Update notebook 3

Author: rickwierenga

03_net.ipynb

@@ -1,86 +1,111 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Net"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
-    "import tensorflow as tf\n",
-    "import numpy as np\n",
-    "from tensorflow.examples.tutorials.mnist import input_data"
+    "import tensorflow as tf"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Populating the interactive namespace from numpy and matplotlib\n"
+     ]
+    }
+   ],
    "source": [
-    "def init_weights(shape):\n",
-    "    return tf.Variable(tf.random_normal(shape, stddev=0.01))\n",
-    "\n",
-    "def model(X, w_h, w_o):\n",
-    "    h = tf.nn.sigmoid(tf.matmul(X, w_h)) # this is a basic mlp, think 2 stacked logistic regressions\n",
-    "    return tf.matmul(h, w_o) # note that we dont take the softmax at the end because our cost fn does that for us\n",
-    "\n",
-    "mnist = input_data.read_data_sets(\"MNIST_data/\", one_hot=True)\n",
-    "trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels"
+    "%pylab inline"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 3,
+   "metadata": {},
    "outputs": [],
    "source": [
-    "X = tf.placeholder(\"float\", [None, 784])\n",
-    "Y = tf.placeholder(\"float\", [None, 10])\n",
-    "\n",
-    "w_h = init_weights([784, 625]) # create symbolic variables\n",
-    "w_o = init_weights([625, 10])\n",
-    "\n",
-    "py_x = model(X, w_h, w_o)\n",
-    "\n",
-    "cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y)) # compute costs\n",
-    "train_op = tf.train.GradientDescentOptimizer(0.05).minimize(cost) # construct an optimizer\n",
-    "predict_op = tf.argmax(py_x, 1)"
+    "(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()\n",
+    "x_train = x_train / 255\n",
+    "x_test = x_test / 255"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 4,
+   "metadata": {},
    "outputs": [],
    "source": [
-    "# Launch the graph in a session\n",
-    "with tf.Session() as sess:\n",
-    "    # you need to initialize all variables\n",
-    "    tf.global_variables_initializer().run()\n",
-    "\n",
-    "    for i in range(100):\n",
-    "        for start, end in zip(range(0, len(trX), 128), range(128, len(trX)+1, 128)):\n",
-    "            sess.run(train_op, feed_dict={X: trX[start:end], Y: trY[start:end]})\n",
-    "        print(i, np.mean(np.argmax(teY, axis=1) ==\n",
-    "                         sess.run(predict_op, feed_dict={X: teX})))"
+    "model = tf.keras.models.Sequential([\n",
+    "    tf.keras.layers.Flatten(),\n",
+    "    tf.keras.layers.Dense(28*28, activation='sigmoid'),\n",
+    "    tf.keras.layers.Dense(10, activation='softmax')\n",
+    "])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 5,
+   "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "model.compile(\n",
+    "    optimizer=tf.keras.optimizers.SGD(lr=0.01),\n",
+    "    loss=tf.keras.losses.sparse_categorical_crossentropy,\n",
+    "    metrics=['accuracy']\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Train on 60000 samples\n",
+      "Epoch 1/10\n",
+      "60000/60000 [==============================] - 5s 76us/sample - loss: 1.2824 - accuracy: 0.7118\n",
+      "Epoch 2/10\n",
+      "60000/60000 [==============================] - 5s 81us/sample - loss: 0.6083 - accuracy: 0.8557\n",
+      "Epoch 3/10\n",
+      "60000/60000 [==============================] - 5s 81us/sample - loss: 0.4741 - accuracy: 0.8762\n",
+      "Epoch 4/10\n",
+      "60000/60000 [==============================] - 5s 81us/sample - loss: 0.4186 - accuracy: 0.8864\n",
+      "Epoch 5/10\n",
+      "60000/60000 [==============================] - 5s 81us/sample - loss: 0.3876 - accuracy: 0.8923\n",
+      "Epoch 6/10\n",
+      "60000/60000 [==============================] - 5s 82us/sample - loss: 0.3678 - accuracy: 0.8968\n",
+      "Epoch 7/10\n",
+      "60000/60000 [==============================] - 5s 82us/sample - loss: 0.3537 - accuracy: 0.8989\n",
+      "Epoch 8/10\n",
+      "60000/60000 [==============================] - 5s 82us/sample - loss: 0.3430 - accuracy: 0.9012\n",
+      "Epoch 9/10\n",
+      "60000/60000 [==============================] - 5s 85us/sample - loss: 0.3345 - accuracy: 0.9047\n",
+      "Epoch 10/10\n",
+      "60000/60000 [==============================] - 5s 81us/sample - loss: 0.3274 - accuracy: 0.9058\n"
+     ]
+    }
+   ],
+   "source": [
+    "history = model.fit(x_train, y_train, epochs=10)"
+   ]
   }
  ],
  "metadata": {
@@ -92,16 +117,16 @@
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.13"
+   "pygments_lexer": "ipython3",
+   "version": "3.7.1"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 0
+ "nbformat_minor": 1
 }

README.md

@@ -6,7 +6,7 @@ Introduction to deep learning based on Google's TensorFlow framework.  A fork of
 * [Simple Multiplication](00_multiply.ipynb)
 * [Linear Regression](01_linear_regression.ipynb)
 * [Logistic Regression](02_logistic_regression.ipynb)
-* [Feedforward Neural Network (Multilayer Perceptron)](03_net.ipynb) (not yet updated)
+* [Feedforward Neural Network (Multilayer Perceptron)](03_net.ipynb)
 * [Deep Feedforward Neural Network (Multilayer Perceptron with 2 Hidden Layers O.o)](04_modern_net.ipynb) (not yet updated)
 * [Convolutional Neural Network](05_convolutional_net.ipynb) (not yet updated)
 * [Denoising Autoencoder](06_autoencoder.ipynb) (not yet updated)