iamaziz/tf_practice_1_mini_linear_nn.ipynb

## tf_practice_1_mini_linear_nn.ipynb
{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "tf_practice_1_mini_linear_nn.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyM1vSZh39AO9KWD0E0jJf5/",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/iamaziz/d3fe74c008edd88ed9cd225fe2b8eb3d/tf_practice_1_mini_linear_nn.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "HMFPui2BnX_0"
      },
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow import keras\n",
        "import numpy as np"
      ],
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8w7X5occojiP",
        "outputId": "7cebd6fb-cf9b-461c-a840-407ff3ee4eaf",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "# -- get the labeled data (relation: y = 2x - 1)\n",
        "x = np.array([-1,  0, 1,  2, 3, 4], dtype=float)\n",
        "y = np.array([-3, -1, 1,  3, 5, 7], dtype=float)\n",
        "\n",
        "# -- build the model\n",
        "layers = keras.layers.Dense(units=1, input_shape=[1])\n",
        "model = keras.models.Sequential(layers)\n",
        "model.compile(optimizer='sgd', loss=keras.losses.mean_squared_error)\n",
        "\n",
        "# -- train the model\n",
        "\n",
        "model.fit(x, y, epochs=300, verbose=0)\n",
        "\n",
        "# -- check the accuracy\n",
        "print(model.history.history['loss'][-1])"
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "0.0031866703648120165\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "kBC3Q2QsxNVx",
        "outputId": "517109f2-a8de-4142-d2c0-262c993e3c2b",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "# -- use the model to predict new data\n",
        "new_data = [9, 10] # correct: 17, 19\n",
        "model.predict(new_data).tolist()"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[[16.859172821044922], [18.835302352905273]]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "wqXnRGDvzyVJ",
        "outputId": "899443b5-0ec3-4f4c-80f3-219677499613",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "model.summary()"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Model: \"sequential\"\n",
            "_________________________________________________________________\n",
            "Layer (type)                 Output Shape              Param #   \n",
            "=================================================================\n",
            "dense (Dense)                (None, 1)                 2         \n",
            "=================================================================\n",
            "Total params: 2\n",
            "Trainable params: 2\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "uQ62odrouQif",
        "outputId": "f280f6fd-2a8c-4a57-ba86-84476d7367ba",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "# -- inspect the learned params\n",
        "params = model.get_weights()\n",
        "params # almost: 2x - 1"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[array([[1.9761295]], dtype=float32), array([-0.9259935], dtype=float32)]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "xodoXX-0NOUQ",
        "outputId": "d4007ef1-5e53-49dd-c425-5eb16446257a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 174
        }
      },
      "source": [
        "keras.utils.plot_model(model)"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<IPython.core.display.Image object>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 7
        }
      ]
    }
  ]
}
	{
	"nbformat": 4,
	"nbformat_minor": 0,
	"metadata": {
	"colab": {
	"name": "tf_practice_1_mini_linear_nn.ipynb",
	"provenance": [],
	"collapsed_sections": [],
	"authorship_tag": "ABX9TyM1vSZh39AO9KWD0E0jJf5/",
	"include_colab_link": true
	},
	"kernelspec": {
	"name": "python3",
	"display_name": "Python 3"
	}
	},
	"cells": [
	{
	"cell_type": "markdown",
	"metadata": {
	"id": "view-in-github",
	"colab_type": "text"
	},
	"source": [
	"<a href=\"https://colab.research.google.com/gist/iamaziz/d3fe74c008edd88ed9cd225fe2b8eb3d/tf_practice_1_mini_linear_nn.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
	]
	},
	{
	"cell_type": "code",
	"metadata": {
	"id": "HMFPui2BnX_0"
	},
	"source": [
	"import tensorflow as tf\n",
	"from tensorflow import keras\n",
	"import numpy as np"
	],
	"execution_count": 1,
	"outputs": []
	},
	{
	"cell_type": "code",
	"metadata": {
	"id": "8w7X5occojiP",
	"outputId": "7cebd6fb-cf9b-461c-a840-407ff3ee4eaf",
	"colab": {
	"base_uri": "https://localhost:8080/"
	}
	},
	"source": [
	"# -- get the labeled data (relation: y = 2x - 1)\n",
	"x = np.array([-1, 0, 1, 2, 3, 4], dtype=float)\n",
	"y = np.array([-3, -1, 1, 3, 5, 7], dtype=float)\n",
	"\n",
	"# -- build the model\n",
	"layers = keras.layers.Dense(units=1, input_shape=[1])\n",
	"model = keras.models.Sequential(layers)\n",
	"model.compile(optimizer='sgd', loss=keras.losses.mean_squared_error)\n",
	"\n",
	"# -- train the model\n",
	"\n",
	"model.fit(x, y, epochs=300, verbose=0)\n",
	"\n",
	"# -- check the accuracy\n",
	"print(model.history.history['loss'][-1])"
	],
	"execution_count": 2,
	"outputs": [
	{
	"output_type": "stream",
	"text": [
	"0.0031866703648120165\n"
	],
	"name": "stdout"
	}
	]
	},
	{
	"cell_type": "code",
	"metadata": {
	"id": "kBC3Q2QsxNVx",
	"outputId": "517109f2-a8de-4142-d2c0-262c993e3c2b",
	"colab": {
	"base_uri": "https://localhost:8080/"
	}
	},
	"source": [
	"# -- use the model to predict new data\n",
	"new_data = [9, 10] # correct: 17, 19\n",
	"model.predict(new_data).tolist()"
	],
	"execution_count": 4,
	"outputs": [
	{
	"output_type": "execute_result",
	"data": {
	"text/plain": [
	"[[16.859172821044922], [18.835302352905273]]"
	]
	},
	"metadata": {
	"tags": []
	},
	"execution_count": 4
	}
	]
	},
	{
	"cell_type": "code",
	"metadata": {
	"id": "wqXnRGDvzyVJ",
	"outputId": "899443b5-0ec3-4f4c-80f3-219677499613",
	"colab": {
	"base_uri": "https://localhost:8080/"
	}
	},
	"source": [
	"model.summary()"
	],
	"execution_count": 5,
	"outputs": [
	{
	"output_type": "stream",
	"text": [
	"Model: \"sequential\"\n",
	"_________________________________________________________________\n",
	"Layer (type) Output Shape Param # \n",
	"=================================================================\n",
	"dense (Dense) (None, 1) 2 \n",
	"=================================================================\n",
	"Total params: 2\n",
	"Trainable params: 2\n",
	"Non-trainable params: 0\n",
	"_________________________________________________________________\n"
	],
	"name": "stdout"
	}
	]
	},
	{
	"cell_type": "code",
	"metadata": {
	"id": "uQ62odrouQif",
	"outputId": "f280f6fd-2a8c-4a57-ba86-84476d7367ba",
	"colab": {
	"base_uri": "https://localhost:8080/"
	}
	},
	"source": [
	"# -- inspect the learned params\n",
	"params = model.get_weights()\n",
	"params # almost: 2x - 1"
	],
	"execution_count": 6,
	"outputs": [
	{
	"output_type": "execute_result",
	"data": {
	"text/plain": [
	"[array([[1.9761295]], dtype=float32), array([-0.9259935], dtype=float32)]"
	]
	},
	"metadata": {
	"tags": []
	},
	"execution_count": 6
	}
	]
	},
	{
	"cell_type": "code",
	"metadata": {
	"id": "xodoXX-0NOUQ",
	"outputId": "d4007ef1-5e53-49dd-c425-5eb16446257a",
	"colab": {
	"base_uri": "https://localhost:8080/",
	"height": 174
	}
	},
	"source": [
	"keras.utils.plot_model(model)"
	],
	"execution_count": 7,
	"outputs": [
	{
	"output_type": "execute_result",
	"data": {
	"image/png": "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\n",
	"text/plain": [
	"<IPython.core.display.Image object>"
	]
	},
	"metadata": {
	"tags": []
	},
	"execution_count": 7
	}
	]
	}
	]
	}