diff --git a/notebooks/wut-web-alpha.ipynb b/notebooks/wut-web-alpha.ipynb
index 74d0dec..b5033a8 100644
--- a/notebooks/wut-web-alpha.ipynb
+++ b/notebooks/wut-web-alpha.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -31,13 +31,13 @@
     "from IPython.display import display, Image\n",
     "from IPython.utils import text\n",
     "from PIL import Image as im\n",
-    "from tensorflow.python.keras.models import load_model\n",
-    "from tensorflow.python.keras.preprocessing.image import ImageDataGenerator"
+    "from keras.models import load_model\n",
+    "from keras.preprocessing.image import ImageDataGenerator"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -47,24 +47,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<H1><B>wut? ALPHA DEVELOPMENT VERSION<B></H1>\n",
-       "Main site: <A HREF=\"https://wut.spacecruft.org/\">wut.spacecruft.org</A><BR>\n",
-       "Test site: <A HREF=\"https://wut-beta.spacecruft.org/\">wut-beta.spacecruft.org</A>\n"
-      ],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "%%HTML\n",
     "<H1><B>wut? ALPHA DEVELOPMENT VERSION<B></H1>\n",
@@ -74,7 +59,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -89,7 +74,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -100,7 +85,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -109,7 +94,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -127,7 +112,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -138,7 +123,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -157,7 +142,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -174,7 +159,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -192,7 +177,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -205,7 +190,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -216,7 +201,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -263,7 +248,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -276,7 +261,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -290,45 +275,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<IPython.core.display.Image object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "head_pic()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "wut? --- What U Think? SatNOGS Observation AI development version.\n",
-      "Source Code: https://spacecruft.org/spacecruft/satnogs-wut\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "site_intro()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -340,7 +305,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -349,31 +314,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Enter an Observation ID between 1292461 and 1470525\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a4fc1c396e4449ec8123d94828a5dfe3",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "interactive(children=(IntText(value=1307433, description=' '), Checkbox(value=True, description='showwater'), …"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "display_main()"
    ]
diff --git a/notebooks/wut-web-beta.ipynb b/notebooks/wut-web-beta.ipynb
index de346a2..ed6b173 100644
--- a/notebooks/wut-web-beta.ipynb
+++ b/notebooks/wut-web-beta.ipynb
@@ -26,8 +26,8 @@
     "from IPython.display import display, Image\n",
     "from IPython.utils import text\n",
     "from PIL import Image as im\n",
-    "from tensorflow.python.keras.models import load_model\n",
-    "from tensorflow.python.keras.preprocessing.image import ImageDataGenerator"
+    "from keras.models import load_model\n",
+    "from keras.preprocessing.image import ImageDataGenerator"
    ]
   },
   {
diff --git a/notebooks/wut-web.ipynb b/notebooks/wut-web.ipynb
index 3660b3e..29b4143 100644
--- a/notebooks/wut-web.ipynb
+++ b/notebooks/wut-web.ipynb
@@ -19,8 +19,8 @@
     "import tensorflow as tf\n",
     "from IPython.display import display, Image\n",
     "from IPython.utils import text\n",
-    "from tensorflow.python.keras.models import load_model\n",
-    "from tensorflow.python.keras.preprocessing.image import ImageDataGenerator\n",
+    "from keras.models import load_model\n",
+    "from keras.preprocessing.image import ImageDataGenerator\n",
     "\n",
     "display(Image(filename='/srv/satnogs/satnogs-wut/pics/spacecruft-bk.png'))"
    ]
diff --git a/notebooks/wut.ipynb b/notebooks/wut.ipynb
index 7c7ab4d..845f1fb 100644
--- a/notebooks/wut.ipynb
+++ b/notebooks/wut.ipynb
@@ -78,7 +78,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import tensorflow.python.keras"
+    "import keras"
    ]
   },
   {
@@ -87,34 +87,18 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from tensorflow.python.keras import Sequential\n",
-    "from tensorflow.python.keras.layers import Activation, Dropout, Flatten, Dense\n",
-    "from tensorflow.python.keras.preprocessing.image import ImageDataGenerator\n",
-    "from tensorflow.python.keras.layers import Convolution2D, MaxPooling2D, ZeroPadding2D\n",
-    "from tensorflow.python.keras import optimizers\n",
-    "from tensorflow.python.keras.preprocessing import image\n",
-    "from tensorflow.python.keras.models import load_model\n",
-    "from tensorflow.python.keras.preprocessing.image import load_img\n",
-    "from tensorflow.python.keras.preprocessing.image import img_to_array"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from tensorflow.python.keras.models import Model\n",
-    "from tensorflow.python.keras.layers import Input, concatenate"
+    "from keras import Sequential\n",
+    "from keras.layers import Activation, Dropout, Flatten, Dense\n",
+    "from keras.preprocessing.image import ImageDataGenerator\n",
+    "from keras.layers import Convolution2D, MaxPooling2D, ZeroPadding2D\n",
+    "from keras import optimizers\n",
+    "from keras.preprocessing import image\n",
+    "from keras.models import load_model\n",
+    "#from keras.preprocessing.image import load_img\n",
+    "#from keras.preprocessing.image import img_to_array\n",
+    "from keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D\n",
+    "from keras.models import Model\n",
+    "from keras.layers import Input, concatenate"
    ]
   },
   {