nbfmt

Author: tfdocsbot

site/en/tutorials/customization/custom_training_walkthrough.ipynb

@@ -260,7 +260,6 @@
         "id": "PD33PxSmCrtL"
       },
       "source": [
-        "\n",
         "### Download the preprocessed dataset\n",
         "\n",
         "Now, download the preprocessed penguins dataset (`penguins/processed`) with the `tfds.load` method, which returns a list of `tf.data.Dataset` objects. Note that the `penguins/processed` dataset doesn't come with its own test set, so use an 80:20 split to [slice the full dataset](https://www.tensorflow.org/datasets/splits) into the training and test sets. You will use the test dataset later to verify your model."
@@ -348,7 +347,6 @@
         "id": "LsaVrtNM3Tx5"
       },
       "source": [
-        "\n",
         "## Build a simple linear model\n",
         "\n",
         "### Why model?\n",
@@ -793,7 +791,6 @@
         "id": "z-EvK7hGL0d8"
       },
       "source": [
-        "\n",
         "### Set up the test set\n",
         "\n",
         "Evaluating the model is similar to training the model. The biggest difference is the examples come from a separate *[test set](https://developers.google.com/machine-learning/crash-course/glossary#test_set)* rather than the training set. To fairly assess a model's effectiveness, the examples used to evaluate a model must be different from the examples used to train the model.\n",
@@ -903,24 +900,12 @@
         "  name = class_names[class_idx]\n",
         "  print(\"Example {} prediction: {} ({:4.1f}%)\".format(i, name, 100*p))"
       ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "NpCnZDaycIkY"
-      },
-      "outputs": [],
-      "source": [
-        ""
-      ]
     }
   ],
   "metadata": {
     "colab": {
       "collapsed_sections": [],
       "name": "custom_training_walkthrough.ipynb",
-      "provenance": [],
       "toc_visible": true
     },
     "kernelspec": {