{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "pixDvex9KBqt"
      },
      "source": [
        "##### Copyright 2019 The TensorFlow Authors."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "cellView": "form",
        "id": "K16pBM8mKK7a"
      },
      "outputs": [],
      "source": [
        "#@title Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
        "# You may obtain a copy of the License at\n",
        "#\n",
        "# https://www.apache.org/licenses/LICENSE-2.0\n",
        "#\n",
        "# Unless required by applicable law or agreed to in writing, software\n",
        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
        "# See the License for the specific language governing permissions and\n",
        "# limitations under the License."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "TfRdquslKbO3"
      },
      "source": [
        "# Load NumPy data"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-uq3F0ggKlZb"
      },
      "source": [
        "<table class=\"tfo-notebook-buttons\" align=\"left\">\n",
        "  <td>\n",
        "    <a target=\"_blank\" href=\"https://www.tensorflow.org/tutorials/load_data/numpy\"><img src=\"https://www.tensorflow.org/images/tf_logo_32px.png\" />View on TensorFlow.org</a>\n",
        "  </td>\n",
        "  <td>\n",
        "    <a target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/tutorials/load_data/numpy.ipynb\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
        "  </td>\n",
        "  <td>\n",
        "    <a target=\"_blank\" href=\"https://github.com/tensorflow/docs/blob/master/site/en/tutorials/load_data/numpy.ipynb\"><img src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" />View source on GitHub</a>\n",
        "  </td>\n",
        "  <td>\n",
        "    <a href=\"https://storage.googleapis.com/tensorflow_docs/docs/site/en/tutorials/load_data/numpy.ipynb\"><img src=\"https://www.tensorflow.org/images/download_logo_32px.png\" />Download notebook</a>\n",
        "  </td>\n",
        "</table>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-0tqX8qkXZEj"
      },
      "source": [
        "This tutorial provides an example of loading data from NumPy arrays into a `tf.data.Dataset`.\n",
        "\n",
        "This example loads the MNIST dataset from a `.npz` file. However, the source of the NumPy arrays is not important.\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-Ze5IBx9clLB"
      },
      "source": [
        "## Setup"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "k6J3JzK5NxQ6"
      },
      "outputs": [],
      "source": [
        " \n",
        "import numpy as np\n",
        "import tensorflow as tf"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "G0yWiN8-cpDb"
      },
      "source": [
        "### Load from `.npz` file"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "GLHNrFM6RWoM"
      },
      "outputs": [],
      "source": [
        "DATA_URL = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz'\n",
        "\n",
        "path = tf.keras.utils.get_file('mnist.npz', DATA_URL)\n",
        "with np.load(path) as data:\n",
        "  train_examples = data['x_train']\n",
        "  train_labels = data['y_train']\n",
        "  test_examples = data['x_test']\n",
        "  test_labels = data['y_test']"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "cCeCkvrDgCMM"
      },
      "source": [
        "## Load NumPy arrays with `tf.data.Dataset`"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "tslB0tJPgB-2"
      },
      "source": [
        "Assuming you have an array of examples and a corresponding array of labels, pass the two arrays as a tuple into `tf.data.Dataset.from_tensor_slices` to create a `tf.data.Dataset`."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "QN_8wwc5R7Qm"
      },
      "outputs": [],
      "source": [
        "train_dataset = tf.data.Dataset.from_tensor_slices((train_examples, train_labels))\n",
        "test_dataset = tf.data.Dataset.from_tensor_slices((test_examples, test_labels))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "6Rco85bbkDfN"
      },
      "source": [
        "## Use the datasets"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0dvl1uUukc4K"
      },
      "source": [
        "### Shuffle and batch the datasets"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "GTXdRMPcSXZj"
      },
      "outputs": [],
      "source": [
        "BATCH_SIZE = 64\n",
        "SHUFFLE_BUFFER_SIZE = 100\n",
        "\n",
        "train_dataset = train_dataset.shuffle(SHUFFLE_BUFFER_SIZE).batch(BATCH_SIZE)\n",
        "test_dataset = test_dataset.batch(BATCH_SIZE)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "w69Jl8k6lilg"
      },
      "source": [
        "### Build and train a model"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Uhxr8py4DkDN"
      },
      "outputs": [],
      "source": [
        "model = tf.keras.Sequential([\n",
        "    tf.keras.layers.Flatten(input_shape=(28, 28)),\n",
        "    tf.keras.layers.Dense(128, activation='relu'),\n",
        "    tf.keras.layers.Dense(10)\n",
        "])\n",
        "\n",
        "model.compile(optimizer=tf.keras.optimizers.RMSprop(),\n",
        "              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
        "              metrics=['sparse_categorical_accuracy'])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "XLDzlPGgOHBx"
      },
      "outputs": [],
      "source": [
        "model.fit(train_dataset, epochs=10)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "2q82yN8mmKIE"
      },
      "outputs": [],
      "source": [
        "model.evaluate(test_dataset)"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "collapsed_sections": [],
      "name": "numpy.ipynb",
      "toc_visible": true
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}