# Module: tf.keras.applications.xception

<br />

|---|
| [![](https://www.tensorflow.org/images/tf_logo_32px.png) TensorFlow 1 version](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/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](https://arxiv.org/abs/1610.02357) (CVPR 2017)

## Functions

[`Xception(...)`](https://www.tensorflow.org/versions/r2.2/api_docs/python/tf/keras/applications/Xception): Instantiates the Xception architecture.

[`decode_predictions(...)`](https://www.tensorflow.org/versions/r2.2/api_docs/python/tf/keras/applications/xception/decode_predictions): Decodes the prediction of an ImageNet model.

[`preprocess_input(...)`](https://www.tensorflow.org/versions/r2.2/api_docs/python/tf/keras/applications/xception/preprocess_input): Preprocesses a tensor or Numpy array encoding a batch of images.