add learning rate hyperparameter

Author: dsilver829

LeNet-Lab-Solution.ipynb

@@ -22,11 +22,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Extracting MNIST_data/train-images-idx3-ubyte.gz\n",
+      "Extracting MNIST_data/train-labels-idx1-ubyte.gz\n",
+      "Extracting MNIST_data/t10k-images-idx3-ubyte.gz\n",
+      "Extracting MNIST_data/t10k-labels-idx1-ubyte.gz\n",
+      "\n",
+      "Image Shape: (784,)\n",
+      "\n",
+      "Training Set:   55000 samples\n",
+      "Validation Set: 5000 samples\n",
+      "Test Set:       10000 samples\n"
+     ]
+    }
+   ],
    "source": [
     "from tensorflow.examples.tutorials.mnist import input_data\n",
     "\n",
@@ -65,11 +82,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Updated Image Shape: (32, 32, 1)\n"
+     ]
+    }
+   ],
    "source": [
     "import numpy as np\n",
     "\n",
@@ -99,11 +124,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "8\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAH0AAAB6CAYAAACShVydAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAElFTkSuQmCC\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f62f51cc358>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "import random\n",
     "import numpy as np\n",
@@ -131,7 +174,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {
     "collapsed": false
    },
@@ -154,7 +197,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {
     "collapsed": true
    },
@@ -208,7 +251,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {
     "collapsed": true
    },
@@ -285,7 +328,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {
     "collapsed": false
    },
@@ -308,16 +351,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {
     "collapsed": false
    },
    "outputs": [],
    "source": [
+    "rate = 0.01\n",
+    "\n",
     "logits = LeNet(x)\n",
     "cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits, one_hot_y)\n",
     "loss_operation = tf.reduce_mean(cross_entropy)\n",
-    "optimizer = tf.train.AdamOptimizer()\n",
+    "optimizer = tf.train.AdamOptimizer(learning_rate = rate)\n",
     "training_operation = optimizer.minimize(loss_operation)"
    ]
   },
@@ -333,7 +378,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {
     "collapsed": true
    },
@@ -372,11 +417,61 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Training...\n",
+      "\n",
+      "EPOCH 1 ...\n",
+      "Validation Loss     = 0.068\n",
+      "Validation Accuracy = 0.982\n",
+      "\n",
+      "EPOCH 2 ...\n",
+      "Validation Loss     = 0.072\n",
+      "Validation Accuracy = 0.982\n",
+      "\n",
+      "EPOCH 3 ...\n",
+      "Validation Loss     = 0.058\n",
+      "Validation Accuracy = 0.986\n",
+      "\n",
+      "EPOCH 4 ...\n",
+      "Validation Loss     = 0.062\n",
+      "Validation Accuracy = 0.987\n",
+      "\n",
+      "EPOCH 5 ...\n",
+      "Validation Loss     = 0.061\n",
+      "Validation Accuracy = 0.987\n",
+      "\n",
+      "EPOCH 6 ...\n",
+      "Validation Loss     = 0.080\n",
+      "Validation Accuracy = 0.981\n",
+      "\n",
+      "EPOCH 7 ...\n",
+      "Validation Loss     = 0.080\n",
+      "Validation Accuracy = 0.984\n",
+      "\n",
+      "EPOCH 8 ...\n",
+      "Validation Loss     = 0.074\n",
+      "Validation Accuracy = 0.981\n",
+      "\n",
+      "EPOCH 9 ...\n",
+      "Validation Loss     = 0.067\n",
+      "Validation Accuracy = 0.984\n",
+      "\n",
+      "EPOCH 10 ...\n",
+      "Validation Loss     = 0.105\n",
+      "Validation Accuracy = 0.978\n",
+      "\n",
+      "Model saved\n"
+     ]
+    }
+   ],
    "source": [
     "with tf.Session() as sess:\n",
     "    sess.run(tf.global_variables_initializer())\n",
@@ -421,11 +516,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Test Loss     = 0.091\n",
+      "Test Accuracy = 0.980\n"
+     ]
+    }
+   ],
    "source": [
     "with tf.Session() as sess:\n",
     "    loader = tf.train.import_meta_graph('lenet.meta')\n",

LeNet-Lab.ipynb

@@ -292,10 +292,12 @@
    },
    "outputs": [],
    "source": [
+    "rate = 0.01\n",
+    "\n",
     "logits = LeNet(x)\n",
     "cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits, one_hot_y)\n",
     "loss_operation = tf.reduce_mean(cross_entropy)\n",
-    "optimizer = tf.train.AdamOptimizer()\n",
+    "optimizer = tf.train.AdamOptimizer(learning_rate = rate)\n",
     "training_operation = optimizer.minimize(loss_operation)"
    ]
   },