Instantiates the MobileNetV3Large architecture
application_mobilenet_v3_large( input_shape = NULL, alpha = 1, minimalistic = FALSE, include_top = TRUE, weights = "imagenet", input_tensor = NULL, classes = 1000L, pooling = NULL, dropout_rate = 0.2, classifier_activation = "softmax", include_preprocessing = TRUE ) application_mobilenet_v3_small( input_shape = NULL, alpha = 1, minimalistic = FALSE, include_top = TRUE, weights = "imagenet", input_tensor = NULL, classes = 1000L, pooling = NULL, dropout_rate = 0.2, classifier_activation = "softmax", include_preprocessing = TRUE )
Optional shape vector, to be specified if you would
like to use a model with an input image resolution that is not
controls the width of the network. This is known as the depth multiplier in the MobileNetV3 paper, but the name is kept for consistency with MobileNetV1 in Keras.
In addition to large and small models this module also contains so-called minimalistic models, these models have the same per-layer dimensions characteristic as MobilenetV3 however, they don't utilize any of the advanced blocks (squeeze-and-excite units, hard-swish, and 5x5 convolutions). While these models are less efficient on CPU, they are much more performant on GPU/DSP.
Boolean, whether to include the fully-connected
layer at the top of the network. Defaults to
String, one of
Optional Keras tensor (i.e. output of
Integer, optional number of classes to classify images
into, only to be specified if
String, optional pooling mode for feature extraction
fraction of the input units to drop on the last layer.
A string or callable. The activation function to use
on the "top" layer. Ignored unless
Boolean, whether to include the preprocessing
Searching for MobileNetV3 (ICCV 2019)
MACs stands for Multiply Adds
|Classification Checkpoint||MACs(M)||Parameters(M)||Top1 Accuracy||Pixel1 CPU(ms)|
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.
Each Keras application typically expects a specific kind of input preprocessing.
For ModelNetV3, by default input preprocessing is included as a part of the
model (as a
Rescaling layer), and thus
a preprocessing function is not necessary. In this use case, ModelNetV3 models expect their inputs
to be float tensors of pixels with values in the
At the same time, preprocessing as a part of the model (i.e.
layer) can be disabled by setting
include_preprocessing argument to FALSE.
With preprocessing disabled ModelNetV3 models expect their inputs to be float
tensors of pixels with values in the
[-1, 1] range.