copy edits and matrix shape for char rnn

Author: cezannec

cycle-gan/CycleGAN_Exercise.ipynb

@@ -233,7 +233,7 @@
     "def scale(x, feature_range=(-1, 1)):\n",
     "    ''' Scale takes in an image x and returns that image, scaled\n",
     "       with a feature_range of pixel values from -1 to 1. \n",
-    "       This function assumes that the input x is already scaled from 0-255.'''\n",
+    "       This function assumes that the input x is already scaled from 0-1.'''\n",
     "    \n",
     "    # scale from 0-1 to feature_range\n",
     "    min, max = feature_range\n",
@@ -684,7 +684,7 @@
     "    \n",
     "\n",
     "def fake_mse_loss(D_out):\n",
-    "    # how close is the produced output from being \"false\"?\n",
+    "    # how close is the produced output from being \"fake\"?\n",
     "    \n",
     "\n",
     "def cycle_consistency_loss(real_im, reconstructed_im, lambda_weight):\n",

cycle-gan/CycleGAN_Solution.ipynb

@@ -263,7 +263,7 @@
     "def scale(x, feature_range=(-1, 1)):\n",
     "    ''' Scale takes in an image x and returns that image, scaled\n",
     "       with a feature_range of pixel values from -1 to 1. \n",
-    "       This function assumes that the input x is already scaled from 0-255.'''\n",
+    "       This function assumes that the input x is already scaled from 0-1.'''\n",
     "    \n",
     "    # scale from 0-1 to feature_range\n",
     "    min, max = feature_range\n",
@@ -1003,7 +1003,7 @@
     "    return torch.mean((D_out-1)**2)\n",
     "\n",
     "def fake_mse_loss(D_out):\n",
-    "    # how close is the produced output from being \"false\"?\n",
+    "    # how close is the produced output from being \"fake\"?\n",
     "    return torch.mean(D_out**2)\n",
     "\n",
     "def cycle_consistency_loss(real_im, reconstructed_im, lambda_weight):\n",

project-tv-script-generation/dlnd_tv_script_generation.ipynb

@@ -165,7 +165,7 @@
    "source": [
     "## Pre-process all the data and save it\n",
     "\n",
-    "Running the code cell below will pre-process all the data and save it to file. You're encouraged to lok at the code for `preprocess_and_save_data` in the `helpers.py` file to see what it's doing in detail, but you do not need to change this code."
+    "Running the code cell below will pre-process all the data and save it to file. You're encouraged to look at the code for `preprocess_and_save_data` in the `helpers.py` file to see what it's doing in detail, but you do not need to change this code."
    ]
   },
   {
@@ -345,7 +345,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# test dataloader\n",
@@ -902,14 +904,16 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python [default]",
    "language": "python",
    "name": "python3"
   },
@@ -923,7 +927,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.3"
+   "version": "3.6.4"
   },
   "widgets": {
    "state": {},

recurrent-neural-networks/char-rnn/Character_Level_RNN_Exercise.ipynb

@@ -142,7 +142,7 @@
     "def one_hot_encode(arr, n_labels):\n",
     "    \n",
     "    # Initialize the the encoded array\n",
-    "    one_hot = np.zeros((np.multiply(*arr.shape), n_labels), dtype=np.float32)\n",
+    "    one_hot = np.zeros((arr.size, n_labels), dtype=np.float32)\n",
     "    \n",
     "    # Fill the appropriate elements with ones\n",
     "    one_hot[np.arange(one_hot.shape[0]), arr.flatten()] = 1.\n",

recurrent-neural-networks/char-rnn/Character_Level_RNN_Solution.ipynb

@@ -165,7 +165,7 @@
     "def one_hot_encode(arr, n_labels):\n",
     "    \n",
     "    # Initialize the the encoded array\n",
-    "    one_hot = np.zeros((np.multiply(*arr.shape), n_labels), dtype=np.float32)\n",
+    "    one_hot = np.zeros((arr.size, n_labels), dtype=np.float32)\n",
     "    \n",
     "    # Fill the appropriate elements with ones\n",
     "    one_hot[np.arange(one_hot.shape[0]), arr.flatten()] = 1.\n",