Help protect the Great Barrier Reef with TensorFlow on Kaggle Join Challenge

Module: tf.keras.applications.xception

TensorFlow 1 version

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(...): 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.