HyperEfficientNet
- 원본 링크 : https://keras.io/api/keras_tuner/hypermodels/hyper_efficientnet/
- 최종 확인 : 2024-11-25
HyperEfficientNet
class
keras_tuner.applications.HyperEfficientNet(
input_shape=None, input_tensor=None, classes=None, augmentation_model=None, **kwargs
)
An EfficientNet hypermodel.
Models built by HyperEfficientNet
take images with shape (height, width,
channels) as input. The output are one-hot encoded with the length matching
the number of classes specified by the classes
argument.
Arguments
- input_shape: Optional shape tuple, e.g.
(256, 256, 3)
. One ofinput_shape
orinput_tensor
must be specified. - input_tensor: Optional Keras tensor (i.e. output of
layers.Input()
) to use as image input for the model. One ofinput_shape
orinput_tensor
must be specified. - classes: Optional number of classes to classify images into, only to be
specified if
include_top
is True, and if noweights
argument is specified. - augmentation_model: Optional
Model
orHyperModel
instance for image augmentation. - **kwargs: Additional keyword arguments that apply to all hypermodels.
See
keras_tuner.HyperModel
.