Instantiates a Mobile NASNet model in ImageNet mode.
View aliases
Main aliases
tf.keras.applications.nasnet.NASNetMobile
See Migration guide for more details.
tf.compat.v1.keras.applications.NASNetMobile
, tf.compat.v1.keras.applications.nasnet.NASNetMobile
tf.keras.applications.NASNetMobile(
input_shape=None, include_top=True, weights='imagenet',
input_tensor=None, pooling=None, classes=1000
)
Reference:
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at ~/.keras/keras.json
.
Arguments | |
---|---|
input_
|
Optional shape tuple, only to be specified
if include_ is False (otherwise the input shape
has to be (224, for NASNetMobile
It should have exactly 3 inputs channels,
and width and height should be no smaller than 32.
E.g. (224, would be one valid value.
|
include_
|
Whether to include the fully-connected layer at the top of the network. |
weights
|
None (random initialization) or
imagenet (ImageNet weights)
For loading imagenet weights, input_ should be (224, 224, 3)
|
input_
|
Optional Keras tensor (i.e. output of
layers.Input() )
to use as image input for the model.
|
pooling
|
Optional pooling mode for feature extraction
when include_ is False .
|
classes
|
Optional number of classes to classify images
into, only to be specified if include_ is True, and
if no weights argument is specified.
|
Returns | |
---|---|
A Keras model instance. |
Raises | |
---|---|
ValueError
|
In case of invalid argument for weights ,
or invalid input shape.
|
RuntimeError
|
If attempting to run this model with a backend that does not support separable convolutions. |