From 101d3fc8f45e682e2bf182b165ae0464f7487f68 Mon Sep 17 00:00:00 2001
From: Sebastian Raschka <mail@sebastianraschka.com>
Date: Tue, 5 Nov 2019 12:10:55 -0600
Subject: [PATCH] run part 2

---
 ch17/ch17_part2.ipynb | 360 ++++++++++++++++++++++++++----------------
 ch17/ch17_part2.py    | 246 +++++++++++++++--------------
 2 files changed, 353 insertions(+), 253 deletions(-)

diff --git a/ch17/ch17_part2.ipynb b/ch17/ch17_part2.ipynb
index 568e0204..24835dc0 100644
--- a/ch17/ch17_part2.ipynb
+++ b/ch17/ch17_part2.ipynb
@@ -27,23 +27,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "The watermark extension is already loaded. To reload it, use:\n",
-      "  %reload_ext watermark\n",
       "Sebastian Raschka & Vahid Mirjalili \n",
-      "last updated: 2019-11-04 \n",
+      "last updated: 2019-11-05 \n",
       "\n",
-      "numpy 1.17.3\n",
-      "scipy 1.3.1\n",
-      "matplotlib 3.1.1\n",
+      "numpy 1.17.2\n",
+      "scipy 1.2.1\n",
+      "matplotlib 3.1.0\n",
       "tensorflow 2.0.0\n",
-      "tensorflow_datasets 1.2.0\n"
+      "tensorflow_datasets 1.3.0\n"
      ]
     }
    ],
@@ -259,7 +257,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 10,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -275,13 +273,15 @@
      "output_type": "stream",
      "text": [
       "2.0.0\n",
-      "GPU Available: False\n",
-      "CPU:0\n"
+      "GPU Available: True\n",
+      "/device:GPU:0\n"
      ]
     }
    ],
    "source": [
     "import tensorflow as tf\n",
+    "\n",
+    "\n",
     "print(tf.__version__)\n",
     "\n",
     "print(\"GPU Available:\", tf.test.is_gpu_available())\n",
@@ -297,7 +297,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 11,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -309,7 +309,6 @@
    },
    "outputs": [],
    "source": [
-    "import tensorflow as tf\n",
     "import tensorflow_datasets as tfds\n",
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
@@ -318,7 +317,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 12,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -402,12 +401,12 @@
     "    \n",
     "    model.add(tf.keras.layers.Reshape((1,)))\n",
     "    \n",
-    "    return model\n"
+    "    return model"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 13,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -422,71 +421,71 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Model: \"sequential_6\"\n",
+      "Model: \"sequential\"\n",
       "_________________________________________________________________\n",
       "Layer (type)                 Output Shape              Param #   \n",
       "=================================================================\n",
-      "dense_3 (Dense)              (None, 6272)              125440    \n",
+      "dense (Dense)                (None, 6272)              125440    \n",
       "_________________________________________________________________\n",
-      "batch_normalization_21 (Batc (None, 6272)              25088     \n",
+      "batch_normalization (BatchNo (None, 6272)              25088     \n",
       "_________________________________________________________________\n",
-      "leaky_re_lu_21 (LeakyReLU)   (None, 6272)              0         \n",
+      "leaky_re_lu (LeakyReLU)      (None, 6272)              0         \n",
       "_________________________________________________________________\n",
-      "reshape_6 (Reshape)          (None, 7, 7, 128)         0         \n",
+      "reshape (Reshape)            (None, 7, 7, 128)         0         \n",
       "_________________________________________________________________\n",
-      "conv2d_transpose_12 (Conv2DT (None, 7, 7, 128)         409600    \n",
+      "conv2d_transpose (Conv2DTran (None, 7, 7, 128)         409600    \n",
       "_________________________________________________________________\n",
-      "batch_normalization_22 (Batc (None, 7, 7, 128)         512       \n",
+      "batch_normalization_1 (Batch (None, 7, 7, 128)         512       \n",
       "_________________________________________________________________\n",
-      "leaky_re_lu_22 (LeakyReLU)   (None, 7, 7, 128)         0         \n",
+      "leaky_re_lu_1 (LeakyReLU)    (None, 7, 7, 128)         0         \n",
       "_________________________________________________________________\n",
-      "conv2d_transpose_13 (Conv2DT (None, 14, 14, 64)        204800    \n",
+      "conv2d_transpose_1 (Conv2DTr (None, 14, 14, 64)        204800    \n",
       "_________________________________________________________________\n",
-      "batch_normalization_23 (Batc (None, 14, 14, 64)        256       \n",
+      "batch_normalization_2 (Batch (None, 14, 14, 64)        256       \n",
       "_________________________________________________________________\n",
-      "leaky_re_lu_23 (LeakyReLU)   (None, 14, 14, 64)        0         \n",
+      "leaky_re_lu_2 (LeakyReLU)    (None, 14, 14, 64)        0         \n",
       "_________________________________________________________________\n",
-      "conv2d_transpose_14 (Conv2DT (None, 28, 28, 32)        51200     \n",
+      "conv2d_transpose_2 (Conv2DTr (None, 28, 28, 32)        51200     \n",
       "_________________________________________________________________\n",
-      "batch_normalization_24 (Batc (None, 28, 28, 32)        128       \n",
+      "batch_normalization_3 (Batch (None, 28, 28, 32)        128       \n",
       "_________________________________________________________________\n",
-      "leaky_re_lu_24 (LeakyReLU)   (None, 28, 28, 32)        0         \n",
+      "leaky_re_lu_3 (LeakyReLU)    (None, 28, 28, 32)        0         \n",
       "_________________________________________________________________\n",
-      "conv2d_transpose_15 (Conv2DT (None, 28, 28, 1)         800       \n",
+      "conv2d_transpose_3 (Conv2DTr (None, 28, 28, 1)         800       \n",
       "=================================================================\n",
       "Total params: 817,824\n",
       "Trainable params: 804,832\n",
       "Non-trainable params: 12,992\n",
       "_________________________________________________________________\n",
-      "Model: \"sequential_7\"\n",
+      "Model: \"sequential_1\"\n",
       "_________________________________________________________________\n",
       "Layer (type)                 Output Shape              Param #   \n",
       "=================================================================\n",
-      "conv2d_12 (Conv2D)           (None, 28, 28, 64)        1664      \n",
+      "conv2d (Conv2D)              (None, 28, 28, 64)        1664      \n",
       "_________________________________________________________________\n",
-      "batch_normalization_25 (Batc (None, 28, 28, 64)        256       \n",
+      "batch_normalization_4 (Batch (None, 28, 28, 64)        256       \n",
       "_________________________________________________________________\n",
-      "leaky_re_lu_25 (LeakyReLU)   (None, 28, 28, 64)        0         \n",
+      "leaky_re_lu_4 (LeakyReLU)    (None, 28, 28, 64)        0         \n",
       "_________________________________________________________________\n",
-      "conv2d_13 (Conv2D)           (None, 14, 14, 128)       204928    \n",
+      "conv2d_1 (Conv2D)            (None, 14, 14, 128)       204928    \n",
       "_________________________________________________________________\n",
-      "batch_normalization_26 (Batc (None, 14, 14, 128)       512       \n",
+      "batch_normalization_5 (Batch (None, 14, 14, 128)       512       \n",
       "_________________________________________________________________\n",
-      "leaky_re_lu_26 (LeakyReLU)   (None, 14, 14, 128)       0         \n",
+      "leaky_re_lu_5 (LeakyReLU)    (None, 14, 14, 128)       0         \n",
       "_________________________________________________________________\n",
-      "dropout_6 (Dropout)          (None, 14, 14, 128)       0         \n",
+      "dropout (Dropout)            (None, 14, 14, 128)       0         \n",
       "_________________________________________________________________\n",
-      "conv2d_14 (Conv2D)           (None, 7, 7, 256)         819456    \n",
+      "conv2d_2 (Conv2D)            (None, 7, 7, 256)         819456    \n",
       "_________________________________________________________________\n",
-      "batch_normalization_27 (Batc (None, 7, 7, 256)         1024      \n",
+      "batch_normalization_6 (Batch (None, 7, 7, 256)         1024      \n",
       "_________________________________________________________________\n",
-      "leaky_re_lu_27 (LeakyReLU)   (None, 7, 7, 256)         0         \n",
+      "leaky_re_lu_6 (LeakyReLU)    (None, 7, 7, 256)         0         \n",
       "_________________________________________________________________\n",
-      "dropout_7 (Dropout)          (None, 7, 7, 256)         0         \n",
+      "dropout_1 (Dropout)          (None, 7, 7, 256)         0         \n",
       "_________________________________________________________________\n",
-      "conv2d_15 (Conv2D)           (None, 1, 1, 1)           12545     \n",
+      "conv2d_3 (Conv2D)            (None, 1, 1, 1)           12545     \n",
       "_________________________________________________________________\n",
-      "reshape_7 (Reshape)          (None, 1)                 0         \n",
+      "reshape_1 (Reshape)          (None, 1)                 0         \n",
       "=================================================================\n",
       "Total params: 1,040,385\n",
       "Trainable params: 1,039,489\n",
@@ -583,7 +582,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 16,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -609,7 +608,6 @@
    },
    "outputs": [],
    "source": [
-    "\n",
     "mnist_bldr = tfds.builder('mnist')\n",
     "mnist_bldr.download_and_prepare()\n",
     "mnist = mnist_bldr.as_dataset(shuffle_files=False)\n",
@@ -620,87 +618,87 @@
     "\n",
     "    image = image*2 - 1.0\n",
     "    if mode == 'uniform':\n",
-    "      input_z = tf.random.uniform(\n",
-    "          shape=(z_size,), minval=-1.0, maxval=1.0)\n",
+    "        input_z = tf.random.uniform(\n",
+    "            shape=(z_size,), minval=-1.0, maxval=1.0)\n",
     "    elif mode == 'normal':\n",
-    "      input_z = tf.random.normal(shape=(z_size,))\n",
-    "    return input_z, image\n"
+    "        input_z = tf.random.normal(shape=(z_size,))\n",
+    "    return input_z, image"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Model: \"sequential_15\"\n",
+      "Model: \"sequential_2\"\n",
       "_________________________________________________________________\n",
       "Layer (type)                 Output Shape              Param #   \n",
       "=================================================================\n",
-      "dense_8 (Dense)              (None, 6272)              125440    \n",
+      "dense_1 (Dense)              (None, 6272)              125440    \n",
       "_________________________________________________________________\n",
-      "batch_normalization_51 (Batc (None, 6272)              25088     \n",
+      "batch_normalization_7 (Batch (None, 6272)              25088     \n",
       "_________________________________________________________________\n",
-      "leaky_re_lu_51 (LeakyReLU)   (None, 6272)              0         \n",
+      "leaky_re_lu_7 (LeakyReLU)    (None, 6272)              0         \n",
       "_________________________________________________________________\n",
-      "reshape_15 (Reshape)         (None, 7, 7, 128)         0         \n",
+      "reshape_2 (Reshape)          (None, 7, 7, 128)         0         \n",
       "_________________________________________________________________\n",
-      "conv2d_transpose_29 (Conv2DT (None, 7, 7, 128)         409600    \n",
+      "conv2d_transpose_4 (Conv2DTr (None, 7, 7, 128)         409600    \n",
       "_________________________________________________________________\n",
-      "batch_normalization_52 (Batc (None, 7, 7, 128)         512       \n",
+      "batch_normalization_8 (Batch (None, 7, 7, 128)         512       \n",
       "_________________________________________________________________\n",
-      "leaky_re_lu_52 (LeakyReLU)   (None, 7, 7, 128)         0         \n",
+      "leaky_re_lu_8 (LeakyReLU)    (None, 7, 7, 128)         0         \n",
       "_________________________________________________________________\n",
-      "conv2d_transpose_30 (Conv2DT (None, 14, 14, 64)        204800    \n",
+      "conv2d_transpose_5 (Conv2DTr (None, 14, 14, 64)        204800    \n",
       "_________________________________________________________________\n",
-      "batch_normalization_53 (Batc (None, 14, 14, 64)        256       \n",
+      "batch_normalization_9 (Batch (None, 14, 14, 64)        256       \n",
       "_________________________________________________________________\n",
-      "leaky_re_lu_53 (LeakyReLU)   (None, 14, 14, 64)        0         \n",
+      "leaky_re_lu_9 (LeakyReLU)    (None, 14, 14, 64)        0         \n",
       "_________________________________________________________________\n",
-      "conv2d_transpose_31 (Conv2DT (None, 28, 28, 32)        51200     \n",
+      "conv2d_transpose_6 (Conv2DTr (None, 28, 28, 32)        51200     \n",
       "_________________________________________________________________\n",
-      "batch_normalization_54 (Batc (None, 28, 28, 32)        128       \n",
+      "batch_normalization_10 (Batc (None, 28, 28, 32)        128       \n",
       "_________________________________________________________________\n",
-      "leaky_re_lu_54 (LeakyReLU)   (None, 28, 28, 32)        0         \n",
+      "leaky_re_lu_10 (LeakyReLU)   (None, 28, 28, 32)        0         \n",
       "_________________________________________________________________\n",
-      "conv2d_transpose_32 (Conv2DT (None, 28, 28, 1)         800       \n",
+      "conv2d_transpose_7 (Conv2DTr (None, 28, 28, 1)         800       \n",
       "=================================================================\n",
       "Total params: 817,824\n",
       "Trainable params: 804,832\n",
       "Non-trainable params: 12,992\n",
       "_________________________________________________________________\n",
-      "Model: \"sequential_16\"\n",
+      "Model: \"sequential_3\"\n",
       "_________________________________________________________________\n",
       "Layer (type)                 Output Shape              Param #   \n",
       "=================================================================\n",
-      "conv2d_28 (Conv2D)           (None, 28, 28, 64)        1664      \n",
+      "conv2d_4 (Conv2D)            (None, 28, 28, 64)        1664      \n",
       "_________________________________________________________________\n",
-      "batch_normalization_55 (Batc (None, 28, 28, 64)        256       \n",
+      "batch_normalization_11 (Batc (None, 28, 28, 64)        256       \n",
       "_________________________________________________________________\n",
-      "leaky_re_lu_55 (LeakyReLU)   (None, 28, 28, 64)        0         \n",
+      "leaky_re_lu_11 (LeakyReLU)   (None, 28, 28, 64)        0         \n",
       "_________________________________________________________________\n",
-      "conv2d_29 (Conv2D)           (None, 14, 14, 128)       204928    \n",
+      "conv2d_5 (Conv2D)            (None, 14, 14, 128)       204928    \n",
       "_________________________________________________________________\n",
-      "batch_normalization_56 (Batc (None, 14, 14, 128)       512       \n",
+      "batch_normalization_12 (Batc (None, 14, 14, 128)       512       \n",
       "_________________________________________________________________\n",
-      "leaky_re_lu_56 (LeakyReLU)   (None, 14, 14, 128)       0         \n",
+      "leaky_re_lu_12 (LeakyReLU)   (None, 14, 14, 128)       0         \n",
       "_________________________________________________________________\n",
-      "dropout_14 (Dropout)         (None, 14, 14, 128)       0         \n",
+      "dropout_2 (Dropout)          (None, 14, 14, 128)       0         \n",
       "_________________________________________________________________\n",
-      "conv2d_30 (Conv2D)           (None, 7, 7, 256)         819456    \n",
+      "conv2d_6 (Conv2D)            (None, 7, 7, 256)         819456    \n",
       "_________________________________________________________________\n",
-      "batch_normalization_57 (Batc (None, 7, 7, 256)         1024      \n",
+      "batch_normalization_13 (Batc (None, 7, 7, 256)         1024      \n",
       "_________________________________________________________________\n",
-      "leaky_re_lu_57 (LeakyReLU)   (None, 7, 7, 256)         0         \n",
+      "leaky_re_lu_13 (LeakyReLU)   (None, 7, 7, 256)         0         \n",
       "_________________________________________________________________\n",
-      "dropout_15 (Dropout)         (None, 7, 7, 256)         0         \n",
+      "dropout_3 (Dropout)          (None, 7, 7, 256)         0         \n",
       "_________________________________________________________________\n",
-      "conv2d_31 (Conv2D)           (None, 1, 1, 1)           12545     \n",
+      "conv2d_7 (Conv2D)            (None, 1, 1, 1)           12545     \n",
       "_________________________________________________________________\n",
-      "reshape_16 (Reshape)         (None, 1)                 0         \n",
+      "reshape_3 (Reshape)          (None, 1)                 0         \n",
       "=================================================================\n",
       "Total params: 1,040,385\n",
       "Trainable params: 1,039,489\n",
@@ -736,34 +734,125 @@
     "\n",
     "    disc_model = make_dcgan_discriminator()\n",
     "    disc_model.build(input_shape=(None, np.prod(image_size)))\n",
-    "    disc_model.summary()\n"
+    "    disc_model.summary()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch   1 | ET 0.03 min | Avg Losses >> G/D   0.75/  6.81 [D-Real:  -1.27 D-Fake:  -0.75]\n",
-      "Epoch   2 | ET 0.07 min | Avg Losses >> G/D   2.50/ -0.14 [D-Real:  -6.28 D-Fake:  -2.50]\n",
-      "Epoch   3 | ET 0.10 min | Avg Losses >> G/D   4.14/ -5.65 [D-Real:  -9.88 D-Fake:  -4.14]\n",
-      "Epoch   4 | ET 0.13 min | Avg Losses >> G/D   4.10/-11.02 [D-Real: -14.86 D-Fake:  -4.10]\n",
-      "Epoch   5 | ET 0.16 min | Avg Losses >> G/D   3.76/-15.94 [D-Real: -19.64 D-Fake:  -3.76]\n",
-      "Epoch   6 | ET 0.20 min | Avg Losses >> G/D   2.51/-18.92 [D-Real: -23.22 D-Fake:  -2.51]\n",
-      "Epoch   7 | ET 0.23 min | Avg Losses >> G/D   1.39/-20.38 [D-Real: -25.34 D-Fake:  -1.39]\n",
-      "Epoch   8 | ET 0.26 min | Avg Losses >> G/D  -0.32/-21.35 [D-Real: -27.44 D-Fake:   0.32]\n",
-      "Epoch   9 | ET 0.30 min | Avg Losses >> G/D  -1.88/-24.97 [D-Real: -31.85 D-Fake:   1.88]\n",
-      "Epoch  10 | ET 0.33 min | Avg Losses >> G/D  -2.93/-27.06 [D-Real: -34.44 D-Fake:   2.93]\n"
+      "Epoch   1 | ET 1.58 min | Avg Losses >> G/D 186.47/-305.89 [D-Real: -204.71 D-Fake: -186.47]\n",
+      "Epoch   2 | ET 3.17 min | Avg Losses >> G/D 125.83/-23.81 [D-Real: -88.27 D-Fake: -125.83]\n",
+      "Epoch   3 | ET 4.77 min | Avg Losses >> G/D  81.43/ -2.47 [D-Real:  29.42 D-Fake: -81.43]\n",
+      "Epoch   4 | ET 6.37 min | Avg Losses >> G/D  43.89/ -6.47 [D-Real: -14.41 D-Fake: -43.89]\n",
+      "Epoch   5 | ET 7.97 min | Avg Losses >> G/D  37.12/ -5.75 [D-Real:   4.77 D-Fake: -37.12]\n",
+      "Epoch   6 | ET 9.56 min | Avg Losses >> G/D  37.59/-10.89 [D-Real:  11.12 D-Fake: -37.59]\n",
+      "Epoch   7 | ET 11.16 min | Avg Losses >> G/D  48.30/-13.90 [D-Real:  32.22 D-Fake: -48.30]\n",
+      "Epoch   8 | ET 12.76 min | Avg Losses >> G/D  43.40/-20.73 [D-Real:  19.27 D-Fake: -43.40]\n",
+      "Epoch   9 | ET 14.36 min | Avg Losses >> G/D  51.94/-32.62 [D-Real:  10.19 D-Fake: -51.94]\n",
+      "Epoch  10 | ET 15.97 min | Avg Losses >> G/D  54.99/-34.56 [D-Real:  10.05 D-Fake: -54.99]\n",
+      "Epoch  11 | ET 17.57 min | Avg Losses >> G/D  78.72/-43.58 [D-Real:  21.09 D-Fake: -78.72]\n",
+      "Epoch  12 | ET 19.16 min | Avg Losses >> G/D  83.79/-43.11 [D-Real:  26.02 D-Fake: -83.79]\n",
+      "Epoch  13 | ET 20.76 min | Avg Losses >> G/D  84.35/-33.70 [D-Real:  29.12 D-Fake: -84.35]\n",
+      "Epoch  14 | ET 22.36 min | Avg Losses >> G/D  78.19/-30.97 [D-Real:  34.40 D-Fake: -78.19]\n",
+      "Epoch  15 | ET 23.96 min | Avg Losses >> G/D  75.11/-44.77 [D-Real:  18.49 D-Fake: -75.11]\n",
+      "Epoch  16 | ET 25.56 min | Avg Losses >> G/D  83.66/-44.93 [D-Real:  25.06 D-Fake: -83.66]\n",
+      "Epoch  17 | ET 27.16 min | Avg Losses >> G/D  97.82/-41.78 [D-Real:  42.69 D-Fake: -97.82]\n",
+      "Epoch  18 | ET 28.76 min | Avg Losses >> G/D 102.77/-41.13 [D-Real:  44.20 D-Fake: -102.77]\n",
+      "Epoch  19 | ET 30.36 min | Avg Losses >> G/D  98.06/-45.39 [D-Real:  36.53 D-Fake: -98.06]\n",
+      "Epoch  20 | ET 31.96 min | Avg Losses >> G/D  92.78/-43.22 [D-Real:  39.53 D-Fake: -92.78]\n",
+      "Epoch  21 | ET 33.56 min | Avg Losses >> G/D 119.17/-45.35 [D-Real:  63.00 D-Fake: -119.17]\n",
+      "Epoch  22 | ET 35.15 min | Avg Losses >> G/D 167.63/-45.22 [D-Real: 109.72 D-Fake: -167.63]\n",
+      "Epoch  23 | ET 36.75 min | Avg Losses >> G/D 143.33/-43.10 [D-Real:  78.66 D-Fake: -143.33]\n",
+      "Epoch  24 | ET 38.35 min | Avg Losses >> G/D 165.30/-45.59 [D-Real: 108.96 D-Fake: -165.30]\n",
+      "Epoch  25 | ET 39.95 min | Avg Losses >> G/D 185.48/-49.65 [D-Real: 120.26 D-Fake: -185.48]\n",
+      "Epoch  26 | ET 41.54 min | Avg Losses >> G/D 177.84/-46.74 [D-Real: 111.94 D-Fake: -177.84]\n",
+      "Epoch  27 | ET 43.14 min | Avg Losses >> G/D 235.96/-57.86 [D-Real: 165.91 D-Fake: -235.96]\n",
+      "Epoch  28 | ET 44.74 min | Avg Losses >> G/D 246.81/-30.65 [D-Real: 198.56 D-Fake: -246.81]\n",
+      "Epoch  29 | ET 46.34 min | Avg Losses >> G/D 296.19/-36.56 [D-Real: 256.34 D-Fake: -296.19]\n",
+      "Epoch  30 | ET 47.94 min | Avg Losses >> G/D 317.43/-51.34 [D-Real: 260.19 D-Fake: -317.43]\n",
+      "Epoch  31 | ET 49.54 min | Avg Losses >> G/D 343.99/-47.43 [D-Real: 285.17 D-Fake: -343.99]\n",
+      "Epoch  32 | ET 51.14 min | Avg Losses >> G/D 367.00/-46.06 [D-Real: 303.26 D-Fake: -367.00]\n",
+      "Epoch  33 | ET 52.74 min | Avg Losses >> G/D 359.17/ 15.57 [D-Real: 311.80 D-Fake: -359.17]\n",
+      "Epoch  34 | ET 54.35 min | Avg Losses >> G/D 306.75/-28.72 [D-Real: 252.32 D-Fake: -306.75]\n",
+      "Epoch  35 | ET 55.94 min | Avg Losses >> G/D 338.60/-47.47 [D-Real: 282.77 D-Fake: -338.60]\n",
+      "Epoch  36 | ET 57.54 min | Avg Losses >> G/D 348.70/-51.16 [D-Real: 285.71 D-Fake: -348.70]\n",
+      "Epoch  37 | ET 59.14 min | Avg Losses >> G/D 339.03/-42.02 [D-Real: 291.79 D-Fake: -339.03]\n",
+      "Epoch  38 | ET 60.73 min | Avg Losses >> G/D 384.91/-48.19 [D-Real: 321.08 D-Fake: -384.91]\n",
+      "Epoch  39 | ET 62.34 min | Avg Losses >> G/D 377.89/-46.81 [D-Real: 322.20 D-Fake: -377.89]\n",
+      "Epoch  40 | ET 63.94 min | Avg Losses >> G/D 356.70/-41.24 [D-Real: 307.53 D-Fake: -356.70]\n",
+      "Epoch  41 | ET 65.54 min | Avg Losses >> G/D 352.23/-36.78 [D-Real: 312.28 D-Fake: -352.23]\n",
+      "Epoch  42 | ET 67.14 min | Avg Losses >> G/D 512.82/-54.96 [D-Real: 452.57 D-Fake: -512.82]\n",
+      "Epoch  43 | ET 68.74 min | Avg Losses >> G/D 525.44/-58.37 [D-Real: 451.38 D-Fake: -525.44]\n",
+      "Epoch  44 | ET 70.34 min | Avg Losses >> G/D 537.93/-46.99 [D-Real: 471.04 D-Fake: -537.93]\n",
+      "Epoch  45 | ET 71.94 min | Avg Losses >> G/D 586.10/-53.15 [D-Real: 523.73 D-Fake: -586.10]\n",
+      "Epoch  46 | ET 73.53 min | Avg Losses >> G/D 631.31/-61.20 [D-Real: 556.68 D-Fake: -631.31]\n",
+      "Epoch  47 | ET 75.14 min | Avg Losses >> G/D 644.35/-66.45 [D-Real: 571.78 D-Fake: -644.35]\n",
+      "Epoch  48 | ET 76.74 min | Avg Losses >> G/D 766.90/-68.34 [D-Real: 683.32 D-Fake: -766.90]\n",
+      "Epoch  49 | ET 78.33 min | Avg Losses >> G/D 715.37/-11.67 [D-Real: 654.83 D-Fake: -715.37]\n",
+      "Epoch  50 | ET 79.93 min | Avg Losses >> G/D 707.44/-65.47 [D-Real: 631.52 D-Fake: -707.44]\n",
+      "Epoch  51 | ET 81.53 min | Avg Losses >> G/D 682.43/-77.68 [D-Real: 600.63 D-Fake: -682.43]\n",
+      "Epoch  52 | ET 83.12 min | Avg Losses >> G/D 883.31/-74.31 [D-Real: 797.64 D-Fake: -883.31]\n",
+      "Epoch  53 | ET 84.72 min | Avg Losses >> G/D 828.10/ -4.36 [D-Real: 771.68 D-Fake: -828.10]\n",
+      "Epoch  54 | ET 86.32 min | Avg Losses >> G/D 916.28/-18.10 [D-Real: 871.71 D-Fake: -916.28]\n",
+      "Epoch  55 | ET 87.92 min | Avg Losses >> G/D 890.63/-52.51 [D-Real: 832.85 D-Fake: -890.63]\n",
+      "Epoch  56 | ET 89.51 min | Avg Losses >> G/D 706.38/-60.17 [D-Real: 642.28 D-Fake: -706.38]\n",
+      "Epoch  57 | ET 91.11 min | Avg Losses >> G/D 841.65/-93.87 [D-Real: 740.63 D-Fake: -841.65]\n",
+      "Epoch  58 | ET 92.71 min | Avg Losses >> G/D 1030.48/-117.84 [D-Real: 902.95 D-Fake: -1030.48]\n",
+      "Epoch  59 | ET 94.31 min | Avg Losses >> G/D 965.95/-89.45 [D-Real: 867.79 D-Fake: -965.95]\n",
+      "Epoch  60 | ET 95.91 min | Avg Losses >> G/D 1197.10/-105.03 [D-Real: 1055.86 D-Fake: -1197.10]\n",
+      "Epoch  61 | ET 97.51 min | Avg Losses >> G/D 1094.58/-125.98 [D-Real: 946.71 D-Fake: -1094.58]\n",
+      "Epoch  62 | ET 99.11 min | Avg Losses >> G/D 1158.20/-130.87 [D-Real: 1009.98 D-Fake: -1158.20]\n",
+      "Epoch  63 | ET 100.70 min | Avg Losses >> G/D 1015.38/-102.59 [D-Real: 907.90 D-Fake: -1015.38]\n",
+      "Epoch  64 | ET 102.30 min | Avg Losses >> G/D 1452.54/-183.59 [D-Real: 1250.75 D-Fake: -1452.54]\n",
+      "Epoch  65 | ET 103.90 min | Avg Losses >> G/D 1532.75/-176.89 [D-Real: 1327.26 D-Fake: -1532.75]\n",
+      "Epoch  66 | ET 105.50 min | Avg Losses >> G/D 1372.27/-184.02 [D-Real: 1173.63 D-Fake: -1372.27]\n",
+      "Epoch  67 | ET 107.10 min | Avg Losses >> G/D 1476.47/-151.54 [D-Real: 1286.28 D-Fake: -1476.47]\n",
+      "Epoch  68 | ET 108.70 min | Avg Losses >> G/D 1337.81/-165.44 [D-Real: 1155.44 D-Fake: -1337.81]\n",
+      "Epoch  69 | ET 110.30 min | Avg Losses >> G/D 1868.09/-265.95 [D-Real: 1564.99 D-Fake: -1868.09]\n",
+      "Epoch  70 | ET 111.90 min | Avg Losses >> G/D 1815.22/155.57 [D-Real: 1589.90 D-Fake: -1815.22]\n",
+      "Epoch  71 | ET 113.50 min | Avg Losses >> G/D 2016.40/-162.41 [D-Real: 1828.58 D-Fake: -2016.40]\n",
+      "Epoch  72 | ET 115.10 min | Avg Losses >> G/D 2118.12/-280.26 [D-Real: 1827.30 D-Fake: -2118.12]\n",
+      "Epoch  73 | ET 116.69 min | Avg Losses >> G/D 2143.48/-318.27 [D-Real: 1818.62 D-Fake: -2143.48]\n",
+      "Epoch  74 | ET 118.29 min | Avg Losses >> G/D 2188.90/-349.97 [D-Real: 1830.72 D-Fake: -2188.90]\n",
+      "Epoch  75 | ET 119.90 min | Avg Losses >> G/D 2362.95/-404.66 [D-Real: 1941.11 D-Fake: -2362.95]\n",
+      "Epoch  76 | ET 121.50 min | Avg Losses >> G/D 2443.07/-427.19 [D-Real: 2004.03 D-Fake: -2443.07]\n",
+      "Epoch  77 | ET 123.10 min | Avg Losses >> G/D 2404.13/-391.35 [D-Real: 1998.95 D-Fake: -2404.13]\n",
+      "Epoch  78 | ET 124.70 min | Avg Losses >> G/D 2562.10/-411.77 [D-Real: 2129.07 D-Fake: -2562.10]\n",
+      "Epoch  79 | ET 126.30 min | Avg Losses >> G/D 2826.90/-540.18 [D-Real: 2257.65 D-Fake: -2826.90]\n",
+      "Epoch  80 | ET 127.90 min | Avg Losses >> G/D 2765.97/-489.78 [D-Real: 2263.39 D-Fake: -2765.97]\n",
+      "Epoch  81 | ET 129.50 min | Avg Losses >> G/D 2775.33/-561.67 [D-Real: 2196.64 D-Fake: -2775.33]\n",
+      "Epoch  82 | ET 131.10 min | Avg Losses >> G/D 3329.70/-599.79 [D-Real: 2616.69 D-Fake: -3329.70]\n",
+      "Epoch  83 | ET 132.70 min | Avg Losses >> G/D 3475.59/-675.97 [D-Real: 2752.62 D-Fake: -3475.59]\n",
+      "Epoch  84 | ET 134.29 min | Avg Losses >> G/D 3634.00/-782.03 [D-Real: 2835.74 D-Fake: -3634.00]\n",
+      "Epoch  85 | ET 135.90 min | Avg Losses >> G/D 3804.03/-801.69 [D-Real: 2961.38 D-Fake: -3804.03]\n",
+      "Epoch  86 | ET 137.50 min | Avg Losses >> G/D 3938.59/-868.39 [D-Real: 3045.14 D-Fake: -3938.59]\n",
+      "Epoch  87 | ET 139.10 min | Avg Losses >> G/D 3951.56/-853.02 [D-Real: 3086.04 D-Fake: -3951.56]\n",
+      "Epoch  88 | ET 140.70 min | Avg Losses >> G/D 3248.74/-723.00 [D-Real: 2495.87 D-Fake: -3248.74]\n",
+      "Epoch  89 | ET 142.29 min | Avg Losses >> G/D 4644.86/-1046.76 [D-Real: 3557.25 D-Fake: -4644.86]\n",
+      "Epoch  90 | ET 143.89 min | Avg Losses >> G/D 4885.19/-1035.63 [D-Real: 3767.10 D-Fake: -4885.19]\n",
+      "Epoch  91 | ET 145.49 min | Avg Losses >> G/D 3802.31/-880.71 [D-Real: 2886.02 D-Fake: -3802.31]\n",
+      "Epoch  92 | ET 147.09 min | Avg Losses >> G/D 4992.27/-1107.25 [D-Real: 3849.27 D-Fake: -4992.27]\n",
+      "Epoch  93 | ET 148.70 min | Avg Losses >> G/D 5438.34/-1285.65 [D-Real: 4107.10 D-Fake: -5438.34]\n",
+      "Epoch  94 | ET 150.30 min | Avg Losses >> G/D 5705.12/-1254.32 [D-Real: 4341.58 D-Fake: -5705.12]\n",
+      "Epoch  95 | ET 151.90 min | Avg Losses >> G/D 6116.86/-1472.97 [D-Real: 4579.57 D-Fake: -6116.86]\n",
+      "Epoch  96 | ET 153.50 min | Avg Losses >> G/D 6402.22/-1595.38 [D-Real: 4765.93 D-Fake: -6402.22]\n",
+      "Epoch  97 | ET 155.10 min | Avg Losses >> G/D 6487.41/-1598.25 [D-Real: 4807.29 D-Fake: -6487.41]\n",
+      "Epoch  98 | ET 156.70 min | Avg Losses >> G/D 5330.31/-1202.23 [D-Real: 4032.31 D-Fake: -5330.31]\n",
+      "Epoch  99 | ET 158.30 min | Avg Losses >> G/D 6946.26/-1631.31 [D-Real: 5270.38 D-Fake: -6946.26]\n",
+      "Epoch 100 | ET 159.90 min | Avg Losses >> G/D 7301.76/-1722.93 [D-Real: 5541.48 D-Fake: -7301.76]\n"
      ]
     }
    ],
    "source": [
     "import time\n",
     "\n",
+    "\n",
     "## optimizers:\n",
     "g_optimizer = tf.keras.optimizers.Adam(0.0002)\n",
     "d_optimizer = tf.keras.optimizers.Adam(0.0002)\n",
@@ -805,7 +894,7 @@
     "            d_loss_fake =  tf.math.reduce_mean(d_critics_fake)\n",
     "            d_loss = d_loss_real + d_loss_fake\n",
     "\n",
-    "            ## Gradeint-penalty:\n",
+    "            ## Gradient penalty:\n",
     "            with tf.GradientTape() as gp_tape:\n",
     "                alpha = tf.random.uniform(\n",
     "                    shape=[d_critics_real.shape[0], 1, 1, 1], \n",
@@ -846,26 +935,12 @@
     "    \n",
     "    epoch_samples.append(\n",
     "        create_samples(gen_model, fixed_z).numpy()\n",
-    "    )\n"
+    "    )"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 19,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -884,12 +959,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 576x432 with 2 Axes>"
       ]
@@ -931,31 +1006,20 @@
     "ax.tick_params(axis='both', which='major', labelsize=15)\n",
     "ax2.tick_params(axis='both', which='major', labelsize=15)\n",
     "\n",
-    "#plt.savefig('/content/drive/My Drive/Colab Notebooks/PyML-3rd-edition/ch17-wdcgan-learning-curve.pdf')\n",
-    "plt.show()\n"
+    "#plt.savefig('images/ch17-wdcgan-learning-curve.pdf')\n",
+    "plt.show()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
-    {
-     "ename": "IndexError",
-     "evalue": "list index out of range",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mIndexError\u001b[0m                                Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-30-b074bab00d4d>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     14\u001b[0m                 transform=ax.transAxes)\n\u001b[1;32m     15\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 16\u001b[0;31m         \u001b[0mimage\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mepoch_samples\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mj\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     17\u001b[0m         \u001b[0max\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimshow\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcmap\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'gray_r'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     18\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mIndexError\u001b[0m: list index out of range"
-     ]
-    },
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
-       "<Figure size 720x1008 with 21 Axes>"
+       "<Figure size 720x1008 with 30 Axes>"
       ]
      },
      "metadata": {},
@@ -963,7 +1027,6 @@
     }
    ],
    "source": [
-    "\n",
     "selected_epochs = [1, 2, 4, 10, 50, 100]\n",
     "fig = plt.figure(figsize=(10, 14))\n",
     "for i,e in enumerate(selected_epochs):\n",
@@ -982,8 +1045,8 @@
     "        image = epoch_samples[e-1][j]\n",
     "        ax.imshow(image, cmap='gray_r')\n",
     "    \n",
-    "#plt.savefig('/content/drive/My Drive/Colab Notebooks/PyML-3rd-edition/ch17-wdcgan-samples.pdf')\n",
-    "plt.show()\n"
+    "#plt.savefig('images/ch17-wdcgan-samples.pdf')\n",
+    "plt.show()"
    ]
   },
   {
@@ -995,9 +1058,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 22,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<IPython.core.display.Image object>"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {
+      "image/png": {
+       "width": 600
+      }
+     },
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "Image(filename='images/17_16.png', width=600)"
    ]
@@ -1024,9 +1103,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 23,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[NbConvertApp] Converting notebook ch17_part2.ipynb to script\n",
+      "[NbConvertApp] Writing 11640 bytes to ch17_part2.py\n"
+     ]
+    }
+   ],
    "source": [
     "! python ../.convert_notebook_to_script.py --input ch17_part2.ipynb --output ch17_part2.py"
    ]
@@ -1054,7 +1142,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.4"
+   "version": "3.7.3"
   }
  },
  "nbformat": 4,
diff --git a/ch17/ch17_part2.py b/ch17/ch17_part2.py
index 2f566824..145b7735 100644
--- a/ch17/ch17_part2.py
+++ b/ch17/ch17_part2.py
@@ -15,8 +15,7 @@
 # 
 # Code License: [MIT License](https://github.com/rasbt/python-machine-learning-book-3rd-edition/blob/master/LICENSE.txt)
 
-# Chapter 17: Generative Adversarial Networks (part 2/2)
-# =====
+# # Chapter 17: Generative Adversarial Networks (Part 2/2)
 
 # Note that the optional watermark extension is a small IPython notebook plugin that I developed to make the code reproducible. You can just skip the following line(s).
 
@@ -70,15 +69,19 @@
 
 
 
-#import tensorflow as tf
-#print("GPU Available: ", tf.test.is_gpu_available())
-#device_name = tf.test.gpu_device_name()
-#device_name
 
 
+print(tf.__version__)
 
+print("GPU Available:", tf.test.is_gpu_available())
 
+if tf.test.is_gpu_available():
+    device_name = tf.test.gpu_device_name()
 
+else:
+    device_name = 'CPU:0'
+    
+print(device_name)
 
 
 
@@ -87,11 +90,16 @@
 
 
 
-def make_dcgan_generator(z_size=20, output_size=(28, 28, 1),
-                         n_filters=128, n_blocks=2):
+def make_dcgan_generator(
+        z_size=20, 
+        output_size=(28, 28, 1),
+        n_filters=128, 
+        n_blocks=2):
     size_factor = 2**n_blocks
-    hidden_size = (output_size[0]//size_factor, 
-                   output_size[1]//size_factor)
+    hidden_size = (
+        output_size[0]//size_factor, 
+        output_size[1]//size_factor
+    )
     
     model = tf.keras.Sequential([
         tf.keras.layers.Input(shape=(z_size,)),
@@ -114,21 +122,25 @@ def make_dcgan_generator(z_size=20, output_size=(28, 28, 1),
     nf = n_filters
     for i in range(n_blocks):
         nf = nf // 2
-        model.add(tf.keras.layers.Conv2DTranspose(
-            filters=nf, kernel_size=(5, 5), strides=(2, 2),
-            padding='same', use_bias=False))
+        model.add(
+            tf.keras.layers.Conv2DTranspose(
+                filters=nf, kernel_size=(5, 5), strides=(2, 2),
+                padding='same', use_bias=False))
         model.add(tf.keras.layers.BatchNormalization())
         model.add(tf.keras.layers.LeakyReLU())
                 
-        
-    model.add(tf.keras.layers.Conv2DTranspose(
-        filters=output_size[2], kernel_size=(5, 5), strides=(1, 1), 
-        padding='same', use_bias=False, activation='tanh'))
+    model.add(
+        tf.keras.layers.Conv2DTranspose(
+            filters=output_size[2], kernel_size=(5, 5), 
+            strides=(1, 1), padding='same', use_bias=False, 
+            activation='tanh'))
         
     return model
 
-def make_dcgan_discriminator(input_size=(28, 28, 1),
-                             n_filters=64, n_blocks=2):
+def make_dcgan_discriminator(
+        input_size=(28, 28, 1),
+        n_filters=64, 
+        n_blocks=2):
     model = tf.keras.Sequential([
         tf.keras.layers.Input(shape=input_size),
         tf.keras.layers.Conv2D(
@@ -141,9 +153,10 @@ def make_dcgan_discriminator(input_size=(28, 28, 1),
     nf = n_filters
     for i in range(n_blocks):
         nf = nf*2
-        model.add(tf.keras.layers.Conv2D(
-            filters=nf, kernel_size=(5, 5), 
-            strides=(2, 2),padding='same'))
+        model.add(
+            tf.keras.layers.Conv2D(
+                filters=nf, kernel_size=(5, 5), 
+                strides=(2, 2),padding='same'))
         model.add(tf.keras.layers.BatchNormalization())
         model.add(tf.keras.layers.LeakyReLU())
         model.add(tf.keras.layers.Dropout(0.3))
@@ -183,7 +196,6 @@ def make_dcgan_discriminator(input_size=(28, 28, 1),
 
 
 
-
 mnist_bldr = tfds.builder('mnist')
 mnist_bldr.download_and_prepare()
 mnist = mnist_bldr.as_dataset(shuffle_files=False)
@@ -194,48 +206,28 @@ def preprocess(ex, mode='uniform'):
 
     image = image*2 - 1.0
     if mode == 'uniform':
-      input_z = tf.random.uniform(shape=(z_size,),
-                                  minval=-1.0, maxval=1.0)
+        input_z = tf.random.uniform(
+            shape=(z_size,), minval=-1.0, maxval=1.0)
     elif mode == 'normal':
-      input_z = tf.random.normal(shape=(z_size,))
+        input_z = tf.random.normal(shape=(z_size,))
     return input_z, image
 
 
 
 
 num_epochs = 100
-batch_size = 64
+batch_size = 128
 image_size = (28, 28)
 z_size = 20
 mode_z = 'uniform'
-gen_hidden_layers = 1
-gen_hidden_size = 100
-disc_hidden_layers = 1
-disc_hidden_size = 100
+lambda_gp = 10.0
 
 tf.random.set_seed(1)
 np.random.seed(1)
 
-
-if mode_z == 'uniform':
-    fixed_z = tf.random.uniform(
-        shape=(batch_size, z_size),
-        minval=-1, maxval=1)
-elif mode_z == 'normal':
-    fixed_z = tf.random.normal(
-        shape=(batch_size, z_size))
-
-def create_samples(g_model, input_z):
-    g_output = g_model(input_z, training=False)
-    images = tf.reshape(g_output, (batch_size, *image_size))    
-    return (images+1)/2.0
-
 ## Set-up the dataset
 mnist_trainset = mnist['train']
-mnist_trainset = mnist_trainset.map(
-    lambda ex: preprocess(ex, mode=mode_z))
-
-input_z, input_real = next(iter(mnist_trainset))
+mnist_trainset = mnist_trainset.map(preprocess)
 
 mnist_trainset = mnist_trainset.shuffle(10000)
 mnist_trainset = mnist_trainset.batch(
@@ -245,84 +237,100 @@ def create_samples(g_model, input_z):
 with tf.device(device_name):
     gen_model = make_dcgan_generator()
     gen_model.build(input_shape=(None, z_size))
+    gen_model.summary()
 
     disc_model = make_dcgan_discriminator()
     disc_model.build(input_shape=(None, np.prod(image_size)))
+    disc_model.summary()
+
+
+
+
+
 
-## Loss function and optimizers:
-loss_fn = tf.keras.losses.BinaryCrossentropy(from_logits=True)
-g_optimizer = tf.keras.optimizers.Adam()
-d_optimizer = tf.keras.optimizers.Adam()
+## optimizers:
+g_optimizer = tf.keras.optimizers.Adam(0.0002)
+d_optimizer = tf.keras.optimizers.Adam(0.0002)
+
+if mode_z == 'uniform':
+    fixed_z = tf.random.uniform(
+        shape=(batch_size, z_size),
+        minval=-1, maxval=1)
+elif mode_z == 'normal':
+    fixed_z = tf.random.normal(
+        shape=(batch_size, z_size))
 
-avg_epoch_losses = []
-avg_d_vals = []
+def create_samples(g_model, input_z):
+    g_output = g_model(input_z, training=False)
+    images = tf.reshape(g_output, (batch_size, *image_size))    
+    return (images+1)/2.0
+
+all_losses = []
 epoch_samples = []
 
 start_time = time.time()
+
 for epoch in range(1, num_epochs+1):
-    losses = []
+    epoch_losses = []
     for i,(input_z,input_real) in enumerate(mnist_trainset):
         
-        ## Compute discriminator's real-loss and its gradients:
-        with tf.GradientTape() as d_tape_real:
-            d_logits_real = disc_model(input_real, training=True)
-
-            d_labels_real = tf.ones_like(d_logits_real)# * smoothing_factor
+        ## Compute discriminator's loss and gradients:
+        with tf.GradientTape() as d_tape, tf.GradientTape() as g_tape:
+            g_output = gen_model(input_z, training=True)
+            
+            d_critics_real = disc_model(input_real, training=True)
+            d_critics_fake = disc_model(g_output, training=True)
+
+            ## Compute generator's loss:
+            g_loss = -tf.math.reduce_mean(d_critics_fake)
+
+            ## Compute discriminator's losses
+            d_loss_real = -tf.math.reduce_mean(d_critics_real)
+            d_loss_fake =  tf.math.reduce_mean(d_critics_fake)
+            d_loss = d_loss_real + d_loss_fake
+
+            ## Gradient penalty:
+            with tf.GradientTape() as gp_tape:
+                alpha = tf.random.uniform(
+                    shape=[d_critics_real.shape[0], 1, 1, 1], 
+                    minval=0.0, maxval=1.0)
+                interpolated = (
+                    alpha*input_real + (1-alpha)*g_output)
+                gp_tape.watch(interpolated)
+                d_critics_intp = disc_model(interpolated)
             
-            d_loss_real = loss_fn(y_true=d_labels_real,
-                                  y_pred=d_logits_real)
-        d_grads_real = d_tape_real.gradient(
-               d_loss_real, disc_model.trainable_variables)
-        ## Optimization: Apply the gradients
+            grads_intp = gp_tape.gradient(
+                d_critics_intp, [interpolated,])[0]
+            grads_intp_l2 = tf.sqrt(
+                tf.reduce_sum(tf.square(grads_intp), axis=[1, 2, 3]))
+            grad_penalty = tf.reduce_mean(tf.square(grads_intp_l2 - 1.0))
+        
+            d_loss = d_loss + lambda_gp*grad_penalty
+        
+        ## Optimization: Compute the gradients apply them
+        d_grads = d_tape.gradient(d_loss, disc_model.trainable_variables)
         d_optimizer.apply_gradients(
-            grads_and_vars=zip(d_grads_real,
-                               disc_model.trainable_variables))
-       
+            grads_and_vars=zip(d_grads, disc_model.trainable_variables))
         
-        ## Compute generator's loss and its gradients:
-        with tf.GradientTape() as g_tape:
-            g_output = gen_model(input_z)
-            d_logits_fake = disc_model(g_output, training=True)
-            labels_real = tf.ones_like(d_logits_fake)
-            g_loss = loss_fn(y_true=labels_real,
-                             y_pred=d_logits_fake)
-            
         g_grads = g_tape.gradient(g_loss, gen_model.trainable_variables)
         g_optimizer.apply_gradients(
             grads_and_vars=zip(g_grads, gen_model.trainable_variables))
-        
-            
-        ## Compute discriminator's fake-loss and its gradients:
-        with tf.GradientTape() as d_tape_fake:
-            d_logits_fake = disc_model(g_output.numpy(), training=True)
-            d_labels_fake = tf.zeros_like(d_logits_fake)
-
-            d_loss_fake = loss_fn(y_true=d_labels_fake,
-                                  y_pred=d_logits_fake)
 
-            d_grads_fake = d_tape_fake.gradient(
-                d_loss_fake, disc_model.trainable_variables)
-        ## Optimization: Apply the gradients
-        d_optimizer.apply_gradients(
-            grads_and_vars=zip(d_grads_fake, 
-                               disc_model.trainable_variables))
-        
-        d_loss = (d_loss_real + d_loss_fake)/2.0
-        losses.append(
+        epoch_losses.append(
             (g_loss.numpy(), d_loss.numpy(), 
              d_loss_real.numpy(), d_loss_fake.numpy()))
-        
-        
-        d_probs_real = tf.reduce_mean(tf.sigmoid(d_logits_real))
-        d_probs_fake = tf.reduce_mean(tf.sigmoid(d_logits_fake))
-        avg_d_vals.append((d_probs_real.numpy(), d_probs_fake.numpy()))        
-    avg_epoch_losses.append(np.mean(losses, axis=0))
+                    
+    all_losses.append(epoch_losses)
+    
     print('Epoch {:-3d} | ET {:.2f} min | Avg Losses >>'
-          ' G/D {:.4f}/{:.4f} [D-Real: {:.4f} D-Fake: {:.4f}]'
+          ' G/D {:6.2f}/{:6.2f} [D-Real: {:6.2f} D-Fake: {:6.2f}]'
           .format(epoch, (time.time() - start_time)/60, 
-                  *list(avg_epoch_losses[-1])))
-    epoch_samples.append(create_samples(
-          gen_model, num_samples=8).numpy())
+                  *list(np.mean(all_losses[-1], axis=0)))
+    )
+    
+    epoch_samples.append(
+        create_samples(gen_model, fixed_z).numpy()
+    )
 
 
 
@@ -367,7 +375,7 @@ def create_samples(g_model, input_z):
 ax.tick_params(axis='both', which='major', labelsize=15)
 ax2.tick_params(axis='both', which='major', labelsize=15)
 
-#plt.savefig('/content/drive/My Drive/Colab Notebooks/PyML-3rd-edition/ch17-wdcgan-learning-curve.pdf')
+#plt.savefig('images/ch17-wdcgan-learning-curve.pdf')
 plt.show()
 
 
@@ -381,30 +389,34 @@ def create_samples(g_model, input_z):
         ax.set_xticks([])
         ax.set_yticks([])
         if j == 0:
-            ax.text(-0.06, 0.5, 'Epoch {}'.format(e),
-                    rotation=90, size=18, color='red',
-                    horizontalalignment='right',
-                    verticalalignment='center', 
-                    transform=ax.transAxes)
+            ax.text(
+                -0.06, 0.5, 'Epoch {}'.format(e),
+                rotation=90, size=18, color='red',
+                horizontalalignment='right',
+                verticalalignment='center', 
+                transform=ax.transAxes)
         
         image = epoch_samples[e-1][j]
         ax.imshow(image, cmap='gray_r')
     
-#plt.savefig('/content/drive/My Drive/Colab Notebooks/PyML-3rd-edition/ch17-wdcgan-samples.pdf')
+#plt.savefig('images/ch17-wdcgan-samples.pdf')
 plt.show()
 
 
-
-
-
-
-
 # ## Mode collapse
 
 
 
 
 
+# 
+# ----
+
+# 
+# 
+# Readers may ignore the next cell.
+# 
+#