Bugfix

.dockerignore

@@ -0,0 +1,2 @@
+data/
+run/

.gitignore

@@ -1,3 +1,4 @@
+Dockerfile
 
 run/gan/*
 run/compose/*

02_01_deep_learning_deep_neural_network.ipynb

@@ -23,12 +23,12 @@
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
     "\n",
-    "from keras.layers import Input, Flatten, Dense, Conv2D\n",
-    "from keras.models import Model\n",
-    "from keras.optimizers import Adam\n",
-    "from keras.utils import to_categorical\n",
+    "from tensorflow.keras.layers import Input, Flatten, Dense, Conv2D\n",
+    "from tensorflow.keras.models import Model\n",
+    "from tensorflow.keras.optimizers import Adam\n",
+    "from tensorflow.keras.utils import to_categorical\n",
     "\n",
-    "from keras.datasets import cifar10"
+    "from tensorflow.keras.datasets import cifar10"
    ]
   },
   {
@@ -100,15 +100,8 @@
     "\n",
     "output_layer = Dense(NUM_CLASSES, activation = 'softmax')(x)\n",
     "\n",
-    "model = Model(input_layer, output_layer)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "model = Model(input_layer, output_layer)\n",
+    "\n",
     "model.summary()"
    ]
   },
@@ -174,7 +167,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "scrolled": true
+   },
    "outputs": [],
    "source": [
     "\n",
@@ -192,13 +187,6 @@
     "    ax.text(0.5, -0.7, 'act = ' + str(actual_single[idx]), fontsize=10, ha='center', transform=ax.transAxes)\n",
     "    ax.imshow(img)\n"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -217,7 +205,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.5"
+   "version": "3.7.5"
   }
  },
  "nbformat": 4,

02_02_deep_learning_convolutions.ipynb

@@ -219,13 +219,6 @@
     "plt.axis('off')\n",
     "plt.imshow(new_image, cmap='Greys');"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -244,7 +237,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.5"
+   "version": "3.7.5"
   }
  },
  "nbformat": 4,

03_01_autoencoder_train.ipynb

@@ -153,27 +153,13 @@
     "    , initial_epoch = INITIAL_EPOCH\n",
     ")"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "gdl_code",
+   "display_name": "gdl_code_2",
    "language": "python",
-   "name": "gdl_code"
+   "name": "gdl_code_2"
   },
   "language_info": {
    "codemirror_mode": {
@@ -185,7 +171,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.5"
+   "version": "3.7.3"
   }
  },
  "nbformat": 4,

03_02_autoencoder_analysis.ipynb

@@ -277,7 +277,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.5"
+   "version": "3.7.5"
   }
  },
  "nbformat": 4,

03_03_vae_digits_train.ipynb

@@ -14,6 +14,16 @@
     "## imports"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -86,6 +96,7 @@
     "    , decoder_conv_t_kernel_size = [3,3,3,3]\n",
     "    , decoder_conv_t_strides = [1,2,2,1]\n",
     "    , z_dim = 2\n",
+    "    , r_loss_factor = 1000\n",
     ")\n",
     "\n",
     "if mode == 'build':\n",
@@ -125,8 +136,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "LEARNING_RATE = 0.0005\n",
-    "R_LOSS_FACTOR = 1000"
+    "LEARNING_RATE = 0.0005"
    ]
   },
   {
@@ -135,7 +145,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "vae.compile(LEARNING_RATE, R_LOSS_FACTOR)"
+    "vae.compile(LEARNING_RATE)"
    ]
   },
   {
@@ -153,7 +163,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "scrolled": false
+   },
    "outputs": [],
    "source": [
     "vae.train(     \n",
@@ -190,9 +202,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.5"
+   "version": "3.7.5"
   }
  },
  "nbformat": 4,
  "nbformat_minor": 2
-}
+}

03_04_vae_digits_analysis.ipynb

@@ -14,6 +14,16 @@
     "## imports"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -93,7 +103,7 @@
     "example_idx = np.random.choice(range(len(x_test)), n_to_show)\n",
     "example_images = x_test[example_idx]\n",
     "\n",
-    "z_points = vae.encoder.predict(example_images)\n",
+    "_,_,z_points = vae.encoder.predict(example_images)\n",
     "\n",
     "reconst_images = vae.decoder.predict(z_points)\n",
     "\n",
@@ -135,7 +145,7 @@
     "example_images = x_test[example_idx]\n",
     "example_labels = y_test[example_idx]\n",
     "\n",
-    "z_points = vae.encoder.predict(example_images)\n",
+    "_,_,z_points = vae.encoder.predict(example_images)\n",
     "\n",
     "min_x = min(z_points[:, 0])\n",
     "max_x = max(z_points[:, 0])\n",
@@ -204,7 +214,7 @@
     "example_images = x_test[example_idx]\n",
     "example_labels = y_test[example_idx]\n",
     "\n",
-    "z_points = vae.encoder.predict(example_images)\n",
+    "_,_,z_points = vae.encoder.predict(example_images)\n",
     "p_points = norm.cdf(z_points)\n",
     "\n",
     "fig = plt.figure(figsize=(fig_width, fig_height))\n",
@@ -237,7 +247,7 @@
     "example_images = x_test[example_idx]\n",
     "example_labels = y_test[example_idx]\n",
     "\n",
-    "z_points = vae.encoder.predict(example_images)\n",
+    "_,_,z_points = vae.encoder.predict(example_images)\n",
     "\n",
     "plt.figure(figsize=(5, 5))\n",
     "plt.scatter(z_points[:, 0] , z_points[:, 1] , cmap='rainbow' , c= example_labels\n",
@@ -287,7 +297,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.5"
+   "version": "3.7.5"
   }
  },
  "nbformat": 4,