debug

Author: MarkDaoust

Diff for: site/en/tutorials/structured_data/preprocessing_layers.ipynb

@@ -447,7 +447,7 @@
       "source": [
         "### Categorical columns\n",
         "\n",
-        "Pet `Type`s in the dataset are represented as strings—`Dog`s and `Cat`s—which need to be multi-hot encoded before being fed into the model. The `Age` feature \n",
+        "Pet `Type`s in the dataset are represented as strings—`Dog`s and `Cat`s—which need to be multi-hot encoded before being fed into the model. The `Age` feature\n",
         "\n",
         "Define another new utility function that returns a layer which maps values from a vocabulary to integer indices and multi-hot encodes the features using the `tf.keras.layers.StringLookup`, `tf.keras.layers.IntegerLookup`, and `tf.keras.CategoryEncoding` preprocessing layers:"
       ]
@@ -589,15 +589,15 @@
       },
       "outputs": [],
       "source": [
-        "all_inputs = []\n",
+        "all_inputs = {}\n",
         "encoded_features = []\n",
         "\n",
         "# Numerical features.\n",
         "for header in ['PhotoAmt', 'Fee']:\n",
         "  numeric_col = tf.keras.Input(shape=(1,), name=header)\n",
         "  normalization_layer = get_normalization_layer(header, train_ds)\n",
         "  encoded_numeric_col = normalization_layer(numeric_col)\n",
-        "  all_inputs.append(numeric_col)\n",
+        "  all_inputs[header] = numeric_col\n",
         "  encoded_features.append(encoded_numeric_col)"
       ]
     },
@@ -625,7 +625,7 @@
         "                                             dtype='int64',\n",
         "                                             max_tokens=5)\n",
         "encoded_age_col = encoding_layer(age_col)\n",
-        "all_inputs.append(age_col)\n",
+        "all_inputs['Age'] = age_col\n",
         "encoded_features.append(encoded_age_col)"
       ]
     },
@@ -656,7 +656,7 @@
         "                                               dtype='string',\n",
         "                                               max_tokens=5)\n",
         "  encoded_categorical_col = encoding_layer(categorical_col)\n",
-        "  all_inputs.append(categorical_col)\n",
+        "  all_inputs[header] = categorical_col\n",
         "  encoded_features.append(encoded_categorical_col)"
       ]
     },
@@ -678,6 +678,17 @@
         "The next step is to create a model using the [Keras Functional API](https://www.tensorflow.org/guide/keras/functional). For the first layer in your model, merge the list of feature inputs—`encoded_features`—into one vector via concatenation with `tf.keras.layers.concatenate`."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "EtkwHC-akvcv"
+      },
+      "outputs": [],
+      "source": [
+        "encoded_features"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -713,7 +724,8 @@
       "source": [
         "model.compile(optimizer='adam',\n",
         "              loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),\n",
-        "              metrics=[\"accuracy\"])"
+        "              metrics=[\"accuracy\"],\n",
+        "              run_eagerly=True)"
       ]
     },
     {
@@ -734,7 +746,7 @@
       "outputs": [],
       "source": [
         "# Use `rankdir='LR'` to make the graph horizontal.\n",
-        "tf.keras.utils.plot_model(model, show_shapes=True, rankdir=\"LR\")"
+        "tf.keras.utils.plot_model(model, show_shapes=True, show_layer_names=True, rankdir=\"LR\")"
       ]
     },
     {
@@ -765,8 +777,8 @@
       },
       "outputs": [],
       "source": [
-        "loss, accuracy = model.evaluate(test_ds)\n",
-        "print(\"Accuracy\", accuracy)"
+        "result = model.evaluate(test_ds, return_dict=True)\n",
+        "print(result)"
       ]
     },
     {
@@ -869,7 +881,6 @@
   ],
   "metadata": {
     "colab": {
-      "collapsed_sections": [],
       "name": "preprocessing_layers.ipynb",
       "toc_visible": true
     },