfficientNet, input preprocessing is included as part of the model (as a Rescaling layer), and thus tf.keras.applications.efficientnet.preprocess_input is actually a pass-through function. EfficientNet models expect their inputs to be float tensors of pixels with values in the [0-255] range.

Arguments

  • include_top: Whether to include the fully-connected layer at the top of the network. Defaults to True.
  • weights: One of None (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. Defaults to 'imagenet'.
  • input_tensor: Optional TF-Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
  • input_shape: Optional shape tuple, only to be specified if include_top is False. It should have exactly 3 inputs channels.
  • pooling: Optional pooling mode for feature extraction when include_top is False. Defaults to None.
    • None means that the output of the model will be the 4D tensor output of the last convolutional layer.
    • avg means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor.
    • max means that global max pooling will be applied.
  • classes: Optional number of classes to classify images into, only to be specified if include_top is True, and if no weights argument is specified. 1000 is how many ImageNet classes there are. Defaults to 1000.
  • classifier_activation: A str or callable. The activation function to use on the "top" layer. Ignored unless include_top=True. Set classifier_activation=None to return the logits of the "top" layer. Defaults to 'softmax'. When loading pretrained weights, classifier_activation can only be None or "softmax".

Returns

A keras.Model instance.


[source]

EfficientNetB5 function

tf_keras.applications.EfficientNetB5(
    include_top=True,
    weights="imagenet",
    input_tensor=None,
    input_shape=None,
    pooling=None,
    classes=1000,
    classifier_activation="softmax",
    **kwargs
)

Instantiates the EfficientNetB5 architecture.

Reference

This function returns a TF-Keras image classification model, optionally loaded with weights pre-trained on ImageNet.

For image classification use cases, see this page for detailed examples.

For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

Note: each TF-Keras Application expects a specific kind of input preprocessing. For EfficientNet, input preprocessing is included as part of the model (as a Rescaling layer), and thus tf.keras.applications.efficientnet.preprocess_input is actually a pass-through function. EfficientNet models expect their inputs to be float tensors of pixels with values in the [0-255] range.

Arguments

  • include_top: Whether to include the fully-connected layer at the top of the network. Defaults to True.
  • weights: One of None (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. Defaults to 'imagenet'.
  • input_tensor: Optional TF-Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
  • input_shape: Optional shape tuple, only to be specified if include_top is False. It should have exactly 3 inputs channels.
  • pooling: Optional pooling mode for feature extraction when include_top is False. Defaults to None.
    • None means that the output of the model will be the 4D tensor output of the last convolutional layer.
    • avg means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor.
    • max means that global max pooling will be applied.
  • classes: Optional number of classes to classify images into, only to be specified if include_top is True, and if no weights argument is specified. 1000 is how many ImageNet classes there are. Defaults to 1000.
  • classifier_activation: A str or callable. The activation function to use on the "top" layer. Ignored unless include_top=True. Set classifier_activation=None to return the logits of the "top" layer. Defaults to 'softmax'. When loading pretrained weights, classifier_activation can only be None or "softmax".

Returns

A keras.Model instance.


[source]

EfficientNetB6 function

tf_keras.applications.EfficientNetB6(
    include_top=True,
    weights="imagenet",
    input_tensor=None,
    input_shape=None,
    pooling=None,
    classes=1000,
    classifier_activation="softmax",
    **kwargs
)

Instantiates the EfficientNetB6 architecture.

Reference

This function returns a TF-Keras image classification model, optionally loaded with weights pre-trained on ImageNet.

For image classification use cases, see this page for detailed examples.

For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

Note: each TF-Keras Application expects a specific kind of input preprocessing. For EfficientNet, input preprocessing is included as part of the model (as a Rescaling layer), and thus tf.keras.applications.efficientnet.preprocess_input is actually a pass-through function. EfficientNet models expect their inputs to be float tensors of pixels with values in the [0-255] range.

Arguments

  • include_top: Whether to include the fully-connected layer at the top of the network. Defaults to True.
  • weights: One of None (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. Defaults to 'imagenet'.
  • input_tensor: Optional TF-Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
  • input_shape: Optional shape tuple, only to be specified if include_top is False. It should have exactly 3 inputs channels.
  • pooling: Optional pooling mode for feature extraction when include_top is False. Defaults to None.
    • None means that the output of the model will be the 4D tensor output of the last convolutional layer.
    • avg means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor.
    • max means that global max pooling will be applied.
  • classes: Optional number of classes to classify images into, only to be specified if include_top is True, and if no weights argument is specified. 1000 is how many ImageNet classes there are. Defaults to 1000.
  • classifier_activation: A str or callable. The activation function to use on the "top" layer. Ignored unless include_top=True. Set classifier_activation=None to return the logits of the "top" layer. Defaults to 'softmax'. When loading pretrained weights, classifier_activation can only be None or "softmax".

Returns

A keras.Model instance.


[source]

EfficientNetB7 function

tf_keras.applications.EfficientNetB7(
    include_top=True,
    weights="imagenet",
    input_tensor=None,
    input_shape=None,
    pooling=None,
    classes=1000,
    classifier_activation="softmax",
    **kwargs
)

Instantiates the EfficientNetB7 architecture.

Reference

This function returns a TF-Keras image classification model, optionally loaded with weights pre-trained on ImageNet.

For image classification use cases, see this page for detailed examples.

For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

Note: each TF-Keras Application expects a specific kind of input preprocessing. For EfficientNet, input preprocessing is included as part of the model (as a Rescaling layer), and thus tf.keras.applications.efficientnet.preprocess_input is actually a pass-through function. EfficientNet models expect their inputs to be float tensors of pixels with values in the [0-255] range.

Arguments

  • include_top: Whether to include the fully-connected layer at the top of the network. Defaults to True.
  • weights: One of None (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. Defaults to 'imagenet'.
  • input_tensor: Optional TF-Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
  • input_shape: Optional shape tuple, only to be specified if include_top is False. It should have exactly 3 inputs channels.
  • pooling: Optional pooling mode for feature extraction when include_top is False. Defaults to None.
    • None means that the output of the model will be the 4D tensor output of the last convolutional layer.
    • avg means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor.
    • max means that global max pooling will be applied.
  • classes: Optional number of classes to classify images into, only to be specified if include_top is True, and if no weights argument is specified. 1000 is how many ImageNet classes there are. Defaults to 1000.
  • classifier_activation: A str or callable. The activation function to use on the "top" layer. Ignored unless include_top=True. Set classifier_activation=None to return the logits of the "top" layer. Defaults to 'softmax'. When loading pretrained weights, classifier_activation can only be None or "softmax".

Returns

A keras.Model instance.