show more


from keras.applications.mobilenet_v2 import MobileNetV2
MobileNetV2(input_shape=None, alpha=1.0, depth_multiplier=1, include_top=True, weights='imagenet', input_tensor=None, pooling=None, classes=1000)

MobileNetV2 model, with weights pre-trained on ImageNet.

Note that this model only supports the data format 'channels_last' (height, width, channels).

The default input size for this model is 224x224.


  • input_shape: optional shape tuple, to be specified if you would like to use a model with an input img resolution that is not (224, 224, 3). It should have exactly 3 inputs channels (224, 224, 3). You can also omit this option if you would like to infer input_shape from an input_tensor. If you choose to include both input_tensor and input_shape then input_shape will be used if they match, if the shapes do not match then we will throw an error. E.g. (160, 160, 3) would be one valid value.
  • alpha: controls the width of the network. This is known as the width multiplier in the MobileNetV2 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.
  • depth_multiplier: depth multiplier for depthwise convolution (also called the resolution multiplier)
  • include_top: whether to include the fully-connected layer at the top of the network.
  • weights: one of None (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded.
  • input_tensor: 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_top is False.
    • 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.
  • classes: optional number of classes to classify images into, only to be specified if include_top is True, and if no weights argument is specified.


A Keras model instance.


ValueError: in case of invalid argument for weights, or invalid input shape or invalid depth_multiplier, alpha, rows when weights='imagenet'


How helpful was this page?