InceptionV3

show more

Implementations

from keras.applications.inception_v3 import InceptionV3
InceptionV3(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000)

Inception V3 model, with weights pre-trained on ImageNet.

This model and can be built both with 'channels_first' data format (channels, height, width) or 'channels_last' data format (height, width, channels).

The default input size for this model is 299x299.

Arguments

  • include_top: whether to include the fully-connected layer at the top of the network.
  • weights: one of None (random initialization) or 'imagenet' (pre-training on ImageNet).
  • input_tensor: optional Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
  • input_shape: optional shape tuple, only to be specified if include_top is False (otherwise the input shape has to be (299, 299, 3) (with 'channels_last' data format) or (3, 299, 299)(with 'channels_first' data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 75. E.g. (150, 150, 3) would be one valid value.
  • 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.

Returns

A Keras Model instance.

(@ keras.io) https://keras.io/applications/#inceptionv3

kerasinceptionv3
How helpful was this page?