|TensorFlow 1 version||View source on GitHub|
Instantiates the MobileNet architecture.
See Migration guide for more details.
tf.keras.applications.MobileNet( input_shape=None, alpha=1.0, depth_multiplier=1, dropout=0.001, include_top=True, weights='imagenet', input_tensor=None, pooling=None, classes=1000, classifier_activation='softmax', **kwargs )
Used in the notebooks
|Used in the guide|
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in the
input_shape: Optional shape tuple, only to be specified if
include_topis False (otherwise the input shape has to be
(224, 224, 3)(with
channels_lastdata format) or (3, 224, 224) (with
channels_firstdata format). It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g.
(200, 200, 3)would be one valid value. Default to
input_shapewill be ignored if the
alpha: Controls the width of the network. This is known as the width multiplier in the MobileNet paper. - If
alpha< 1.0, proportionally decreases the number of filters in each layer. - If
alpha> 1.0, proportionally increases the number of filters in each layer. - If
alpha= 1, default number of filters from the paper are used at each layer. Default to 1.0.
depth_multiplier: Depth multiplier for depthwise convolution. This is called the resolution multiplier in the MobileNet paper. Default to 1.0.
dropout: Dropout rate. Default to 0.001.
include_top: Boolean, whether to include the fully-connected layer at the top of the network. Default to
weights: One of
None(random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. Default to
input_tensor: Optional Keras tensor (i.e. output of
layers.Input()) to use as image input for the model.
input_tensoris useful for sharing inputs between multiple different networks. Default to None.
pooling: Optional pooling mode for feature extraction when
None(default) means that the output of the model will be the 4D tensor output of the last convolutional block.
avgmeans that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor.
maxmeans that global max pooling will be applied.
classes: Optional number of classes to classify images into, only to be specified if
include_topis True, and if no
weightsargument is specified. Defaults to 1000.
stror callable. The activation function to use on the "top" layer. Ignored unless
classifier_activation=Noneto return the logits of the "top" layer.
**kwargs: For backwards compatibility only.
ValueError: in case of invalid argument for
weights, or invalid input shape.
Nonewhen using a pretrained top layer.