diff --git a/06_TransferLearning_Cheetahs.ipynb b/06_TransferLearning_Cheetahs.ipynb
index 0b666b3352a4f48c9cdf31e560af82828ed14167..f020d03269f1392896c93e44e9c7c3ac5f33ae20 100644
--- a/06_TransferLearning_Cheetahs.ipynb
+++ b/06_TransferLearning_Cheetahs.ipynb
@@ -6,7 +6,7 @@
    "source": [
     "# Übung 6: Transfer learning\n",
     "\n",
-    "Gruppe 2: Albrecht Oster, Linus Helfmann"
+    "Gruppe 2: Albrecht Oster, Linus Helfmann\n"
    ]
   },
   {
@@ -36,12 +36,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T20:52:44.530667Z",
-     "start_time": "2018-04-15T20:52:41.160191Z"
-    }
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stderr",
@@ -75,12 +70,7 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T20:52:44.537661Z",
-     "start_time": "2018-04-15T20:52:44.532660Z"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "EPOCHEN=3\n",
@@ -92,12 +82,7 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T20:53:01.019333Z",
-     "start_time": "2018-04-15T20:52:44.540663Z"
-    }
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -150,12 +135,7 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T20:53:01.173303Z",
-     "start_time": "2018-04-15T20:53:01.022281Z"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "model = Sequential()\n",
@@ -177,19 +157,15 @@
     "model.add(Flatten())\n",
     "model.add(Dense(1000, activation='relu'))\n",
     "model.add(Dense(3, activation='softmax'))\n",
-    "model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])\n",
+    "model.compile(optimizer='rmsprop', loss='categorical_crossentropy', \\\n",
+    "                          metrics=['accuracy'])\n",
     "#model.summary()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T21:00:02.052086Z",
-     "start_time": "2018-04-15T20:53:01.176284Z"
-    }
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -218,12 +194,7 @@
   {
    "cell_type": "code",
    "execution_count": 6,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T21:00:02.061113Z",
-     "start_time": "2018-04-15T21:00:02.055090Z"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "def classes2BinaryForROC(array):\n",
@@ -236,18 +207,14 @@
     "    print(cm)\n",
     "    print(\"Accuracy:\",(cm[0,0]+cm[1,1]+cm[2,2])/(cm.sum()))\n",
     "    \n",
-    "    print(\"ROC AUC\",roc_auc_score(classes2BinaryForROC(val),classes2BinaryForROC(predict)))"
+    "    print(\"ROC AUC\",roc_auc_score(classes2BinaryForROC(val), \\\n",
+    "                                  classes2BinaryForROC(predict)))"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 7,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T21:00:16.126793Z",
-     "start_time": "2018-04-15T21:00:02.064089Z"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "predict = model.predict_generator(val_gen)"
@@ -256,12 +223,7 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T21:00:16.147780Z",
-     "start_time": "2018-04-15T21:00:16.129771Z"
-    }
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -296,12 +258,7 @@
   {
    "cell_type": "code",
    "execution_count": 9,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T21:00:26.832784Z",
-     "start_time": "2018-04-15T21:00:16.150772Z"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "from keras.applications.inception_v3 import InceptionV3\n",
@@ -313,7 +270,8 @@
     "modelInceptionV3 = InceptionV3(weights='imagenet', include_top=True)\n",
     "\n",
     "# compile the model\n",
-    "modelInceptionV3.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])"
+    "modelInceptionV3.compile(optimizer='rmsprop', loss='categorical_crossentropy', \\\n",
+    "                                 metrics=['accuracy'])"
    ]
   },
   {
@@ -326,12 +284,7 @@
   {
    "cell_type": "code",
    "execution_count": 10,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T21:00:42.810125Z",
-     "start_time": "2018-04-15T21:00:26.834774Z"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "predict_original = modelInceptionV3.predict_generator(val_gen)"
@@ -340,12 +293,7 @@
   {
    "cell_type": "code",
    "execution_count": 11,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T21:00:42.826126Z",
-     "start_time": "2018-04-15T21:00:42.813125Z"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "predict_labels = np.argmax(predict_original, axis=1)\n",
@@ -368,12 +316,7 @@
   {
    "cell_type": "code",
    "execution_count": 12,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T21:00:42.843126Z",
-     "start_time": "2018-04-15T21:00:42.829128Z"
-    }
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -407,12 +350,7 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T21:00:56.296178Z",
-     "start_time": "2018-04-15T21:00:42.847126Z"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "from keras.applications.inception_v3 import InceptionV3\n",
@@ -437,18 +375,14 @@
     "    layer.trainable = False\n",
     "\n",
     "# compile the model (should be done *after* setting layers to non-trainable)\n",
-    "model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])"
+    "model.compile(optimizer='rmsprop', loss='categorical_crossentropy', \\\n",
+    "                              metrics=['accuracy'])"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 14,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T21:07:49.981356Z",
-     "start_time": "2018-04-15T21:00:56.298161Z"
-    }
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -488,12 +422,7 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T21:08:04.433674Z",
-     "start_time": "2018-04-15T21:07:49.984359Z"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "predict = model.predict_generator(val_gen)"
@@ -502,12 +431,7 @@
   {
    "cell_type": "code",
    "execution_count": 16,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2018-04-15T21:08:04.449677Z",
-     "start_time": "2018-04-15T21:08:04.437678Z"
-    }
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -582,10 +506,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.5"
+   "version": "3.6.4"
   },
   "toc": {
-   "base_numbering": 1,
    "nav_menu": {},
    "number_sections": true,
    "sideBar": true,
diff --git a/06_TransferLearning_Cheetahs.pdf b/06_TransferLearning_Cheetahs.pdf
new file mode 100644
index 0000000000000000000000000000000000000000..ee4b5b295e807d3f34448c7ea542b196fdd1215d
Binary files /dev/null and b/06_TransferLearning_Cheetahs.pdf differ