EfficientNetV2B0
functionkeras.applications.EfficientNetV2B0(
include_top=True,
weights="imagenet",
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation="softmax",
include_preprocessing=True,
)
Instantiates the EfficientNetV2B0 architecture.
Reference
This function returns a 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 Keras Application expects a specific kind of input preprocessing.
For EfficientNetV2, by default input preprocessing is included as a part of
the model (as a Rescaling
layer), and thus
keras.applications.efficientnet_v2.preprocess_input
is actually a
pass-through function. In this use case, EfficientNetV2 models expect their
inputs to be float tensors of pixels with values in the [0, 255]
range.
At the same time, preprocessing as a part of the model (i.e. Rescaling
layer) can be disabled by setting include_preprocessing
argument to False
.
With preprocessing disabled EfficientNetV2 models expect their inputs to be
float tensors of pixels with values in the [-1, 1]
range.
Arguments
True
.None
(random initialization),
"imagenet"
(pre-training on ImageNet),
or the path to the weights file to be loaded. Defaults to "imagenet"
.layers.Input()
)
to use as image input for the model.include_top
is False
.
It should have exactly 3 inputs channels.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.include_top
is True
, and
if no weights
argument is specified. Defaults to 1000 (number of
ImageNet classes).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 model instance.
EfficientNetV2B1
functionkeras.applications.EfficientNetV2B1(
include_top=True,
weights="imagenet",
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation="softmax",
include_preprocessing=True,
)
Instantiates the EfficientNetV2B1 architecture.
Reference
This function returns a 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 Keras Application expects a specific kind of input preprocessing.
For EfficientNetV2, by default input preprocessing is included as a part of
the model (as a Rescaling
layer), and thus
keras.applications.efficientnet_v2.preprocess_input
is actually a
pass-through function. In this use case, EfficientNetV2 models expect their
inputs to be float tensors of pixels with values in the [0, 255]
range.
At the same time, preprocessing as a part of the model (i.e. Rescaling
layer) can be disabled by setting include_preprocessing
argument to False
.
With preprocessing disabled EfficientNetV2 models expect their inputs to be
float tensors of pixels with values in the [-1, 1]
range.
Arguments
True
.None
(random initialization),
"imagenet"
(pre-training on ImageNet),
or the path to the weights file to be loaded. Defaults to "imagenet"
.layers.Input()
)
to use as image input for the model.include_top
is False
.
It should have exactly 3 inputs channels.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.include_top
is True
, and
if no weights
argument is specified. Defaults to 1000 (number of
ImageNet classes).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 model instance.
EfficientNetV2B2
functionkeras.applications.EfficientNetV2B2(
include_top=True,
weights="imagenet",
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation="softmax",
include_preprocessing=True,
)
Instantiates the EfficientNetV2B2 architecture.
Reference
This function returns a 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 Keras Application expects a specific kind of input preprocessing.
For EfficientNetV2, by default input preprocessing is included as a part of
the model (as a Rescaling
layer), and thus
keras.applications.efficientnet_v2.preprocess_input
is actually a
pass-through function. In this use case, EfficientNetV2 models expect their
inputs to be float tensors of pixels with values in the [0, 255]
range.
At the same time, preprocessing as a part of the model (i.e. Rescaling
layer) can be disabled by setting include_preprocessing
argument to False
.
With preprocessing disabled EfficientNetV2 models expect their inputs to be
float tensors of pixels with values in the [-1, 1]
range.
Arguments
True
.None
(random initialization),
"imagenet"
(pre-training on ImageNet),
or the path to the weights file to be loaded. Defaults to "imagenet"
.layers.Input()
)
to use as image input for the model.include_top
is False
.
It should have exactly 3 inputs channels.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.include_top
is True
, and
if no weights
argument is specified. Defaults to 1000 (number of
ImageNet classes).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 model instance.
EfficientNetV2B3
functionkeras.applications.EfficientNetV2B3(
include_top=True,
weights="imagenet",
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation="softmax",
include_preprocessing=True,
)
Instantiates the EfficientNetV2B3 architecture.
Reference
This function returns a 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 Keras Application expects a specific kind of input preprocessing.
For EfficientNetV2, by default input preprocessing is included as a part of
the model (as a Rescaling
layer), and thus
keras.applications.efficientnet_v2.preprocess_input
is actually a
pass-through function. In this use case, EfficientNetV2 models expect their
inputs to be float tensors of pixels with values in the [0, 255]
range.
At the same time, preprocessing as a part of the model (i.e. Rescaling
layer) can be disabled by setting include_preprocessing
argument to False
.
With preprocessing disabled EfficientNetV2 models expect their inputs to be
float tensors of pixels with values in the [-1, 1]
range.
Arguments
True
.None
(random initialization),
"imagenet"
(pre-training on ImageNet),
or the path to the weights file to be loaded. Defaults to "imagenet"
.layers.Input()
)
to use as image input for the model.include_top
is False
.
It should have exactly 3 inputs channels.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.include_top
is True
, and
if no weights
argument is specified. Defaults to 1000 (number of
ImageNet classes).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 model instance.
EfficientNetV2S
functionkeras.applications.EfficientNetV2S(
include_top=True,
weights="imagenet",
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation="softmax",
include_preprocessing=True,
)
Instantiates the EfficientNetV2S architecture.
Reference
This function returns a 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 Keras Application expects a specific kind of input preprocessing.
For EfficientNetV2, by default input preprocessing is included as a part of
the model (as a Rescaling
layer), and thus
keras.applications.efficientnet_v2.preprocess_input
is actually a
pass-through function. In this use case, EfficientNetV2 models expect their
inputs to be float tensors of pixels with values in the [0, 255]
range.
At the same time, preprocessing as a part of the model (i.e. Rescaling
layer) can be disabled by setting include_preprocessing
argument to False
.
With preprocessing disabled EfficientNetV2 models expect their inputs to be
float tensors of pixels with values in the [-1, 1]
range.
Arguments
True
.None
(random initialization),
"imagenet"
(pre-training on ImageNet),
or the path to the weights file to be loaded. Defaults to "imagenet"
.layers.Input()
)
to use as image input for the model.include_top
is False
.
It should have exactly 3 inputs channels.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.include_top
is True
, and
if no weights
argument is specified. Defaults to 1000 (number of
ImageNet classes).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 model instance.
EfficientNetV2M
functionkeras.applications.EfficientNetV2M(
include_top=True,
weights="imagenet",
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation="softmax",
include_preprocessing=True,
)
Instantiates the EfficientNetV2M architecture.
Reference
This function returns a 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 Keras Application expects a specific kind of input preprocessing.
For EfficientNetV2, by default input preprocessing is included as a part of
the model (as a Rescaling
layer), and thus
keras.applications.efficientnet_v2.preprocess_input
is actually a
pass-through function. In this use case, EfficientNetV2 models expect their
inputs to be float tensors of pixels with values in the [0, 255]
range.
At the same time, preprocessing as a part of the model (i.e. Rescaling
layer) can be disabled by setting include_preprocessing
argument to False
.
With preprocessing disabled EfficientNetV2 models expect their inputs to be
float tensors of pixels with values in the [-1, 1]
range.
Arguments
True
.None
(random initialization),
"imagenet"
(pre-training on ImageNet),
or the path to the weights file to be loaded. Defaults to "imagenet"
.layers.Input()
)
to use as image input for the model.include_top
is False
.
It should have exactly 3 inputs channels.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.include_top
is True
, and
if no weights
argument is specified. Defaults to 1000 (number of
ImageNet classes).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 model instance.
EfficientNetV2L
functionkeras.applications.EfficientNetV2L(
include_top=True,
weights="imagenet",
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation="softmax",
include_preprocessing=True,
)
Instantiates the EfficientNetV2L architecture.
Reference
This function returns a 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 Keras Application expects a specific kind of input preprocessing.
For EfficientNetV2, by default input preprocessing is included as a part of
the model (as a Rescaling
layer), and thus
keras.applications.efficientnet_v2.preprocess_input
is actually a
pass-through function. In this use case, EfficientNetV2 models expect their
inputs to be float tensors of pixels with values in the [0, 255]
range.
At the same time, preprocessing as a part of the model (i.e. Rescaling
layer) can be disabled by setting include_preprocessing
argument to False
.
With preprocessing disabled EfficientNetV2 models expect their inputs to be
float tensors of pixels with values in the [-1, 1]
range.
Arguments
True
.None
(random initialization),
"imagenet"
(pre-training on ImageNet),
or the path to the weights file to be loaded. Defaults to "imagenet"
.layers.Input()
)
to use as image input for the model.include_top
is False
.
It should have exactly 3 inputs channels.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.include_top
is True
, and
if no weights
argument is specified. Defaults to 1000 (number of
ImageNet classes).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 model instance.