Fix / standardize references in Keras Applications docstrings.

PiperOrigin-RevId: 308674354
Change-Id: Id0d186974e7dcebc8a9b2d80ca940e88f20acf47

tensorflow/python/keras/applications/densenet.py

@@ -138,9 +138,9 @@ def DenseNet(
     classifier_activation='softmax'):
   """Instantiates the DenseNet architecture.
 
-  Reference paper:
-  - [Densely Connected Convolutional Networks]
-    (https://arxiv.org/abs/1608.06993) (CVPR 2017 Best Paper Award)
+  Reference:
+  - [Densely Connected Convolutional Networks](
+      https://arxiv.org/abs/1608.06993) (CVPR 2017)
 
   Optionally loads weights pre-trained on ImageNet.
   Note that the data format convention used by the model is

tensorflow/python/keras/applications/efficientnet.py

@@ -145,7 +145,7 @@ layers = VersionAwareLayers()
 
 BASE_DOCSTRING = """Instantiates the {name} architecture.
 
-  Reference paper:
+  Reference:
   - [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](
       https://arxiv.org/abs/1905.11946) (ICML 2019)
 

tensorflow/python/keras/applications/inception_resnet_v2.py

@@ -53,7 +53,7 @@ def InceptionResNetV2(include_top=True,
                       **kwargs):
   """Instantiates the Inception-ResNet v2 architecture.
 
-  Reference paper:
+  Reference:
   - [Inception-v4, Inception-ResNet and the Impact of
      Residual Connections on Learning](https://arxiv.org/abs/1602.07261)
     (AAAI 2017)

tensorflow/python/keras/applications/inception_v3.py

@@ -56,7 +56,7 @@ def InceptionV3(
     classifier_activation='softmax'):
   """Instantiates the Inception v3 architecture.
 
-  Reference paper:
+  Reference:
   - [Rethinking the Inception Architecture for Computer Vision](
       http://arxiv.org/abs/1512.00567) (CVPR 2016)
 

tensorflow/python/keras/applications/mobilenet.py

@@ -95,9 +95,10 @@ def MobileNet(input_shape=None,
               **kwargs):
   """Instantiates the MobileNet architecture.
 
-  Reference paper:
-  - [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision
-    Applications](https://arxiv.org/abs/1704.04861)
+  Reference:
+  - [MobileNets: Efficient Convolutional Neural Networks
+     for Mobile Vision Applications](
+      https://arxiv.org/abs/1704.04861)
 
   Optionally loads weights pre-trained on ImageNet.
   Note that the data format convention used by the model is

tensorflow/python/keras/applications/mobilenet_v2.py

@@ -106,9 +106,9 @@ def MobileNetV2(input_shape=None,
                 **kwargs):
   """Instantiates the MobileNetV2 architecture.
 
-  Reference paper:
-  - [MobileNetV2: Inverted Residuals and Linear Bottlenecks]
-  (https://arxiv.org/abs/1801.04381) (CVPR 2018)
+  Reference:
+  - [MobileNetV2: Inverted Residuals and Linear Bottlenecks](
+      https://arxiv.org/abs/1801.04381) (CVPR 2018)
 
   Optionally loads weights pre-trained on ImageNet.
 

tensorflow/python/keras/applications/nasnet.py

@@ -79,9 +79,9 @@ def NASNet(
     classifier_activation='softmax'):
   """Instantiates a NASNet model.
 
-  Reference paper:
-  - [Learning Transferable Architectures for Scalable Image Recognition]
-    (https://arxiv.org/abs/1707.07012) (CVPR 2018)
+  Reference:
+  - [Learning Transferable Architectures for Scalable Image Recognition](
+      https://arxiv.org/abs/1707.07012) (CVPR 2018)
 
   Optionally loads weights pre-trained on ImageNet.
   Note that the data format convention used by the model is

tensorflow/python/keras/applications/resnet.py

@@ -15,9 +15,9 @@
 # pylint: disable=invalid-name
 """ResNet models for Keras.
 
-Reference paper:
-  - [Deep Residual Learning for Image Recognition]
-    (https://arxiv.org/abs/1512.03385) (CVPR 2015)
+Reference:
+  - [Deep Residual Learning for Image Recognition](
+      https://arxiv.org/abs/1512.03385) (CVPR 2015)
 """
 from __future__ import absolute_import
 from __future__ import division
@@ -72,9 +72,9 @@ def ResNet(stack_fn,
            **kwargs):
   """Instantiates the ResNet, ResNetV2, and ResNeXt architecture.
 
-  Reference paper:
-  - [Deep Residual Learning for Image Recognition]
-    (https://arxiv.org/abs/1512.03385) (CVPR 2015)
+  Reference:
+  - [Deep Residual Learning for Image Recognition](
+      https://arxiv.org/abs/1512.03385) (CVPR 2015)
 
   Optionally loads weights pre-trained on ImageNet.
   Note that the data format convention used by the model is

tensorflow/python/keras/applications/resnet_v2.py

@@ -138,7 +138,7 @@ decode_predictions.__doc__ = imagenet_utils.decode_predictions.__doc__
 
 DOC = """
 
-  Reference paper:
+  Reference:
   - [Identity Mappings in Deep Residual Networks]
     (https://arxiv.org/abs/1603.05027) (CVPR 2016)
 

tensorflow/python/keras/applications/xception.py

@@ -18,7 +18,7 @@
 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:
+Reference:
   - [Xception: Deep Learning with Depthwise Separable Convolutions](
       https://arxiv.org/abs/1610.02357) (CVPR 2017)
 
@@ -60,6 +60,10 @@ def Xception(
     classifier_activation='softmax'):
   """Instantiates the Xception architecture.
 
+  Reference:
+  - [Xception: Deep Learning with Depthwise Separable Convolutions](
+      https://arxiv.org/abs/1610.02357) (CVPR 2017)
+
   Optionally loads weights pre-trained on ImageNet.
   Note that the data format convention used by the model is
   the one specified in your Keras config at `~/.keras/keras.json`.