Keras guides snapshot: Mon, 09 Aug 2021 07:01:49 GMT

tensorflow · Aug 9, 2021 · fb351df · fb351df
1 parent d606019
commit fb351df
Show file tree

Hide file tree

Showing 2 changed files with 33 additions and 30 deletions.
diff --git a/site/en/guide/keras/preprocessing_layers.ipynb b/site/en/guide/keras/preprocessing_layers.ipynb
@@ -83,56 +83,59 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "85f1ef32e744"
+        "id": "313360fa9024"
       },
       "source": [
         "## Available preprocessing\n",
         "\n",
         "### Text preprocessing\n",
         "\n",
-        "- `TextVectorization` layer: turns raw strings into an encoded representation that can be\n",
-        "read by an `Embedding` layer or `Dense` layer.\n",
+        "- `tf.keras.layers.TextVectorization`: turns raw strings into an encoded\n",
+        "  representation that can be read by an `Embedding` layer or `Dense` layer.\n",
         "\n",
         "### Numerical features preprocessing\n",
         "\n",
-        "- `Normalization` layer: performs feature-wise normalize of input features.\n",
-        "- `Discretization` layer: turns continuous numerical features into integer categorical\n",
-        "features.\n",
+        "- `tf.keras.layers.Normalization`: performs feature-wise normalize of\n",
+        "  input features.\n",
+        "- `tf.keras.layers.Discretization`: turns continuous numerical features\n",
+        "  into integer categorical features.\n",
         "\n",
         "### Categorical features preprocessing\n",
         "\n",
-        "- `CategoryEncoding` layer: turns integer categorical features into one-hot, multi-hot,\n",
-        "or count dense representations.\n",
-        "- `Hashing` layer: performs categorical feature hashing, also known as the \"hashing\n",
-        "trick\".\n",
-        "- `StringLookup` layer: turns string categorical values an encoded representation that can be\n",
-        "read by an `Embedding` layer or `Dense` layer.\n",
-        "- `IntegerLookup` layer: turns integer categorical values into an encoded representation that can be\n",
-        "read by an `Embedding` layer or `Dense` layer.\n",
+        "- `tf.keras.layers.CategoryEncoding`: turns integer categorical features\n",
+        "  into one-hot, multi-hot, or count dense representations.\n",
+        "- `tf.keras.layers.Hashing`: performs categorical feature hashing, also known as\n",
+        "  the \"hashing trick\".\n",
+        "- `tf.keras.layers.StringLookup`: turns string categorical values an encoded\n",
+        "  representation that can be read by an `Embedding` layer or `Dense` layer.\n",
+        "- `tf.keras.layers.IntegerLookup`: turns integer categorical values into an\n",
+        "  encoded representation that can be read by an `Embedding` layer or `Dense`\n",
+        "  layer.\n",
         "\n",
         "\n",
         "### Image preprocessing\n",
         "\n",
         "These layers are for standardizing the inputs of an image model.\n",
         "\n",
-        "- `Resizing` layer: resizes a batch of images to a target size.\n",
-        "- `Rescaling` layer: rescales and offsets the values of a batch of image (e.g. go from\n",
-        "inputs in the `[0, 255]` range to inputs in the `[0, 1]` range.\n",
-        "- `CenterCrop` layer: returns a center crop of a batch of images.\n",
+        "- `tf.keras.layers.Resizing`: resizes a batch of images to a target size.\n",
+        "- `tf.keras.layers.Rescaling`: rescales and offsets the values of a batch of\n",
+        "  image (e.g. go from inputs in the `[0, 255]` range to inputs in the `[0, 1]`\n",
+        "  range.\n",
+        "- `tf.keras.layers.CenterCrop`: returns a center crop of a batch of images.\n",
         "\n",
         "### Image data augmentation\n",
         "\n",
         "These layers apply random augmentation transforms to a batch of images. They\n",
         "are only active during training.\n",
         "\n",
-        "- `RandomCrop` layer\n",
-        "- `RandomFlip` layer\n",
-        "- `RandomTranslation` layer\n",
-        "- `RandomRotation` layer\n",
-        "- `RandomZoom` layer\n",
-        "- `RandomHeight` layer\n",
-        "- `RandomWidth` layer\n",
-        "- `RandomContrast` layer"
+        "- `tf.keras.layers.RandomCrop`\n",
+        "- `tf.keras.layers.RandomFlip`\n",
+        "- `tf.keras.layers.RandomTranslation`\n",
+        "- `tf.keras.layers.RandomRotation`\n",
+        "- `tf.keras.layers.RandomZoom`\n",
+        "- `tf.keras.layers.RandomHeight`\n",
+        "- `tf.keras.layers.RandomWidth`\n",
+        "- `tf.keras.layers.RandomContrast`"
       ]
     },
     {

diff --git a/site/en/guide/keras/writing_a_training_loop_from_scratch.ipynb b/site/en/guide/keras/writing_a_training_loop_from_scratch.ipynb
@@ -359,14 +359,14 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "940d8d9fae83"
+        "id": "1c9a16c21790"
       },
       "source": [
         "## Speeding-up your training step with `tf.function`\n",
         "\n",
-        "The default runtime in TensorFlow 2.0 is\n",
-        "[eager execution](https://www.tensorflow.org/guide/eager). As such, our training loop\n",
-        "above executes eagerly.\n",
+        "The default runtime in TensorFlow 2 is\n",
+        "[eager execution](https://www.tensorflow.org/guide/eager).\n",
+        "As such, our training loop above executes eagerly.\n",
         "\n",
         "This is great for debugging, but graph compilation has a definite performance\n",
         "advantage. Describing your computation as a static graph enables the framework\n",