Fix print formatting.

More general exclusion of files (h/t @shreyasva)
Typo (h/t @seanpavlov)
Change: 113597422

1 files changed, 62 insertions, 59 deletions

diff --git a/tensorflow/examples/udacity/1_notmnist.ipynb b/tensorflow/examples/udacity/1_notmnist.ipynb
index 661ea4df92..d3f72c4fe8 100644
--- a/tensorflow/examples/udacity/1_notmnist.ipynb
+++ b/tensorflow/examples/udacity/1_notmnist.ipynb
@@ -45,6 +45,7 @@
       "source": [
         "# These are all the modules we'll be using later. Make sure you can import them\n",
         "# before proceeding further.\n",
+        "from __future__ import print_function\n",
         "import matplotlib.pyplot as plt\n",
         "import numpy as np\n",
         "import os\n",
@@ -191,7 +192,8 @@
         "  tar.extractall()\n",
         "  tar.close()\n",
         "  data_folders = [\n",
-        "    os.path.join(root, d) for d in sorted(os.listdir(root)) if d != '.DS_Store']\n",
+        "    os.path.join(root, d) for d in sorted(os.listdir(root))\n",
+        "    if os.path.isdir(os.path.join(root, d))]\n",
         "  if len(data_folders) != num_classes:\n",
         "    raise Exception(\n",
         "      'Expected %d folders, one per class. Found %d instead.' % (\n",
@@ -284,33 +286,34 @@
         "pixel_depth = 255.0  # Number of levels per pixel.\n",
         "\n",
         "def load_letter(folder, min_num_images):\n",
-        "    image_files = os.listdir(folder)\n",
-        "    dataset = np.ndarray(shape=(len(image_files), image_size, image_size),\n",
+        "  \"\"\"Load the data for a single letter label.\"\"\"\n",
+        "  image_files = os.listdir(folder)\n",
+        "  dataset = np.ndarray(shape=(len(image_files), image_size, image_size),\n",
         "                         dtype=np.float32)\n",
-        "    image_index = 0\n",
-        "    print folder\n",
-        "    for image in os.listdir(folder):\n",
-        "      image_file = os.path.join(folder, image)\n",
-        "      try:\n",
-        "        image_data = (ndimage.imread(image_file).astype(float) - \n",
-        "                      pixel_depth / 2) / pixel_depth\n",
-        "        if image_data.shape != (image_size, image_size):\n",
-        "          raise Exception('Unexpected image shape: %s' % str(image_data.shape))\n",
-        "        dataset[image_index, :, :] = image_data\n",
-        "        image_index += 1\n",
-        "      except IOError as e:\n",
-        "        print('Could not read:', image_file, ':', e, '- it\\'s ok, skipping.')\n",
+        "  image_index = 0\n",
+        "  print(folder)\n",
+        "  for image in os.listdir(folder):\n",
+        "    image_file = os.path.join(folder, image)\n",
+        "    try:\n",
+        "      image_data = (ndimage.imread(image_file).astype(float) - \n",
+        "                    pixel_depth / 2) / pixel_depth\n",
+        "      if image_data.shape != (image_size, image_size):\n",
+        "        raise Exception('Unexpected image shape: %s' % str(image_data.shape))\n",
+        "      dataset[image_index, :, :] = image_data\n",
+        "      image_index += 1\n",
+        "    except IOError as e:\n",
+        "      print('Could not read:', image_file, ':', e, '- it\\'s ok, skipping.')\n",
         "    \n",
-        "    num_images = image_index\n",
-        "    dataset = dataset[0:num_images, :, :]\n",
-        "    if num_images < min_num_images:\n",
-    "        raise Exception('Many fewer images than expected: %d < %d' % \n",
-    "                        (num_images, min_num_images))\n",
+        "  num_images = image_index\n",
+        "  dataset = dataset[0:num_images, :, :]\n",
+        "  if num_images < min_num_images:\n",
+        "    raise Exception('Many fewer images than expected: %d < %d' %\n",
+        "                    (num_images, min_num_images))\n",
         "    \n",
-        "    print('Full dataset tensor:', dataset.shape)\n",
-        "    print('Mean:', np.mean(dataset))\n",
-        "    print('Standard deviation:', np.std(dataset))\n",
-        "    return dataset\n",
+        "  print('Full dataset tensor:', dataset.shape)\n",
+        "  print('Mean:', np.mean(dataset))\n",
+        "  print('Standard deviation:', np.std(dataset))\n",
+        "  return dataset\n",
         "        \n",
         "def load(data_folders, min_num_images_per_class):\n",
         "  dataset_names = []\n",
@@ -506,44 +509,44 @@
       },
       "source": [
         "def make_arrays(nb_rows, img_size):\n",
-        "    if nb_rows:\n",
-        "        dataset = np.ndarray((nb_rows, img_size, img_size), dtype=np.float32)\n",
-        "        labels = np.ndarray(nb_rows, dtype=np.int32)\n",
-        "    else:\n",
-        "        dataset, labels = None, None\n",
-        "    return dataset, labels\n",
+        "  if nb_rows:\n",
+        "    dataset = np.ndarray((nb_rows, img_size, img_size), dtype=np.float32)\n",
+        "    labels = np.ndarray(nb_rows, dtype=np.int32)\n",
+        "  else:\n",
+        "    dataset, labels = None, None\n",
+        "  return dataset, labels\n",
         "\n",
         "def merge_datasets(pickle_files, train_size, valid_size=0):\n",
-        "    num_classes = len(pickle_files)\n",
-        "    valid_dataset, valid_labels = make_arrays(valid_size, image_size)\n",
-        "    train_dataset, train_labels = make_arrays(train_size, image_size)\n",
-        "    vsize_per_class = valid_size // num_classes\n",
-        "    tsize_per_class = train_size // num_classes\n",
+        "  num_classes = len(pickle_files)\n",
+        "  valid_dataset, valid_labels = make_arrays(valid_size, image_size)\n",
+        "  train_dataset, train_labels = make_arrays(train_size, image_size)\n",
+        "  vsize_per_class = valid_size // num_classes\n",
+        "  tsize_per_class = train_size // num_classes\n",
         "    \n",
-        "    start_v, start_t = 0, 0\n",
-        "    end_v, end_t = vsize_per_class, tsize_per_class\n",
-        "    end_l = vsize_per_class+tsize_per_class\n",
-        "    for label, pickle_file in enumerate(pickle_files):       \n",
-        "        try:\n",
-        "            with open(pickle_file, 'rb') as f:\n",
-        "                letter_set = pickle.load(f)\n",
-        "                if valid_dataset is not None:\n",
-        "                    valid_letter = letter_set[:vsize_per_class, :, :]\n",
-        "                    valid_dataset[start_v:end_v, :, :] = valid_letter\n",
-        "                    valid_labels[start_v:end_v] = label\n",
-        "                    start_v += vsize_per_class\n",
-        "                    end_v += vsize_per_class\n",
+        "  start_v, start_t = 0, 0\n",
+        "  end_v, end_t = vsize_per_class, tsize_per_class\n",
+        "  end_l = vsize_per_class+tsize_per_class\n",
+        "  for label, pickle_file in enumerate(pickle_files):       \n",
+        "    try:\n",
+        "      with open(pickle_file, 'rb') as f:\n",
+        "        letter_set = pickle.load(f)\n",
+        "        if valid_dataset is not None:\n",
+        "          valid_letter = letter_set[:vsize_per_class, :, :]\n",
+        "          valid_dataset[start_v:end_v, :, :] = valid_letter\n",
+        "          valid_labels[start_v:end_v] = label\n",
+        "          start_v += vsize_per_class\n",
+        "          end_v += vsize_per_class\n",
         "                    \n",
-        "                train_letter = letter_set[vsize_per_class:end_l, :, :]\n",
-        "                train_dataset[start_t:end_t, :, :] = train_letter\n",
-        "                train_labels[start_t:end_t] = label\n",
-        "                start_t += tsize_per_class\n",
-        "                end_t += tsize_per_class\n",
-        "        except Exception as e:\n",
-        "          print('Unable to process data from', pickle_file, ':', e)\n",
-        "          raise\n",
+        "        train_letter = letter_set[vsize_per_class:end_l, :, :]\n",
+        "        train_dataset[start_t:end_t, :, :] = train_letter\n",
+        "        train_labels[start_t:end_t] = label\n",
+        "        start_t += tsize_per_class\n",
+        "        end_t += tsize_per_class\n",
+        "    except Exception as e:\n",
+        "      print('Unable to process data from', pickle_file, ':', e)\n",
+        "      raise\n",
         "    \n",
-        "    return valid_dataset, valid_labels, train_dataset, train_labels\n",
+        "  return valid_dataset, valid_labels, train_dataset, train_labels\n",
         "            \n",
         "            \n",
         "train_size = 200000\n",
@@ -757,4 +760,4 @@
       ]
     }
   ]
-}
+}
\ No newline at end of file