Update transfer_learning_with_hub.ipynb

site/en/tutorials/images/transfer_learning_with_hub.ipynb

@@ -68,7 +68,7 @@
         "\n",
         "This tutorial demonstrates how to:\n",
         "\n",
-        "1. Use models from TensorFlow Hub with `keras`.\n",
+        "1. Use models from TensorFlow Hub with `tf.keras`.\n",
         "1. Use an image classification model from TensorFlow Hub.\n",
         "1. Do simple transfer learning to fine-tune a model for your own image classes."
       ]
@@ -340,7 +340,7 @@
         "id": "jFHdp18ccah7"
       },
       "source": [
-        "First, load this data into the model using the image data off disk with `keras.utils.image_dataset_from_directory`, which will generate a `tf.data.Dataset`:"
+        "First, load this data into the model using the image data off disk with `tf.keras.utils.image_dataset_from_directory`, which will generate a `tf.data.Dataset`:"
       ]
     },
     {
@@ -401,7 +401,7 @@
         "id": "L0Btd0V3C8h4"
       },
       "source": [
-        "Second, because TensorFlow Hub's convention for image models is to expect float inputs in the `[0, 1]` range, use the `keras.layers.Rescaling` preprocessing layer to achieve this."
+        "Second, because TensorFlow Hub's convention for image models is to expect float inputs in the `[0, 1]` range, use the `tf.keras.layers.Rescaling` preprocessing layer to achieve this."
       ]
     },
     {
@@ -410,7 +410,7 @@
         "id": "Rs6gfO-ApTQW"
       },
       "source": [
-        "Note: You could also include the `keras.layers.Rescaling` layer inside the model. Refer to the [Working with preprocessing layers](https://www.tensorflow.org/guide/keras/preprocessing_layers) guide for a discussion of the tradeoffs."
+        "Note: You could also include the `tf.keras.layers.Rescaling` layer inside the model. Refer to the [Working with preprocessing layers](https://www.tensorflow.org/guide/keras/preprocessing_layers) guide for a discussion of the tradeoffs."
       ]
     },
     {
@@ -622,7 +622,7 @@
       "source": [
         "### Attach a classification head\n",
         "\n",
-        "To complete the model, wrap the feature extractor layer in a `keras.Sequential` model and add a fully-connected layer for classification:"
+        "To complete the model, wrap the feature extractor layer in a `tf.keras.Sequential` model and add a fully-connected layer for classification:"
       ]
     },
     {
@@ -673,7 +673,7 @@
       "source": [
         "### Train the model\n",
         "\n",
-        "Use `Model.compile` to configure the training process and add a `keras.callbacks.TensorBoard` callback to create and store logs:"
+        "Use `Model.compile` to configure the training process and add a `tf.keras.callbacks.TensorBoard` callback to create and store logs:"
       ]
     },
     {