Module: tf.compat.v1.keras.applications.xception

Xception V1 model for Keras.

On ImageNet, this model gets to a top-1 validation accuracy of 0.790 and a top-5 validation accuracy of 0.945.

Reference paper:

• Xception: Deep Learning with Depthwise Separable Convolutions (CVPR 2017)

Functions

Xception(...): Instantiates the Xception architecture.

decode_predictions(...): Decodes the prediction of an ImageNet model.

preprocess_input(...): Preprocesses a tensor or Numpy array encoding a batch of images.