load MNIST data as two-dimensional matrix

Author: dsilver829

LeNet-Lab-Solution.ipynb

@@ -30,7 +30,7 @@
    "source": [
     "from tensorflow.examples.tutorials.mnist import input_data\n",
     "\n",
-    "mnist = input_data.read_data_sets(\"MNIST_data/\")\n",
+    "mnist = input_data.read_data_sets(\"MNIST_data/\", reshape=False)\n",
     "X_train, y_train           = mnist.train.images, mnist.train.labels\n",
     "X_validation, y_validation = mnist.validation.images, mnist.validation.labels\n",
     "X_test, y_test             = mnist.test.images, mnist.test.labels\n",
@@ -51,14 +51,11 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The MNIST data that TensorFlow pre-loads comes as an \"unrolled\" vector of 784 pixels.\n",
+    "The MNIST data that TensorFlow pre-loads comes as 28x28x1 images.\n",
     "\n",
-    "However, the LeNet architecture only accepts 32x32 images.\n",
+    "However, the LeNet architecture only accepts 32x32xC images, where C is the number of color channels.\n",
     "\n",
-    "In order to reformat the MNIST data into a shape that LeNet will accept, we proceed in two steps:\n",
-    "\n",
-    "1. Reshape the 784 pixel vector into a 28x28 matrix (28x28 = 784).\n",
-    "2. Pad the data with two rows of zeros on the top and bottom, and two columns of zeros on the left and right (28+2+2 = 32).\n",
+    "In order to reformat the MNIST data into a shape that LeNet will accept, we pad the data with two rows of zeros on the top and bottom, and two columns of zeros on the left and right (28+2+2 = 32).\n",
     "\n",
     "You do not need to modify this section."
    ]
@@ -73,11 +70,6 @@
    "source": [
     "import numpy as np\n",
     "\n",
-    "# Reshape MNIST image from vector to matrix\n",
-    "X_train      = np.reshape(X_train, (-1, 28, 28, 1))\n",
-    "X_validation = np.reshape(X_validation, (-1, 28, 28, 1))\n",
-    "X_test       = np.reshape(X_test, (-1, 28, 28, 1))\n",
-    "\n",
     "# Pad images with 0s\n",
     "X_train      = np.pad(X_train, ((0,0),(2,2),(2,2),(0,0)), 'constant')\n",
     "X_validation = np.pad(X_validation, ((0,0),(2,2),(2,2),(0,0)), 'constant')\n",

LeNet-Lab.ipynb

@@ -30,7 +30,7 @@
    "source": [
     "from tensorflow.examples.tutorials.mnist import input_data\n",
     "\n",
-    "mnist = input_data.read_data_sets(\"MNIST_data/\")\n",
+    "mnist = input_data.read_data_sets(\"MNIST_data/\", reshape=False)\n",
     "X_train, y_train           = mnist.train.images, mnist.train.labels\n",
     "X_validation, y_validation = mnist.validation.images, mnist.validation.labels\n",
     "X_test, y_test             = mnist.test.images, mnist.test.labels\n",
@@ -51,14 +51,11 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The MNIST data that TensorFlow pre-loads comes as an \"unrolled\" vector of 784 pixels.\n",
+    "The MNIST data that TensorFlow pre-loads comes as 28x28x1 images.\n",
     "\n",
-    "However, the LeNet architecture only accepts 32x32 images.\n",
+    "However, the LeNet architecture only accepts 32x32xC images, where C is the number of color channels.\n",
     "\n",
-    "In order to reformat the MNIST data into a shape that LeNet will accept, we proceed in two steps:\n",
-    "\n",
-    "1. Reshape the 784 pixel vector into a 28x28 matrix (28x28 = 784).\n",
-    "2. Pad the data with two rows of zeros on the top and bottom, and two columns of zeros on the left and right (28+2+2 = 32).\n",
+    "In order to reformat the MNIST data into a shape that LeNet will accept, we pad the data with two rows of zeros on the top and bottom, and two columns of zeros on the left and right (28+2+2 = 32).\n",
     "\n",
     "You do not need to modify this section."
    ]
@@ -73,11 +70,6 @@
    "source": [
     "import numpy as np\n",
     "\n",
-    "# Reshape MNIST image from vector to matrix\n",
-    "X_train      = np.reshape(X_train, (-1, 28, 28, 1))\n",
-    "X_validation = np.reshape(X_validation, (-1, 28, 28, 1))\n",
-    "X_test       = np.reshape(X_test, (-1, 28, 28, 1))\n",
-    "\n",
     "# Pad images with 0s\n",
     "X_train      = np.pad(X_train, ((0,0),(2,2),(2,2),(0,0)), 'constant')\n",
     "X_validation = np.pad(X_validation, ((0,0),(2,2),(2,2),(0,0)), 'constant')\n",
@@ -328,7 +320,7 @@
     "    sess = tf.get_default_session()\n",
     "    for offset in range(0, num_examples, BATCH_SIZE):\n",
     "        batch_x, batch_y = X_data[offset:offset+BATCH_SIZE], y_data[offset:offset+BATCH_SIZE]\n",
-    "        accuracy =  sess.run(accuracy_operation, feed_dict={x: batch_x, y: batch_y})\n",
+    "        accuracy = sess.run(accuracy_operation, feed_dict={x: batch_x, y: batch_y})\n",
     "        total_accuracy += (accuracy * len(batch_x))\n",
     "    return total_accuracy / num_examples"
    ]
@@ -368,7 +360,7 @@
     "        for offset in range(0, num_examples, BATCH_SIZE):\n",
     "            end = offset + BATCH_SIZE\n",
     "            batch_x, batch_y = X_train[offset:end], y_train[offset:end]\n",
-    "            loss = sess.run(training_operation, feed_dict={x: batch_x, y: batch_y})\n",
+    "            sess.run(training_operation, feed_dict={x: batch_x, y: batch_y})\n",
     "            \n",
     "        validation_accuracy = evaluate(X_validation, y_validation)\n",
     "        print(\"EPOCH {} ...\".format(i+1))\n",