Xception V1 model for Keras.
application_xception( include_top = TRUE, weights = "imagenet", input_tensor = NULL, input_shape = NULL, pooling = NULL, classes = 1000 ) xception_preprocess_input(x)
whether to include the fully-connected layer at the top of the network.
optional Keras tensor to use as image input for the model.
optional shape list, only to be specified if
Optional pooling mode for feature extraction when
optional number of classes to classify images into, only to be
Input tensor for preprocessing
A Keras model instance.
On ImageNet, this model gets to a top-1 validation accuracy of 0.790 and a top-5 validation accuracy of 0.945.
Do note that the input image format for this model is different than for the VGG16 and ResNet models (299x299 instead of 224x224).
xception_preprocess_input() function should be used for image
This application is only available when using the TensorFlow back-end.