TensorFlow - Basic Minimisation with Gradient Descent using placeholder data

TensorFlow - Basic Minimisation with Gradient Descent using placeholder data.ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "import numpy as np\nimport tensorflow as tf",
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": "/home/karl/anaconda2/envs/py36-test/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.\n  from ._conv import register_converters as _register_converters\n",
          "name": "stderr"
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "### Using Gradient Descent, find the value of w  when\n10*W**2 - 20*W + 100 = 0"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "coefficients = np.array([[10.0], [-20.0], [100.0]] )\nw = tf.Variable(0, dtype=tf.float32)\nx = tf.placeholder(tf.float32, [3,1])",
      "execution_count": 33,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "cost = x[0][0]*w**2 + x[1][0]*w+x[2][0]\ntrain = tf.train.GradientDescentOptimizer(0.01).minimize(cost)\ninit = tf.global_variables_initializer()\nsession = tf.Session()\nsession.run(init)\nprint(session.run(w))",
      "execution_count": 34,
      "outputs": [
        {
          "output_type": "stream",
          "text": "0.0\n",
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "### Perform 1 round of Gradient Descent"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "session.run(train, feed_dict={x:coefficients})\nprint(session.run(w))",
      "execution_count": 35,
      "outputs": [
        {
          "output_type": "stream",
          "text": "0.19999999\n",
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "### Perform 1000 round of Gradient Descent"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "for i in range(1_000):\n    session.run(train, feed_dict={x:coefficients})\nprint(session.run(w))",
      "execution_count": 36,
      "outputs": [
        {
          "output_type": "stream",
          "text": "0.9999999\n",
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "",
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "_draft": {
      "nbviewer_url": "https://gist.github.com/4b6c4b0abda338d6580e1aca6946c183"
    },
    "gist": {
      "id": "4b6c4b0abda338d6580e1aca6946c183",
      "data": {
        "description": "TensorFlow - Basic Minimisation with Gradient Descent using placeholder data",
        "public": true
      }
    },
    "kernelspec": {
      "name": "py36-test",
      "display_name": "py36-test",
      "language": "python"
    },
    "language_info": {
      "name": "python",
      "version": "3.6.4",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "toc": {
      "nav_menu": {},
      "number_sections": true,
      "sideBar": true,
      "skip_h1_title": false,
      "toc_cell": false,
      "toc_position": {},
      "toc_section_display": "block",
      "toc_window_display": false
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}