Add Normalization layer docs, fix typos

guides/making_new_layers_and_models_via_subclassing.py

@@ -554,7 +554,7 @@ def call(self, inputs, training=None):
 literature as a "model" (as in "deep learning model") or as a "network" (as in
 "deep neural network").
 
-So if you'ree wondering, "should I use the `Layer` class or the `Model` class?",
+So if you're wondering, "should I use the `Layer` class or the `Model` class?",
 ask yourself: will I need to call `fit()` on it? Will I need to call `save()`
 on it? If so, go with `Model`. If not (either because your class is just a block
 in a bigger system, or because you are writing training & saving code yourself),

guides/md/making_new_layers_and_models_via_subclassing.md

@@ -685,7 +685,7 @@ Meanwhile, the `Model` class corresponds to what is referred to in the
 literature as a "model" (as in "deep learning model") or as a "network" (as in
 "deep neural network").
 
-So if you'ree wondering, "should I use the `Layer` class or the `Model` class?",
+So if you're wondering, "should I use the `Layer` class or the `Model` class?",
 ask yourself: will I need to call `fit()` on it? Will I need to call `save()`
 on it? If so, go with `Model`. If not (either because your class is just a block
 in a bigger system, or because you are writing training & saving code yourself),

scripts/layers_master.py

@@ -278,6 +278,11 @@
                             'title': 'TextVectorization layer',
                             'generate': ['tensorflow.keras.layers.experimental.preprocessing.TextVectorization']
                         },
+                        {
+                            'path': 'normalization',
+                            'title': 'Normalization layer',
+                            'generate': ['tensorflow.keras.layers.experimental.preprocessing.Normalization']
+                        },
                     ]
                 },
                 # {

theme/landing.html

@@ -73,7 +73,7 @@ <h2>Iterate at the speed of thought.</h2>
             Keras is the most used deep learning framework among top-5 winning teams on <a href='https://www.kaggle.com/'>Kaggle</a>.
             Because Keras makes it easier to run new experiments,
             it empowers you to try more ideas than your competition, faster.
-            And this how you win.
+            And this is how you win.
           </p>
         </div>
       </div>