From c134060571c8cf0b8ef0ff691165d060dbefca57 Mon Sep 17 00:00:00 2001
From: Jean-Luc Parouty <Jean-Luc.Parouty@grenoble-inp.fr>
Date: Wed, 19 Feb 2020 22:50:09 +0100
Subject: [PATCH] Update notebook layout and README index

---
 GTSRB/99-Scripts-Tensorboard.ipynb       |  54 ++++--
 IMDB/01-Embedding-Keras.ipynb            | 207 ++++++++++++-----------
 IMDB/02-Prediction.ipynb                 | 140 ++++++++++-----
 IMDB/03-LSTM-Keras.ipynb                 |  28 +--
 LinearReg/01-Linear-Regression.ipynb     |   8 +-
 LinearReg/02-Gradient-descent.ipynb      |   9 +-
 LinearReg/03-Polynomial-Regression.ipynb |  10 +-
 LinearReg/04-Logistic-Regression.ipynb   |  14 +-
 README.md                                |  37 +++-
 fidle/pwk.py                             |   2 +-
 10 files changed, 327 insertions(+), 182 deletions(-)

diff --git a/GTSRB/99-Scripts-Tensorboard.ipynb b/GTSRB/99-Scripts-Tensorboard.ipynb
index 5fb722b..fbee18e 100644
--- a/GTSRB/99-Scripts-Tensorboard.ipynb
+++ b/GTSRB/99-Scripts-Tensorboard.ipynb
@@ -4,18 +4,40 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Running Tensorboard from Jupyter lab\n",
-    "====================================\n",
-    "---\n",
-    "Introduction au Deep Learning  (IDLE) - S. Arias, E. Maldonado, JL. Parouty - CNRS/SARI/DEVLOG - 2020  \n",
-    "Vesion : 1.0"
+    "![Fidle](../fidle/img/00-Fidle-header-01.png)\n",
+    "\n",
+    "# <!-- TITLE --> Tensorboard with/from Jupyter \n",
+    "<!-- DESC --> 4 ways to use Tensorboard from the Jupyter environment\n",
+    "<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
+    "\n",
+    "## Objectives :\n",
+    "  - Using Tensorboard\n",
+    "  - ...and if possible, simply and easily !\n",
+    "  \n",
+    "About [Tensorboard](https://www.tensorflow.org/tensorboard/get_started)\n",
+    "\n",
+    "## What we're going to do :\n",
+    " - Using Tensorboard"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Option 1  - From Jupyter\n",
+    "It's the easiest and most fun way: Launch Tensorboard directly from Jupiter.  \n",
+    "Unfortunately, this feature seems to be a bit capricious with the recent versions of Jupyter...  \n",
+    "It works on Jean-Zay (at **IDRIS**), but on Jupyter Notebook."
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## 1/ Méthode 1 : Shell command"
+    "## Option 2 - Shell command\n",
+    "That's what we're going to use in **GRICAD.**  \n",
+    "In fact, this is like starting tensorboard from the command line.  \n",
+    "More about it : `tensorboard --help`"
    ]
   },
   {
@@ -52,7 +74,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Méthode 2 : Magic command\n",
+    "## Option 3 - Magic command\n",
     "**Start**"
    ]
   },
@@ -65,6 +87,13 @@
     "%load_ext tensorboard"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "For example for use on a GRICAD cluster :"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -81,7 +110,7 @@
     "**Stop**  \n",
     "No way... use bash method\n",
     "\n",
-    "## Methode 3  : Tensorboard module\n",
+    "## Option 4 - Tensorboard as a module\n",
     "\n",
     "**Start**"
    ]
@@ -146,11 +175,12 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "source": [
+    "---\n",
+    "![](../fidle/img/00-Fidle-logo-01_s.png)"
+   ]
   }
  ],
  "metadata": {
diff --git a/IMDB/01-Embedding-Keras.ipynb b/IMDB/01-Embedding-Keras.ipynb
index dd2cb00..ad3c1f5 100644
--- a/IMDB/01-Embedding-Keras.ipynb
+++ b/IMDB/01-Embedding-Keras.ipynb
@@ -4,20 +4,21 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Text Embedding - IMDB dataset\n",
-    "=============================\n",
-    "---\n",
-    "Formation Introduction au Deep Learning  (FIDLE) - S. Arias, E. Maldonado, JL. Parouty - CNRS/SARI/DEVLOG - 2020  \n",
+    "![Fidle](../fidle/img/00-Fidle-header-01.png)\n",
     "\n",
-    "## Text classification using **Text embedding** :\n",
+    "# <!-- TITLE --> Text embedding with IMDB\n",
+    "<!-- DESC --> A very classical example of word embedding for text classification (sentiment analysis)\n",
+    "<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
     "\n",
-    "The objective is to guess whether film reviews are **positive or negative** based on the analysis of the text. \n",
+    "## Objectives :\n",
+    " - The objective is to guess whether film reviews are **positive or negative** based on the analysis of the text. \n",
+    " - Understand the management of **textual data** and **sentiment analysis**\n",
     "\n",
     "Original dataset can be find **[there](http://ai.stanford.edu/~amaas/data/sentiment/)**  \n",
     "Note that [IMDb.com](https://imdb.com) offers several easy-to-use [datasets](https://www.imdb.com/interfaces/)  \n",
     "For simplicity's sake, we'll use the dataset directly [embedded in Keras](https://www.tensorflow.org/api_docs/python/tf/keras/datasets)\n",
     "\n",
-    "What we're going to do:\n",
+    "## What we're going to do :\n",
     "\n",
     " - Retrieve data\n",
     " - Preparing the data\n",
@@ -35,7 +36,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -78,8 +79,8 @@
      "text": [
       "\n",
       "FIDLE 2020 - Practical Work Module\n",
-      "Version              : 0.2.8\n",
-      "Run time             : Friday 14 February 2020, 17:09:29\n",
+      "Version              : 0.2.9\n",
+      "Run time             : Wednesday 19 February 2020, 22:04:33\n",
       "TensorFlow version   : 2.0.0\n",
       "Keras version        : 2.2.4-tf\n"
      ]
@@ -94,7 +95,7 @@
     "\n",
     "import matplotlib.pyplot as plt\n",
     "import matplotlib\n",
-    "# import seaborn as sns\n",
+    "import seaborn as sns\n",
     "\n",
     "import os,sys,h5py,json\n",
     "\n",
@@ -141,7 +142,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -160,7 +161,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -196,7 +197,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -224,7 +225,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -259,27 +260,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
-    {
-     "ename": "NameError",
-     "evalue": "name 'sns' is not defined",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-10-b7cb31218cd1>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfigure\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfigsize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m12\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m6\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0max\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msns\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdistplot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mx_train\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mbins\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m60\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      3\u001b[0m \u001b[0max\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset_title\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Distribution of reviews by size'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mxlabel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Review's sizes\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mylabel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Density'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mNameError\u001b[0m: name 'sns' is not defined"
-     ]
-    },
     {
      "data": {
+      "image/png": "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\n",
       "text/plain": [
-       "<Figure size 864x432 with 0 Axes>"
+       "<Figure size 864x432 with 1 Axes>"
       ]
      },
-     "metadata": {},
+     "metadata": {
+      "needs_background": "light"
+     },
      "output_type": "display_data"
     }
    ],
@@ -305,7 +298,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -367,7 +360,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -417,7 +410,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -447,7 +440,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -488,7 +481,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -506,7 +499,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -515,67 +508,67 @@
      "text": [
       "Train on 25000 samples, validate on 25000 samples\n",
       "Epoch 1/30\n",
-      "25000/25000 [==============================] - 2s 78us/sample - loss: 0.6901 - accuracy: 0.5984 - val_loss: 0.6838 - val_accuracy: 0.7333\n",
+      "25000/25000 [==============================] - 2s 60us/sample - loss: 0.6883 - accuracy: 0.6220 - val_loss: 0.6783 - val_accuracy: 0.7303\n",
       "Epoch 2/30\n",
-      "25000/25000 [==============================] - 1s 35us/sample - loss: 0.6646 - accuracy: 0.7538 - val_loss: 0.6378 - val_accuracy: 0.7683\n",
+      "25000/25000 [==============================] - 1s 32us/sample - loss: 0.6511 - accuracy: 0.7672 - val_loss: 0.6162 - val_accuracy: 0.7666\n",
       "Epoch 3/30\n",
-      "25000/25000 [==============================] - 1s 35us/sample - loss: 0.5878 - accuracy: 0.7973 - val_loss: 0.5433 - val_accuracy: 0.7966\n",
+      "25000/25000 [==============================] - 1s 30us/sample - loss: 0.5571 - accuracy: 0.8088 - val_loss: 0.5094 - val_accuracy: 0.8194\n",
       "Epoch 4/30\n",
-      "25000/25000 [==============================] - 1s 35us/sample - loss: 0.4778 - accuracy: 0.8386 - val_loss: 0.4481 - val_accuracy: 0.8300\n",
+      "25000/25000 [==============================] - 1s 30us/sample - loss: 0.4412 - accuracy: 0.8528 - val_loss: 0.4150 - val_accuracy: 0.8494\n",
       "Epoch 5/30\n",
-      "25000/25000 [==============================] - 1s 35us/sample - loss: 0.3860 - accuracy: 0.8691 - val_loss: 0.3815 - val_accuracy: 0.8550\n",
+      "25000/25000 [==============================] - 1s 30us/sample - loss: 0.3553 - accuracy: 0.8767 - val_loss: 0.3595 - val_accuracy: 0.8604\n",
       "Epoch 6/30\n",
-      "25000/25000 [==============================] - 1s 35us/sample - loss: 0.3264 - accuracy: 0.8856 - val_loss: 0.3439 - val_accuracy: 0.8643\n",
+      "25000/25000 [==============================] - 1s 30us/sample - loss: 0.3036 - accuracy: 0.8907 - val_loss: 0.3316 - val_accuracy: 0.8660\n",
       "Epoch 7/30\n",
-      "25000/25000 [==============================] - 1s 35us/sample - loss: 0.2883 - accuracy: 0.8956 - val_loss: 0.3223 - val_accuracy: 0.8695\n",
+      "25000/25000 [==============================] - 1s 30us/sample - loss: 0.2684 - accuracy: 0.9020 - val_loss: 0.3108 - val_accuracy: 0.8733\n",
       "Epoch 8/30\n",
-      "25000/25000 [==============================] - 1s 35us/sample - loss: 0.2602 - accuracy: 0.9052 - val_loss: 0.3083 - val_accuracy: 0.8748\n",
+      "25000/25000 [==============================] - 1s 31us/sample - loss: 0.2427 - accuracy: 0.9120 - val_loss: 0.2999 - val_accuracy: 0.8774\n",
       "Epoch 9/30\n",
-      "25000/25000 [==============================] - 1s 35us/sample - loss: 0.2388 - accuracy: 0.9122 - val_loss: 0.2981 - val_accuracy: 0.8770\n",
+      "25000/25000 [==============================] - 1s 30us/sample - loss: 0.2222 - accuracy: 0.9196 - val_loss: 0.2923 - val_accuracy: 0.8798\n",
       "Epoch 10/30\n",
-      "25000/25000 [==============================] - 1s 35us/sample - loss: 0.2201 - accuracy: 0.9197 - val_loss: 0.2928 - val_accuracy: 0.8791\n",
+      "25000/25000 [==============================] - 1s 30us/sample - loss: 0.2055 - accuracy: 0.9262 - val_loss: 0.2885 - val_accuracy: 0.8817\n",
       "Epoch 11/30\n",
-      "25000/25000 [==============================] - 1s 35us/sample - loss: 0.2050 - accuracy: 0.9261 - val_loss: 0.2898 - val_accuracy: 0.8809\n",
+      "25000/25000 [==============================] - 1s 31us/sample - loss: 0.1915 - accuracy: 0.9321 - val_loss: 0.2871 - val_accuracy: 0.8819\n",
       "Epoch 12/30\n",
-      "25000/25000 [==============================] - 1s 35us/sample - loss: 0.1917 - accuracy: 0.9308 - val_loss: 0.2872 - val_accuracy: 0.8823\n",
+      "25000/25000 [==============================] - 1s 32us/sample - loss: 0.1795 - accuracy: 0.9364 - val_loss: 0.2869 - val_accuracy: 0.8825\n",
       "Epoch 13/30\n",
-      "25000/25000 [==============================] - 1s 34us/sample - loss: 0.1799 - accuracy: 0.9356 - val_loss: 0.2903 - val_accuracy: 0.8799\n",
+      "25000/25000 [==============================] - 1s 30us/sample - loss: 0.1680 - accuracy: 0.9418 - val_loss: 0.2893 - val_accuracy: 0.8824\n",
       "Epoch 14/30\n",
-      "25000/25000 [==============================] - 1s 34us/sample - loss: 0.1699 - accuracy: 0.9405 - val_loss: 0.2890 - val_accuracy: 0.8824\n",
+      "25000/25000 [==============================] - 1s 31us/sample - loss: 0.1581 - accuracy: 0.9454 - val_loss: 0.2915 - val_accuracy: 0.8830\n",
       "Epoch 15/30\n",
-      "25000/25000 [==============================] - 1s 35us/sample - loss: 0.1599 - accuracy: 0.9455 - val_loss: 0.2925 - val_accuracy: 0.8820\n",
+      "25000/25000 [==============================] - 1s 31us/sample - loss: 0.1490 - accuracy: 0.9498 - val_loss: 0.2970 - val_accuracy: 0.8810\n",
       "Epoch 16/30\n",
-      "25000/25000 [==============================] - 1s 34us/sample - loss: 0.1517 - accuracy: 0.9484 - val_loss: 0.2953 - val_accuracy: 0.8816\n",
+      "25000/25000 [==============================] - 1s 30us/sample - loss: 0.1411 - accuracy: 0.9530 - val_loss: 0.3006 - val_accuracy: 0.8815\n",
       "Epoch 17/30\n",
-      "25000/25000 [==============================] - 1s 34us/sample - loss: 0.1436 - accuracy: 0.9517 - val_loss: 0.2996 - val_accuracy: 0.8817\n",
+      "25000/25000 [==============================] - 1s 29us/sample - loss: 0.1341 - accuracy: 0.9556 - val_loss: 0.3075 - val_accuracy: 0.8798\n",
       "Epoch 18/30\n",
-      "25000/25000 [==============================] - 1s 34us/sample - loss: 0.1366 - accuracy: 0.9546 - val_loss: 0.3053 - val_accuracy: 0.8790\n",
+      "25000/25000 [==============================] - 1s 29us/sample - loss: 0.1273 - accuracy: 0.9588 - val_loss: 0.3131 - val_accuracy: 0.8793\n",
       "Epoch 19/30\n",
-      "25000/25000 [==============================] - 1s 34us/sample - loss: 0.1299 - accuracy: 0.9575 - val_loss: 0.3104 - val_accuracy: 0.8798\n",
+      "25000/25000 [==============================] - 1s 29us/sample - loss: 0.1206 - accuracy: 0.9608 - val_loss: 0.3199 - val_accuracy: 0.8774\n",
       "Epoch 20/30\n",
-      "25000/25000 [==============================] - 1s 34us/sample - loss: 0.1246 - accuracy: 0.9589 - val_loss: 0.3181 - val_accuracy: 0.8756\n",
+      "25000/25000 [==============================] - 1s 29us/sample - loss: 0.1151 - accuracy: 0.9630 - val_loss: 0.3319 - val_accuracy: 0.8722\n",
       "Epoch 21/30\n",
-      "25000/25000 [==============================] - 1s 34us/sample - loss: 0.1180 - accuracy: 0.9617 - val_loss: 0.3233 - val_accuracy: 0.8760\n",
+      "25000/25000 [==============================] - 1s 29us/sample - loss: 0.1097 - accuracy: 0.9658 - val_loss: 0.3357 - val_accuracy: 0.8744\n",
       "Epoch 22/30\n",
-      "25000/25000 [==============================] - 1s 34us/sample - loss: 0.1131 - accuracy: 0.9644 - val_loss: 0.3305 - val_accuracy: 0.8750\n",
+      "25000/25000 [==============================] - 1s 30us/sample - loss: 0.1043 - accuracy: 0.9688 - val_loss: 0.3439 - val_accuracy: 0.8734\n",
       "Epoch 23/30\n",
-      "25000/25000 [==============================] - 1s 34us/sample - loss: 0.1075 - accuracy: 0.9668 - val_loss: 0.3379 - val_accuracy: 0.8745\n",
+      "25000/25000 [==============================] - 1s 32us/sample - loss: 0.0986 - accuracy: 0.9708 - val_loss: 0.3530 - val_accuracy: 0.8728\n",
       "Epoch 24/30\n",
-      "25000/25000 [==============================] - 1s 34us/sample - loss: 0.1029 - accuracy: 0.9684 - val_loss: 0.3462 - val_accuracy: 0.8723\n",
+      "25000/25000 [==============================] - 1s 31us/sample - loss: 0.0941 - accuracy: 0.9735 - val_loss: 0.3614 - val_accuracy: 0.8696\n",
       "Epoch 25/30\n",
-      "25000/25000 [==============================] - 1s 35us/sample - loss: 0.0976 - accuracy: 0.9711 - val_loss: 0.3564 - val_accuracy: 0.8726\n",
+      "25000/25000 [==============================] - 1s 32us/sample - loss: 0.0897 - accuracy: 0.9749 - val_loss: 0.3718 - val_accuracy: 0.8703\n",
       "Epoch 26/30\n",
-      "25000/25000 [==============================] - 1s 34us/sample - loss: 0.0940 - accuracy: 0.9728 - val_loss: 0.3627 - val_accuracy: 0.8716\n",
+      "25000/25000 [==============================] - 1s 29us/sample - loss: 0.0854 - accuracy: 0.9768 - val_loss: 0.3822 - val_accuracy: 0.8676\n",
       "Epoch 27/30\n",
-      "25000/25000 [==============================] - 1s 34us/sample - loss: 0.0893 - accuracy: 0.9750 - val_loss: 0.3719 - val_accuracy: 0.8695\n",
+      "25000/25000 [==============================] - 1s 29us/sample - loss: 0.0811 - accuracy: 0.9785 - val_loss: 0.3919 - val_accuracy: 0.8668\n",
       "Epoch 28/30\n",
-      "25000/25000 [==============================] - 1s 35us/sample - loss: 0.0852 - accuracy: 0.9763 - val_loss: 0.3814 - val_accuracy: 0.8692\n",
+      "25000/25000 [==============================] - 1s 30us/sample - loss: 0.0779 - accuracy: 0.9789 - val_loss: 0.4036 - val_accuracy: 0.8651\n",
       "Epoch 29/30\n",
-      "25000/25000 [==============================] - 1s 35us/sample - loss: 0.0816 - accuracy: 0.9778 - val_loss: 0.3910 - val_accuracy: 0.8682\n",
+      "25000/25000 [==============================] - 1s 30us/sample - loss: 0.0747 - accuracy: 0.9803 - val_loss: 0.4138 - val_accuracy: 0.8640\n",
       "Epoch 30/30\n",
-      "25000/25000 [==============================] - 1s 34us/sample - loss: 0.0783 - accuracy: 0.9795 - val_loss: 0.4004 - val_accuracy: 0.8673\n",
-      "CPU times: user 45.5 s, sys: 2.38 s, total: 47.8 s\n",
-      "Wall time: 27.2 s\n"
+      "25000/25000 [==============================] - 1s 30us/sample - loss: 0.0714 - accuracy: 0.9819 - val_loss: 0.4262 - val_accuracy: 0.8629\n",
+      "CPU times: user 1min 35s, sys: 4.59 s, total: 1min 40s\n",
+      "Wall time: 23.6 s\n"
      ]
     }
    ],
@@ -604,12 +597,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 576x432 with 1 Axes>"
       ]
@@ -621,7 +614,7 @@
     },
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 576x432 with 1 Axes>"
       ]
@@ -645,15 +638,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "x_test / loss      : 0.2872\n",
-      "x_test / accuracy  : 0.8823\n"
+      "x_test / loss      : 0.2869\n",
+      "x_test / accuracy  : 0.8825\n"
      ]
     },
     {
@@ -670,7 +663,7 @@
     },
     {
      "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAaAAAAGoCAYAAAAAZTE0AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8QZhcZAAAgAElEQVR4nOzdd3xb1dnA8d/Vsrz3iLMXmRAChL1nB9BSuigvBVo6KJTuAW3f0pfydpe+dNBSoC0tUKAtUGiZhYRNSEL2Xo7jvWVblrXu+8d1nFi6cuxY0tU9er6fjz9OzpWlE0fSo3POc56j6bqOEEIIkW4OqzsghBAiO0kAEkIIYQkJQEIIISwhAUgIIYQlJAAJIYSwhAQgIYQQlpAAJIQQwhISgIQQQlhCApAQQghLSAASQghhCQlAQgghLCEBSAghhCUkAAkhhLCEBCAhhBCWkAAkhBDCEhKAhBBCWEICkBBCCEtIABJCCGEJCUBCCCEsIQFICCGEJSQACSGEsIQEICGEEJaQACSEEMISEoCEEEJYQgKQEEIIS0gAEkIIYQkJQEIIISwhAUgIIYQlJAAJIYSwhAQgIYQQlpAAJIQQwhISgIQQQlhCApAQQghLuKzugBA25QIqgEogF3AOfbkO+bMT40NeeOgrFPM9DPQBrUB/ersvhPUkAAlhcALlGAGlapTvB/5cluTH7wdaEny1xvzdB+hJfnwh0k7TdXkei6xSBCwCFh/ytRCoBjQL+zUegxiBaD+wEdgArB/63mVhv4QYFwlAQlVeYD4jA81iYLqVnUqD/RiB6NCgtBUIWtkpIcxIABIqKAfOBI7BCDJHA3ORJJsDwhhB6EBAWg+8AzRZ2SkhJAAJO8oDzgDOG/paigXTZ4OhCMFQhHBER9d1dDC+6wz/GR00DTRNQ9M0HEN/dmigOTTcTgc5bicOhyWzf1uAF4DngeVArxWdENlLApCwAxewDCPYnA+cAniS/SDBcIRgKDocWAaHvg60Hfr3YCiS1CwAt8sIRDluJzkeJ95D/jzc7jZu43SmZGAXBt7ECEYvACuH2oRIGQlAIhNpGIkCB0Y4ZwOFybhjXdfpD4Tx+YP0+oP4+kP0+oP0B0JEbfJScDk1ctxOCvM8FOW5Kcr3UJTnoSDXjaYlbSTlA17CCEjPAzuQzDuRZBKARKYoAi4F3g2cC9RM9A4HBo1A4/MH6e0P4fMH6RsIEbFLpBknh6ZRmOemKM8zHJSK8t14PUnZbVHPwWD0HNCZjDsV2U0CkLBSPnAx8FGMwJNzpHfUNxCkrSeArz9ofPlDhCPRZPXT1jwuxyEByUNJvofigiP+VYMxNfcs8BDwBMZmWiHGTQKQSDcvRrD5CHAJRkLBuAWCYdq6B2jrDtDWM0AgGElmH5XncTmoLMkd/srLOeJR0gDwFNAA3IaMjMQ4SAAS6aBhJA5cgxF4isZ7B6FwhPaegBF0egL0DYSS3MXslu91UTUUjCqKc3G7jjjRYQfwG+BXSBKDOAwJQCKVpgJXYQSeueP5wUg0SqdvkLaeAdq6B+jpC8oKeJpoQElhDpUluVQV51JamHMkaeI+4AfA/UBjsvso1CABSCSbB/ggRtA5n3HszwkEIzR29NPc0U9H7yBRRZMF7Mbl1Cgv8lJVksuk8nxyxzddFwWeAe4DnkQqMohDSAASyVIMfBr4IlA71h8Khoyg09DeT0dPQEY5NlBe5GVyZT6Ty/PxuJ3j+dF24PfALzAKrIosJwFITNRk4AvAZxjj2k44EjWCTls/bT0DyFPQnjQN3n3i9CNZLwoA9wI/BfYmu1/CPiQAiSO1CPgqcCXgHssPtHUPsK+1j6aOfmX34mST4nwPZy2pncjm1wjwIPAjYFPSOiZsQwKQGA8Nowbb1zD27xxW/0CIfa191Lf1MTAoSVEqOWlBNTVlMVn0nU1w/61w7Dlw7LlQUjXWu3sCI2nhraR2UmQ0CUBiLJzA+zECz0mHu7Gu6zR1+Nnd5KPDF0h554Q1Lj5lOk5HzPTb8r/C8oeNP2sazDzaCEQLTwHXmMr3vYQRiF5ASv8oTwKQGE0ucDXwFWDO4W4ciUTZ19rHrsYe+gMy2lHZ5Ip8TphnMrq583robI5vLyiBky+BZe+CnDHtPV6NEYgew8ikEwqSACTMOIFrge9jnBQ6qmAowp5mH7ubfARD8l6RDc48ppbSwphyPvu2wH23jP6D3jxY9h44+WLILx7LQ23DWCN6AEnhVo4EIBHrHOAOYMnhbugPhNjZ6GNfS68kFWQRB3DxqTPikw+e+i2senZsd+L2wNLz4dT3jXWdqB64GSNpQZ5sipAAJA6YA/wEY61nVN19g+xs6KGxvV/eCbLQUVOKWTC9bGRjOAQ/+wQMjLMuqcMJR58Jp18GlVPH8hOvAJ8H1o3vgUQmkgAkSoBvAzdxmHTq1i4/Oxp6aO+RxIJsdv7xU8j3xjxVtrwJD//oyO9U02DeiXDG5TD5sFWbosBvge8gxU9tTQJQ9nIBnwL+B6gY7YYN7f1s39+Nr1+m4LNdjtvBRcumxU+//fWHsDVJGdQzjzYC0azDzgJ3ALdgbGqVcug2JAEoO10I/BxjM2lCXb2DbNzTQWfvYHp6JTLektnlzKiJKXgx0As//QREkpz5WDsHzvqQMTIa3RrgRuCN5HZApJoEoOwyH6P8yXtHu9HAYJjNdV3sb5NzxsRI7z5xWnz9t7efhn/dnboHnbUE3n0dVE453C3/BHwTMMkDt4amaWdj7G1KJKLrelKOrLWjrP2HZ5kijKm2Gxjl/zwcibKzoYedDT2S1SbiFOd7zOu+rVuR2gfevQ5++yU46b1w1kcgJzfRLa8GPgDcCvwSyKRDox4C/m3SntX7FiQAqe8sjE+G00e7UX1rH5vrOuVkUZHQgmml8Ws/HY2wf1vqHzwShtefgPUvwwVXwZJzEt2yEPgZcB1Gttx/Ut+5MVmj6/pfxvtDmqYV6rrem+BaLhDSdX3Cc5+jPU4qHfGxhyLjeTGm215ilODT6QuwYl0Da3a0SfARo6oo8cY3rk/x6CdWXxc8difcezM07R7tlgswyvn8jTFspraapmkzNE3TNU27VdO0j2iatlrTtAGMkRyapv1x6Hqlpmn3aZrWAvQDU4auuzRN+4amaZs1TQtomtahadpjmqYdPc7HmTp0/3Wapg1qmtaqadrrmqZdnYp/t4yA1LQU+AuwMNEN/IEwm+s6aWjvT1+vhG1NrsiPr/sGxojECvVb4e6vwfEXwHlXQm5holtejlFA9+PAGHfJpkSepmlm2aZBXdd9h/z9/RhbIu7CSDX3xdz+eYw1rtuAfODAQu0DwIeHrt8F1GBMub+hadoZuq6/E3M/cY+jaZpr6OcnYxyrvh3jnK9jMH6Hfxrnv/mwJACpxQV8A2MO3PT/NhyJsmN/NzsbfXLiqBizOZNNyubs2wJdFq7361Gj8sLm1+HcK41gpJlO6lRhnMr6c4y0bSvSOr839BXrX4ysLL8IOEbX9S0J7mejruv/dWiDpmkXYASfR4CP6kOZZZqmPYyRIXgnRgA5VNzjaJp2DDAP+Iau6z8e6z9sIiQAqWMucD9wcqIbdPQEWLOjDb8ciyDGwYGRgBBn3fJ0d8Wcv9coA7T6OXjPp2Dq/ES3/DJGqakrMGrMpdPdwKMm7W0xf//XKMEHjGn1WJcNfb9dPyStWdf19ZqmPQW8T9O0Sl3XD30ss8fpGfp+jqZpf9R1PeWn1koAsj8NuB6jjI5pmeFIVGfrvi52NvSYXRZiVHOmFMcnH4RDsOk1azqUSNNuoxjqMWfBhdckKna6lIP7hv5I+urK7dB1/YUx3G77EVyfiZFNZxa4NgLvG7rNoQEo7n50Xa/TNO12jJp7TZqmrcVI4nhU1/W3x9D3cZMkBHubjDG18GsSBJ+e/kFeXtcgwUccsenVJusr21dBIAPXD3XdGJnd9UXYtTbRrfKA+zBSo0vS1bUx8o92Udd1s+tHciSt6ePouv5tjNmULwK7MLIJV2qaNoE6S4lJALKvjwIbMKoaxNF1ne313by8rhGfP5O2Qwg7yXE7yM0xmShZvzztfRmXvm74y//Ac3+ESMLn/0eAtcCpaetXauzCeC9fYHLtQCLSnrHema7ru3Vd/6Wu6x8GaoGXga9rmjbm423HSgKQ/eRjZLg9BJSa3aB/IMSrG5rYsq8LyTMQE2G698ffCzvWWNOh8dB1Y+/QPd809iuZm47xBvsdjHOw7Ojxoe83a4f8Z2mathi4FHg1Zv3HlKZpxZqmjagyq+t6gINTe6bvNxMha0D2MhPjyXZMohvsafaxaU+nVDIQSTGpPD++ceOrya/7lkpNu+F3XzESFI491+wWToxKIecBV2GcPZRsx2ma9l8Jrj2eoH1MdF1/XtO0RzBmRUqHEg8OpGEHMNKtx+Ic4G5N0/6OkaTRBxyPMQ33lq7rSU/ckABkH+cDDwNlZhcDwTDv7GyntWsgvb0SyiopSFB6J9On38wEA/D4L2HnO3DxZ8FrEliNqiHrgE9iHAWeTFcMfZmZC0w0ol+JkVxxDUYliH5gBfAdXdc3jPE+1gH/AM4euj8nsA/436H7TDopRpr5NOArGMcSm06ZNrT3sW5XB6FwVpeVEkl28sJqqktjcls6GuGXN1jToWQpqYLLvwxT5412q59iFDaV8iApJGtAmS0PY4fzTzD5v4pEoqzZ3saqbW0SfETSVRRnQOmdVOhuhT98C15+1NjMau6rwN8x1lxFikgAylyTMY4fNh22+wMhXtnQRL0cmSBSIHHpHQUCEEA0Ai8+CH/6LvjaE93qfRivwcnp61h2kQCUmZYCK4HjzC62dQ+wYl0jPXJCqUiRxKV3WtLfmVTauxHu+vJop7mO+loUEyMBKPNcCryKkX8fZ2dDD29saiYoU24iRRKX3hntXDUbG+g1jhR/4c+JblGLMRJ6f/o6lR0kAGUODaNW1eOYVDWIRKKs3t7Kpr2daasdIrLTnKmJSu+8bk2H0uXVf8AjP4aQaa3SPIwMsS+nt1NqkwCUGdwYZdF/hklZjUAwzKsbm9jfloGlT4RypleZld55OzNL7yTb5jfgD9+G3k6zqxrGa/SnyHtnUsgv0Xo5GJ+sPmN2sac/yMvrGunuk/UekXpeT4LSO6k+djuTNO6Ee74BzQmr13wF42wcd6IbiLGRAGQtL8aU28VmF1s6/by6oZEBOalUpMl809I7Pthpg9I7ydTTblTW3r4q0S3+C3gSKEhfp9QjAcg6ecA/gXeZXdzd2MNbW1oIR2TFR6SPeemd1+xVeidZggF46Afw9tOJbnER8CJQmb5OqUUCkDXyMT49XRB7Qdd11u/uYMMeSTYQ6VVa4MHjMqnHqWr221joUfjX3caeIXPLgNcw6jSKcZIAlH4FGMfwxlVF1HWd1dvb2NMUewy8EKk3b5pJseOORmjYkf7OZJqXH4V//sbYwBpvLkbdtWnp7ZT9SQBKr0LgaYyihyNEdZ1V29toaM+CTCORkSqKc+MbM+XY7Uyw5nl4OGGa9lSM00Nr0tspe5MAlD7FwLPA6bEXolGdVdtaaZTgIyxilN4xOVhTldI7ybJtJdx/KwyYlsCaAzwPlKe1TzYmASg9SoDngFNiL0SjOm9va6WpY9STeIVIKdPSO3WbjcKdYqT6rUaGXF+X2dXFwDNAUXo7ZU8SgFKvDHgBODH2QiSqs3JrC82dEnyEdRxaotI7y9PeF9toqx8aCfWaXT0BeAqTiiZiJDkPKLXKMYLPsbEXItEoK7e00totB8jZUY7biddjfOV4nLidDjRNw6GBpmloQ9/BSC7RdeN7dOh7OKITCIYJBCMEghEGQ9bt9Zo3tZj502LOOQwH4afXQkA+HI1q8lz4+Pcgx2T9zJhyfx9gumgk5ETUVKrAWJSMOz47Eony1tZW2iT4ZKSCXDf5Xhdej2s4yBz6Z4/biSN2s+YERXWdYCgyHJAODU6BYJj+QJi+gVBSH/OAaWald7atkuAzFg074MHb4b++A+6c2KsXAQ8CH2HiJ54qSQJQauRi7POJCz7hSJS3trTQ3hNIf69EnIJcN8X5HkoKcigp8FCcn2N+DHWKOTRtKMglfkmGwlF6+gfp7gsOf59oUEpYeseOx25bpW4TPPwjuOJmcMZV5/kAcB/GUdlSwj6GTMElnwN4CPhw7IVwJMqbm1vo8EnwsUKmBJtkmmhQOnZOBdOrY0ZAfh/87JPZWf1gIhacDB/6KjhMNvMaxYZvANlffigZASXfbSQIPm9sbqbTJ9PB6eJ2OagpzaOmLI/KEi9us13+Nud2Oagozh2xhycUjtLWPUBzp5+WLv+oZ0dNKjdZJ9/4alqCzw9e2c6a5m5WN3azp9vP9OJc9n7xItPbPr+rlb9vaWR1UzcbWnwMRqK8dPVpnD1jfFVw3qjv5AevbmdNUzcdA0FqC72cO6OSm884ilmlB8sQtfYP8vmn1/P8rlby3E6uOXYa3zt7QVyq+s/f2MlPX9/JlhvOo3jLm/DEr+CyL5g99PVAL/BNJAgNkwCUXNcCt8Q2RqI6b25ukeCTBvleF5PK86kpzaO0KCfpazV24HY5qK3Ip7Yin6iu0+UbpLnLT3Onf8ToqLQwJ0HpneVp6ectL26mLNfNcZNK6A6MPmp7YEM9D27Yz+KqIhZUFrK2uWfcj/fMzhbe++AbzC7N58YTZ1GR52FTay93r9nL37c0suH6c5lcZATya59Yw+rGbv77rHm09gf50Ws7KPW6+cqpc4fvb293P//90hbuv+x4ir1DU2/rloPHC+81LW7/dYwg9P1xd15REoCS5xzgbrMLa3e2ybRbCpUXeakuy2VSWR4FuSbpxFnMoWmUF3spL/ayaEYZfQNBmjuN0dHcKSZ7f9ob0lZ6Z9dNFwyPOhb/5j/0BROPum4/dyG/u/hYclxOfvr6jiMKQHe8uQunpvH6J8+kIu9gwsCiqkI+9eRaHt3cwBdPnsNAKMIzO1u499KlXHPsdAAaegf4x9amEQHo+n+t44LZVXxgQczhxW8/YwShC64268ZtGEHo/8b9D1CQBKDkmAf8HZPf59Z9XXKQXApUleQypTKfqtI8ctzqTa2lSkGuhzmTPcyZXIzp+m8akw8OnfI6nAMjk4nwDYbwupyUekd+SKkt9AKQ7zZevoORCFEdyg75MFPm9dAfPBj0Hlhfz+v1nWz+3HnmD/ba4+DJhbPiZuMB7gC2YqRpZzUJQBNXgVFcNK6SY31rH9vqu9PfI0W5XQ6mVxcyo7qQ/Fw5C2yi4s79gdHOv7G9i2ZX8eb+Lq5+fDVfO3UuFXkeNrb6+MpzG1lQUchHF08GoMTrYX5FAT99fSfzygto8wd5cON+Lh8a6XT4g3zp2Q388LxFowfGlx4y9gedfEnsFQ0jPfsEIOGpd9lAAtDEHDhQbnbshY6eAGt3tqW/RwoqLchh5qRCasvzcTrtnbWW8a77EWx6zZhG2r/d6t4k1c2nH0Vrf5D73qnjgQ37h9vfM7eahy4/gcKcgx9q7r10KZc/spL5v/4PAMtqS7j17PkAfPm5DcwtL+CzJ8w4/IM+c58xHXdc3MkrZRgnIZ8KZO2GQAlAR04D7gVOi73QNxBi5dYWopLrcsScDo3JlfnMrCmipCBug59IFZcHlpxjfDXtgrefhQ0rIGT/I+GdDo3JhV7On1XJZfMnUZbr4bX6Tn65cjcf/dsqnvjoSbiHPuCcOrWcPV+4kE2tveS5ncyrKMChabywu5W/bmzgnc+cTVSH76/YygMb6tGBjy2ewn+fNT++qOuTv4XiSpgdVxDlWOC3GHuEsvLdQgLQkfsu8LHYxmAowpubm0dNfRWJ5XtdzJxUxNSqAvMMLZE+k2bDpZ+DCz5uZHe9/bRxPpBNXfP4Gl6v72Tj584lb2i957IFtcwpy+f6f63jT+v2cd1xM4Zv73U5Ob62ZPjvA6EIn3lqLTefPpeFlUX86NXt/HLlbu6/7Dg0NK56bDX5HhdfP23uyAfWo/D3n8OnfwolVbHd+jjwFvCbVPybM53MZxyZ/8IIQCNEozort7bSH5ANfONVkOvmxPlVnHfcFGbXFkvwySS5BXDyxfD5X8NHvwmVU63u0bjt6/HzwIb9vHdu9XDwOeBDC421nxV17aPex3eXbyHH6eSWM+YBcO87dXz2hBm8Z24N755bzWdPmMG979SZ/7C/16iWEDYdSf4CYyou60gAGr+TMabe4qzd2S7p1uPk9Tg5dk4F5yydzKTyfPOFcZE55p8E198B77sRiius7s2YNQy9LiMmE13haHToe+JZsHeauvnFm7u4+5Jj8QxN0+33BZh6SBLC1KJc6ntGWc5p2g1P/dbsihv4G1l4mJ0EoPEpwsheidtssq2+m/o200OqhAm3y8GiGWWcf9wUplcXZuWGUdtyOGHpecaI6KJrIdekmKmFegIhtrb30u4/uPF7XkUBTk3j8a1NdAdGjkL+uHYfAMtqTY4kx9hI/qkn1/LJpdM5fdrBs+ZqC71saPUN/31Dq284pTuhtS8ZCR7xJgGPYASjrOG89dZbre6DndyDyXHa+9v62LC7w4Lu2I/ToTF3cjHL5lVRWZKLw+wUTmEPDidMnQcnXGj8uXEXRMd+rMSf1+3jye3NvFzXwUt72/GHIoSjOi/XdVDX7WdJzcGNsutbevj9mjperutgRV07Ozv7cWoaG1p9vFzXwZLqYrxD07Z/3bifC/78Onlu53Cpnly3E99gmOd2t/Lwpgb8oTCb2nr5v7d2ccebu5hdms/vLjE2usa6442dPL+7jcc+ctLwYwB0DgT5v7d2E45EWVHXzv+9tZsbl83i7BmHGRnuXgezlpiNIKdjfMg1jVAqkmKkY/cx4IHYxq7eQV7d2ERUUt5GpWkwvbqQeVNLRq34LGysrwtWPAqrnxtTIDr7j6+wos78g9tZ08tZfs0Zw3//49o6rn3inYT3tecLFzCjJH/Ebb971jxuPXvB8G10XeeeNXXc804dm1qNenKTC728d24Nt549n8r8+GzLPV39LL7rRf5y2fFcFlPxIBiJcvMLm4ZTuj929BR+eP6i4Sm6URWWwWd+BgUlZlevxJhpUZ4EoLGZCawl5pjdcCTKS2sb8EvSwahqy/NYML2MAtk8mh06m+E/fzH2E4nEpi+Cq79nVj17AGOteX36O5VeEoAOzwWswCRLZc32Nln3GUWO28mSOeVMKht7yRWhkG1vw5N3GSMjYe7kS+BdnzC7sgtYBij9y5MkhMP7FibBZ39bnwSfUUypLODcpZMl+GSzecvghv+DJWdb3ZPM9eaTsOEVsyuzgfsxNrwrS0ZAozsVeIWYQO0PhHhpbSPhiGw2jSWjHmFKRkOJuXOMEkjV082uXo0RiJQkASixYox1nxmHNuq6zqsbmujslbN9Yk2pLODomWV4pDq1MDPQa9RGS9N5Q7ZSVmNUSvDGfXDrAhYALenvVOpJAErsLxjZKCNsq+9i6z6pcH0oGfWIcZHRkLl5J8IVN5tdeRSTU5ZVIAHI3JUYAWiETl+AVzc0ZWfVwARk1COOiIyGzH3gi3BM3FZDgA8Aj6W5NyknASjeTGAdMGJ7dygcZfnaBvyDknIN4HJqLJ1bSW25jHrEBGx5Ex6/Ewaz9kSCkfKK4IY7IT/utNomYCGg1PSLZMGN5MIY+cTVFlm/u0OCz5A8r4szjqmV4CMmbsHJxgJ8WdaVQTPn98HT95hdmQT8JM29STkJQCPdSIKU6/2Scg1ARbGXs46ppSgvrhyeEEemcip86scw6xire5IZNr5qrJPFuw5IcAa4PckU3EGTMc5pLzi00Ui5biBsVkY3y8yaVMSiGWVSv02kRjQCz/4R3nrK6p5Yr6jcmIrLyYu9shs4BuhPf6eST0ZAB/2cmOCj6zqrt7dlffDRNFgyu4KjZ5VL8BGp43DCuz8Jl94AziyvF+jrgOdNt//MAv4nzb1JGRkBGS4Eno1t3NPkY32WV7n2uB2cOK+a8uLDlJkXIpn2bTEOcOvvsbon1tE0uPo2mLEo9koUOAVYmf5OJZeMgMAL/Dq2cTAYYUtddu9TKMr3cNYxkyX4iPSbtgA+/ROYNMvqnlhH1+HJ30AobtO7A+NQTNsvxEoAgq8Dc2IbN+3tJJTFpXYmledxxtGTyPNm+VSIsE5xJXzif2HRaVb3xDodjbD8YbMri4Fvprk3SZftU3CzgM3AiINA2nsGeG1jszU9ygAzago5Zla5HI8tMoMehafvhZX/tron1nA44LofQ+3s2CshYCmwKf2dSo5sHwH9hJjgE43qrN+Vves+s2uLWDK7QoKPyByaA97zKTj1/Vb3xBrRKPzzV2aH/LmB32LjitnZHIDOxihvMcKuxh56B0Lp700GOGpKMYtnlh/+hkJY4cKr4cwPWd0LazTvhVdNK/GcDlya3s4kT7YGICfwi9jGQDDMtnqlKl2M2fxppSyYXmZ1N4QY3bkfg3PjagRnh5cfgfb9Zld+iFHFxXayNQBdCyyJbdy8t4tINPvWxBZMK2XeVNOz6YXIPGd+EM6/yupepF84BM/9yezKfIz3NNvJxgBUBNwe29jVO5iVJ5weNbWEoyT4CLs5/QNw9kes7kX6bV8Fe01zDr4H2K44YzYGoG8BVbGNG/dkX+LBnMnFLJhWanU3hDgyZ3/UCETZ5nnTUdAk4K9p7smEZVsAmgx8MbZxf1tf1p1weqCumxC2dv5VcPLFVvcivRp2wKbXza5cDMSVTchk2RaAvkLM7uFIJMrmLKt4MK2qgKNnSbabUMS7PgnHnW91L9Jr4yuJrsQdpJnJbJk5cYQqgM/ENu5q8jGQRef8lBd5WTK7wupuCJFc7/00dDRBnW33ZI5Nea0x9Xj0GYlucSzGkTKmQ6RMk00joC8CI2qbhyNRdjVkT7HD3BwXy+ZVSUVroR6nGz78NSiptLonqVFUDpd8zjiiIXHwOeDOdHQpGbKlFE8xUDf0fdjOhh427e20pkdp5nRonHH0JIoLcg5/YyHsqmUv3HszBANW9yQ58ouNRItl7waXe6w/FcSob1mfuo4lR7aMgD5HTPCJRHV2NWbP6Oe4uZUSfIT6qmfAZUn5vjMAACAASURBVF+wuhcT582Dc66AL9wFp1w6nuADxjr3zSnqWVJlwwgoD9gLjBib72n2ZU3Nt3lTS5gv6dYimyx/GJbbLisZ3Dlw4nvg9Msgt3DUm+q6TmN7PwODYeZMidvLF8IYBe1LUU+TIhuSED5FTPCJ6jo792fH6GdSWZ5UORDZ56wPQWsdbH7D6p6MjdMFx11gVHkoHH17hK7rtHYNsGZHG8FwFLfTwfSaItyuERNabuAW4LMp7PWEqT4CygF2Yez/GVbf2seaHW3W9CiNivLcnHFMLS5ntsy0CnGIYADuu9ko5JmpNAccc5ZR1aG0etSb6rpOhy/A6u1tBIIjK2MnmOUIAzOAhiT2OKlUf2e6ipjgA7Bjv/oFRz0uByctqJbgI7KXxwsfvdlYyM80mgYLT4HP/QIuu2nU4KPrOt19g7z4zn5e29gcF3wAdjX6CIXj2l3Ap5Pa7yRTeQTkArYCI05xamzv5+1trdb0KE004NTFNVQU51rdFSGsV7cZ/vTfZufpWGPOUqOid/wBcyPouk7fQIh3drTR1Rc87N0mGAU1A9MxMuMyjsprQB8mJvgAbM+C0c/cKSUSfIQ4YPpCOONyWPGItf2YtgDOuxKmH75ajj8QYu3Odtp6xp5OXtfSy1FTSmL3+dUAlwGm53pbTdUA5MBYgBuhpctPT39GfhBImqI8tyQdCBHrzA/CtpXWrAfVzDQCz9zjD3vTQDDCht0dNHb0j/thAsEITZ39TK4oiL10AxKA0uoSTIryqT760YClcyul0oEQsZxueP9NcPfX0jcVVzHZ2Muz6LTD3jQUjrBpbyd1LRM7EmZPU69ZADoDOBrYMKE7TwFVA9CNsQ3tPQE6fWpXvJ47pYQS2WwqhLmamemZiiuuNLLalpwNDueoNw1Homzb18XORl9SHrrDF8DXH6Qo3xN76XPA9Ul5kCRSMQlhGsbG0xHDgNc3NdPWPWBJh9KhKM/NWUsmy+hHiNFEQvD7r6dmKq6gxAhwJ1xkjLhG60Y0yu5GX0oq8c+oKTQrONyPkRGcURsgVczR/TgxwadvIKR08JGpNyHG6MBU3GFGJuPizTfWeG66C066eNTgE43q7Gny8dQbdSk7BmZ/Wx+hcDS2OR/jvTGjqDYC0oAdxGS/banrUnr956gpJSyYLqV2hBizlx6a+FScxwsnvRdOu8wIQqPQdZ2G9n7e2dlGNC42JN/Rs8qZNakotnkrsBDImDd91daATicm+Oi6Tn1rr0XdST3JehPiCEwkK87pMqbZzvigMe02Cl3Xae70887OdrNRScrsbfKZBaD5wLnAf9LWkcNQLQBdG9vQ1hNgwGTnsApk6k2II3QkWXEOByw5x0gwKB793KGDZXNaCQTTF3gO6B1adqgsidsPeAMSgFKiAGPz6Qj7WtQd/UjWmxATMNasOE2DhacaKdUVcZW9RjDK5gRZs72VvoC1Jy3vafaZBaD3AVOA/envUTyVAtDlGAttw0LhKE2dfou6k1o5bidzp2RgjSsh7OT0D8CaF6A3wcGUc483EgxqZo56N7qu0zsQYs32tozZ7N7c6WdgMExuzoi3eQfwGeA71vRqJJUCUNz0W0N7H9Foxqy3JdW8aSVSaFSIiXLnGFNqT941sn36IiPwTFsw6o/ruo5/MMzane20j6NsTjroOuxt6WVBfH24TwG3ApavTagSgGYBZ8U27pvgruJMle91Mb1q9MOqhBBjdOy58PoT0NFoFAg990qjYOhhBIJh1u1qp7kzc7d41DX3Mi++Plw1cBrwsjW9OkiVAHR1bEOvP0hXn5qVDxZML5XEAyGSxemCd19nnB+08JTD3jwYMsrm7GvN/A+4g6EILV1+JpXHpYl/AAlASeHAJADZ4clxJIrzPdTGP5mEEBMxhhFPOBJl674udiWpbE66NHWYBqDLgC9h8Z4gFQLQ2RjnXQzTdZ39bWoGoIUzytA0Gf0IkS6RaJSdDT627ktN5YJUa+7yE9V1HCPfN6YBxwGrremVQYUAdE1sQ2vXgOmpgXZXUeylKj6tUgiRAtGozt5mHxv2JMiQs4lQOEp7T8DsveMDWByA7J5G5cX4JY6wT9HKBwunl1ndBSGUd6B6yr/e2mv74HNAk/n5Qpelux+x7B6ATidm708wHMnorJQjVVueR2mhbDoVItXe2dnOmh3taanZli7N5vshFwx9WcbuAehdsQ2tXQNE1SqwigZSbFSINDlqSgmqrbIGghE6fab7lCwdBSkZgFQzpbKAgty4A6aEEClQkOtmSlXcqaK2l6AqjASgIzQVk2O3WxU892fmJNl0KkQ6zayJqyRtewnWgU7AyIizhJ0D0EWxDd19gwyG1Mp+K873UFrotbobQmSV0sIcSgrUmnXoD4Tp6TfdnG/ZKMjOASgrpt9mxp/pIYRIAzVHQZk1DWfXAOQGLohtVG36zeV0MLlCqh4IYYXainzcLru+RZpLMA13BlCV5q4A9g1AJwEjPp6EwlE6ezOrGu1ETasukIrXQljE5XQwTbFkBJ8/RN9AKLbZAVxqQXdsG4Dipt/aegZQLPuamTWSfCCElWYoOQ1nOgq6MN39AIUCkGrrP5XFXkm9FsJiBblus1NFba3F/L3y8GXAU8COAagKOD62sbVLrZNPJflAiMyg2kxEV9+g2UGdUzC2tqSVHQNQ3FDR5w8yoFDxUa/HSXVZntXdEEIA1WV55HqcVncjaaJRPVE69qnp7osdA5Dy028zagpjS6cLISzi0DTl1oI6eyUAHQkHJhtQVZt+mybHbQuRUaZVq5UN1+mTAHQk5gEVhzaEI1E6zH+ZtlRS4CE3R4VjmoRQh9fjorRAnWr0CbasLCXmdIFUs1sAOiG2oat3UKnq1zWy9iNERlJpXTYQjOAfDMc2OzF5j00luwWgZbEN3X3qjH4AakrVeZILoRLVPhwmOJ4hrenYdgtAcdFZpQCU63FSrNAwXwiVFOerNT3elQGJCHYKQG6MOcoRuvqCFnQlNVT7hCWEaiYp9BpNsA50KqTvPD47BaCFwIhzCQZDEQbi5zFtq6ZMCo8KkclU+pDY0x8kHIk7d7wcmJuuPtgpACm9/uNyapQXy7k/QmSy8iIvLqcae/R0PeF7aNqm4ewUgOLK76gUgKpKcnE61HhiC6Eqh0OjSqFEIas3pNopAB0T29Cj1PqPTL8JYQcqTcMlyIQ7LV2Pb5cApAGLYxt7/OoEoOpStSruCqGq6pLc9K3Sp1iCTLj5QFrSce0SgKYScwBdOBLFH1AjAaGsKAePW51ih0KozON2UlakxnptMBwlEIx7H3UAs9Lx+HYJQEfHNvT64071s62yQjWezEJki7JCdfbr9cafkApG2bOUs20A8ik0/VZSIAfPCWEnKm0Y75cAdFhx6z++fnUCUHG+Ok9mIbKBSh8a+8wD0FHpeGy7BCBlR0Aup4OCXLfV3RBCjEO+143bZZe3z9ElCEAyAhqiAXNiG3sVCUAqfZISIpuU5Kvx2pUANLoiYETifSQaZTAUV0LClkoUmksWIpuo8tr1B8JEo3FH2lQApal+bDsEoNrYhkAwYkU/UkJGQELYkyqJCDrgHzQdBc1I9WNLALKYJCAIYU8qfXj0B0zfU6en+nHtEIAmxTaoEoAkAUEI+1IpEcHkdFSQAASYjoDUqICg0icoIbKRKokICY61kQCEwlNwqixiCpGtVHkNyxpQYsoGoKI8NT49CZGtihQZAckUXGLKTsHl5kgBUiHszOtxWd2FpBgwL+wsAQiFR0BejwQgIexMlddwIBhB1+P2ApUDKc2SyvQApKHwCEiVT09CZCtVApAOhCNxAQigIJWPm+kBqJSYg5HCkWiiX5StOB0aLmem//qFEKNxOR24nGocTxeOmFaXyeoAJNNvQoiMpspMRoIAVJjKx5QAZBFVnrRCZDtVPkzKFFw8hdd/1HjSCpHtctxqvJbDURkBxSqPbRgMqTICUuNJK0S2U+W1LGtA8eLmqUzKhttSjiJPWiGynSrT6RHzKbisHgHF/c/Gp6rbk9etxpNWiGwnI6Ajl+kBKO5/VkeNCKTKk1aIbKfKazlBEoKMgA6lygjIo8jCpRDZTpXXsoyA4pkEIDUikEONvWtCZD2HpsaLWfYBxYufglMj/qAp8qQVItup8lKWfUDx4rPgFIlAMgISQg2qjIAisg8ojoyAhBAZTZWXsiQhxFN2DUgCkBBqUOW1HDFfA8pN5WPaLwBZ0YsUUOQ5K0TWU+Wl7DBfFxhI6WOm8s6TQNkpOFVGckJkO1VeyU7z42H8qXzMTA9Ayk7BKfLPECLrqfKe5JQRUBwZAQkhMpoi5SkTBSAZAR1KlTRsVZ60QmQ7VT5MyggoXtxvRJXFe1WetEJkO1Vey06HrAHF6oltcJsvlNlORIZAQijBPHvZfpxOmYKL1RHb4Fak8J8qB+sJke0Gg2q8lmUKLl5nbIPHleldHhtVnrRCZLtAKGx1F5JCkhDixY2APC41RkABCUBCKEGVD5OyBhRP2RFQIKjGpyYhsp0qHyZlCi6eyRpQpnd5bAKyBiSEElT5MClJCPFMRkAyBSeEyByqvJZlBBTPZA0o07s8Nqo8aYXIdqq8lmUNKF5XbINbkQA0qMiwXYhsp8p0eoL31qwOQCHAd2iDpmlKBKGoDkFFnrhCZKtgOEJUkU3luTmmyxv7U/mYdngnVzgTTgKQEHamSgp2jttpNgXnA7pT+bh2eCeXvUBCiIykyms4zxtX9xlgLyk+7sgOAShuBKRKKvaArAMJYWv+QTVew3k5CQNQStnhnVzZEVBP36DVXRBCTEBPf9DqLiSFBKDE4gKQ16NGAOruU+PJK0S26lbkQ+QoU3ApZYcAtDe2Id/8l2U7Pf6gMgfsCZFtorqOT0ZAE2KHALQjtiE/121FP5IuGtXp9Yes7oYQ4gj0+UPKnOslI6DE4gJQgVeNAATqDOGFyDbd/eq8dnNlBJTQbmJSAXNzXInqFtmOJCIIYU+qrOFatQcI7BGAAkBdbGO+IqMgVZ7EQmQbVWYvRln/Sfn8oh0CEJiuA0kighDCGkolIFi0/gM2DkAFkogghLCIUgkIFq3/gH0C0LbYhqI8jxX9SAlVhvJCZAulEhBkBHRYG2MbVApAkogghL2otHZbaD6bFLfungp2CUAbYhsKct1oaiTC0eELWN0FIcQ4qPSaLc7PMWuOe89NBbsEoDag5dAGh0NTZh3I5w/hD8g6kBB24B8MK5OAUJDrNjtfzQfsSsfj2yUAgUlEVmkarrkzpQcPCiGSpEWh12pxvul76Bogmo7HlwCUISQACWEPTQq9VksKTKffVqfr8e0dgMyjty21+wKEwmn50CGEOEKhcJT2ngGru5E0JQWm76ESgEzEBaDSQtPobUu6Dq3d6nyyEkJFrd0DqLRvPEECwpp0Pb7dAtCIjx45bieFeWokIoBMwwmR6VR6jSZIQOjFZON/qtgpAA0Cr8c2VhR5LehKarR0DhBVZHe1EKqJ6jotXeoEoDLzGaTVpCkBAewVgACWxzZUFOda0I3UCEWidPaqs79ACJV0+gaVWqctM//wHvchP5VsH4DKi9UZAYFaQ3whVNLc2W91F5IqwQjotXT2wW4BaCWyDiSEsIBKr023y0Gh+TaWN9PZD7sFoCAmEVqldaD+QJgeRXZZC6EKnz9IfyBsdTeSJsHoZzPQmc5+2C0AgeLrQAB1Lb1Wd0EIcYi6ZrVek+UZsP4DigQg1daB6lt7CUfUWewUws7CkSj7WtUKQAkSENK6/gP2DEBvo/g6UDiis7+tz+puCCGA/W39hCPqbI9wuxwZkYAA9gxA5utAik3D7WlS6xOXEHa1t9lndReSqqY0Dy3+LJs9wM5098WOAQjgpdgGlRIRwFj0VOnMESHsqNMXUC4pqKYsz6z5n0Dah3l2DUDLYxtUWwcC9T55CWE3exRLPnBoGlWlprNFT6S7L2DfALQKGJGUr9o6EEBDez+DwYjV3RAiKw2GIjS2q7UWW1HsxeWMe9vvBl61oDu2DUCm60BVJWqtA+k61CmWfSOEXexr6UW10ow15abTb/8CLDmS2a4BCEzWgSZXFFjRj5Ta29yLrlL9dyFsQNd19io2/QZGAoKJf6a7HwfYOQA9FttQWphDntdlRV9SZmAwTEuXOgdgCWEHLV0D+AfVqXwAxuFzuTlx748h4BkLugPYOwBtBdbGNk6pyLegK6m1u7HH6i4IkVV2N6mXAJQg++1FwLJ/rJ0DEMBfYxtUnIZr6wkodQywEJmsvSdAW7d6r7eaMtMP55ZNv4H9A9DDsQ1F+R7lsuEANu/tsroLQmSFzXVprceZFnk5LorzTatfSwCagL2YlA9XcRTU1TdIU4da55EIkWmaOvrp6h20uhtJl2D6bQ2wP81dGcHuAQjgodiGyQquAwFsrusiKhlxQqSErutsqVNzpiFBALJk8+mhVAhAjxJTQqIg101Jgelw09b6BkLUt6q1MU6ITFHf2kfvgCXbYVLK7XQkqhRj6fQbqBGAmjApzaPiNBzA1n1dROSoBiGSKhKNsnWfmqOfKZX5OOKLj+4D1lnQnRFUCECQRdNwgWBEufpUQlhtT1MvA4qWvZpRU2TW/BgWFB+NpUoA+gcwYtdYbo6LsiLTMy9sb/v+bkJhNV8sQqRbKBxl+/5uq7uREmWFORSZZ7/9Pt19MaNKAOoAnottnKLoNFwoHGVng2xOFSIZdjb0EAqrOa09o6bQrPlVYFOau2JKlQAEJtNwtRX5xM18KmJXo49AUK1SIUKkWyAYZpeilUbcLge15ksRv0t3XxJRKQD9ExhxgluO25no7Avbi0R1Nu5Rb8OcEOm0aW8nEdVKXg+ZWlWA0xH3Ft8J/M2C7phSKQD5MMqKjzC7ttiCrqRHQ3s/jbI5VYgj0tTRz/42dV8/M6pNp9/+SMwHdSupFIAA/hDbUFmSS1GeenuCDli/q53BkCQkCDEewVCEdbs6rO5GypQXeSk0f9+7O919GY1qAehpYHts4+xa0zREJQyGomzYre4LSYhU2LCnQ+kPbgmSD14CtqW5K6NSLQBFgTtiG6dUFpDjdlrQnfSQqTghxk71qTeP20FtuWnywW/T3ZfDUS0AAdyPsdA2zOHQmDlJ3VEQyFScEGOh+tQbwLSqQhyOuPzfVuBxC7ozKhUDkB+4K7ZxZk0hzvj/FGXIVJwQh6f61BskTD64DwimuSuHpWIAAvg1xlGzwzxuJ1Or1NyYeoBMxQmRmOpTb2AkXeXnmp6HlhGVD2KpGoCagAdjG1VORjhApuKEiJcNU29gzPSYeBbYneaujImqAQhMkhEKcj1UK7ox9QCZihMiXjZMvRXleZhknnyQMZUPYqkcgNYB/4ltVHlj6gEN7f3sbfZZ3Q0hMsLe5l7lp94A5k8rMWtuAJ5Kc1fGTOUABPDz2IbKktxEZ6MrZf3uDtp7MmbDsxCW6OgJsH53u9XdSLni/ISjnx8Qsx6eSVQPQM8AW2Mbs2EtSNfh7a0t+AMZ+9wTIqX8gTArt7WQDafYz59WatZcD9yT5q6Mi+oByHRj6uSKArwedTemHhAMR3lrSythOUFVZJlwJMpbW1sIhtR/7pcW5FBTlmd26fvAYJq7My6qByCAP2OcFzTM4dCYO1n9tSAAnz/Imh1t6NnwMVCIIe/saMPXn3HbXlJinvnaz16MwqMZLRsC0ADwm9jGGTVF5OW4LOhO+jV1+NlWr+aJj0LE2lbfRWOH3+pupEVZYQ7Vpaajn9vIwI2nsbIhAAH8Cug7tMHh0BLNmyppW303je3qZwKJ7NbU0c/WfdnzYSvBe9gujJmfjJctAagV+Fls45TKfKWPaoi1ZkcbPf0ZPSUsxBHz9QdZvb3N6m6kTXmRl8oS032N/0MGZ74dKlsCEBgBaMSzU9M0Fk7PnlFQJKrz1pZW5TfkiewzGIrw1pYWZU83NZNg3882TKrAZKpsCkC9GFkhI1SX5VFe5LWgO9YYGAzz1pYWyYwTyghHoqzc0oJ/MGx1V9KmothLRbHp6Od7gG1+EdkUgMAoSbE3tnHhjOwZBQF09Q5KEBJKiESivLWlhc7e7JpaTrD2sxl4JM1dmZBsC0CDwHdiG8sKvUyuMN1FrKz2ngArt7Zm1ZSFUEskqrNya2vWVfyoKslNNGtzK2Cr+fVsC0BgzI+uj21cNKNM6fOCzLR1D7BqWytRCULCZqJRnVXbWmntHrC6K2mlabBoZpnZpfXA39PcnQnLxgAUBb4a25ib42J2lmxOPVRzp59V2yUICfuIRnVWb2+juTM79vocatakokSZu9/FeG+zlWwMQADPA0/GNs6dXJwVJXpiNXX4eXubTMeJzHdg5JONBy96Pc5Eaz9vAk+kuTtJka0BCIxR0IhsEZfTwcLppsNb5TV3+lm5tYWIJCaIDBWJRlm5tYWmLBz5ACyeWYbLGfeWHQVuAGz56TGbA9B24JexjVOrCigtyLGgO9Zr7RqQ7DiRkcIRo7BuS1d2rfkcUFnsZXJFgdmlu4A1ae5O0mhZXqSyBNgJlB/a2NM3yIr1jVlRxt1MeZGXkxZU43Zl8+cTkSnCkShvbm6hw5dd2W4HODQ4Z+lkCnLj1n5agXmAbWsPZfs7TDcmadnFBTnMm2q6yzgrdPgCvLK+kb4BW1TzEArrD4R4eX1j1gYfgDmTS8yCD8DXsHHwARkBAbiA1cAxhzZGdZ2X1zXSkyUl3c24XQ6WzatKVG9KiJRq6x7g7W2thMLZOyVckOvm7GMnm20ReRU4E5uu/RyQ7SMgMBIRriVmA5dD0zhubiVZtjVohFA4yhubmtnd2GN1V0SW2dPk441NzVkdfACOnVNhFnwi2Djx4FASgAxrgNtjG4vyPczLoiMbzOjAhj2dvLOzTdK0RcpFozprd7azfneH/d9dJ2hGTWGiigc/xWQzvR3JFNxBHuAt4NhDG3Vd55X1TXT1ZVetKTNlhTksm1+dlXulROoNBiOs3NZCp09ea16Pk/OOm2KWdr0TY7lAiXRAGQEdFASuIeYcDU3TWDq3Akc2z8UN6ewd5OV1DXRLMBZJdiDzVIKPYcnsCrPgA/ApFAk+IAEo1jqMw5xGKMzzJDp7I+sMBCO8uqGJhva+w99YiDFoaO/nlQ1NDGTRcQqjmVJZQE2Z6THbvweWp7c3qSVTcPHcwBvA8Yc26rrOqxuasq7s+2jmTC5m/rTSrCviKpIjEtXZtq+LHQ2S5HJAQa6bs5bUmo1+moCF2DztOpYEIHOLMVKzRyTf9w2EWL62QRbjD1GY5+a4uZWUZGn1CHFkuvsGWbOjjV6/7DU7wOHQOPOYWorzTff8fAB4LM1dSjmZgjO3EaO67AgFuW4WZNER3mPR6w/x8rpGttR1SmAWhxWJ6myp6+LldY0SfGIcPbMsUfB5CAWDD8gIaDQu4DXgxNgLr25oyuqd2YnIaEiMRkY9iU2pzOf4o6rMLu0ATgB86e1RekgAGt18YC0w4h21PxBixbrGrN8kZ0YD5k4p5qipsjYkDJGozvb6bnbs7876vT1mRln3GQROwkiOUpJMwY1uK/Ct2MZ8r5sTjqpC3l7j6cD2/T2skHRtgTHqWbGuge0SfEw5HRrL5lUlSrm+CYWDD8gIaCycwMvAqbEXdjR0s3lvV/p7ZBMyGspeMuoZmyWzK5hRU2h26SHgShQotzMaCUBjMxtYhXF8wwirt7eyv23spzMO+Pt56m9/5JUXnqS1qQG3x0Pt1JlceOlHOffdl6NpB9+oV7+xnMf/+nvq9+xgwN9PeWUNy047j8s+9ilKyipHfRxd11nx3BOsev1Fdm7dQGd7C0XFpcycu5APffwGjlo0ouADA/5+/vCr/+WtV54D4JSzLuKaG27BmztyP8KbK57ljtu+zJ1/fpbqSVPG9G/O97pYML2U2vL8Ef8+oabG9n627OuSauqHcZh1n+OB3vT2KP2ct956q9V9sIMujKHwlTBy5q26JJeWrgEGQxHTHzxUNBrlu1+8iuXPPMbxJ5/N+Rd/mHmLl1K3cytPP/YXgoMBjl12OgDP/fOv/OzWmygsKuHdl13JstPOw+Vy8cwTD/L6S09zwSUfweV2J3ysUDDIVz55KU6Xi1POvIgzL7yUyVNnser1F3nykfuomTydGXPmD9/+vju/z4rnnuD9V1zHUYuO5el/PICvp4vjTzl7+Db9fT6+//Xr+NDHPzei/XBC4SiNHX5auvzke93kexP3W9hXW/cAq7a1srvJR1DWR0dVkOvmpAXVZhVWBoELgX3p71X6yQhofL4B/DC20T8YZsW6BoKh0V90Wzeu4Zuf/SCXfPhaPnnTwWOIQqEgN37sAnp7u3nwGWPK93NXnMeAv5/fPbICT87BHIgH7v4Zj97/a775v7/l5DMvTPhYkXCYLRtWs3jpSSPauzvb+PxV78LhcPCHJ97C4TDmnq9930lceOkVXPHJLwLw0L138PyTj3Df428M/+xdP/kWO7du4Md3P4bTeeT14CqLvSycUSbZcoro7htk895O2nokM3QsnEP7fYrMU64/A9yd5i5ZRpIQxufHwMOxjXk5LpbNq+Jws0sD/Ub5mrKK6hHtbreHopJSvN6D010D/j4KCotHBB+A0gpjyO7NHf2MHqfLFRd8AErKKll07In0dHXQ09Ux3D44GKCw6OAMY0FhCYGAf/jvm9e9zX/+9Tdu+MYPJhR8ANp6AqxY18jbW1voG8je85bsrm8gxNvbWlmxrlGCzzgcPas8UfB5EKPcTtZwWd0Bm9GBT2KkZy859EJFcS6LZ5SxYU9nwh+eu2AJ+QVFPPbg3VTVTOGohUsIBgd58d9/Y9e2jXz2q98fvu2xJ57JS0//nft+eTsXXPIRvLl57Ny6nkf/9CsWHXsSRx8XlxMxZh2tzbjcHvILiobb5i86jmeeeJBFx56Ejs4zjz/A/MXHKjzAPgAAGGhJREFUAcYI7Tc/voVLPnwts45adMSPG6uxw09Th59p1YXMm1pCbo48He0gEAyzrb6buuZetVfIU2BadQHTq02TDrYDn0XxpINYMgV3ZGZgJCWUx154Z0cb+1oTF+rctG4lv/7hzTTW7xluy80r4Avf/umIKbX+Ph+//tEtvPnys0QjB9eXznvPB7n+67fjch3ZOsqqN17i+1/7JGdfdBlf/M7Phtsb9u3m9q9fR+P+vQDUTpnBt358D5OnzeKhe+9g+bNPcOefnyEnx/R8kglzODRmTypiVm0RXo8EokwUCIbZ3ehjd5NPql4cgerSXE5cUI0jfqokgLHfR4kzfsZDAtCROxd4DiNNe1gkqvPahsTnB+3evolH/vQramqnMX/xcfT2dvP0P/7C/rpd3PLD33HssjMAGAwM8OA9d9DW3MCy084jx+vlnZWv8J9/Pcp57/0QN3zjB+PucGP9Hr7xmcvx5Hj5+X1PUlw6Mn6GwyHq9+wEYOrMObhcbur37OBLn7iE7/z4HpYsO51//+PPPPPYAwz4+1h2+vlc/blvJjUoaRrUluczo6aIiuLUBDsxPh09AfY0+2js6EfeLo5MaUEOpy6uSbTf59Nk2dTbARKAJuYLwC9iGwPBMMvXNsZlxu3dtZWvf+oyPnHTt3nX+68cbh8MDHDTVe8iqkf57cPL0TSNb3/+CiKRCD+869ERqcv33/Uj/vHA7/jeHfezZChjbixaGuv51o0fZXAwwG13PsCM2fMP+zO6rnPz5z7MpCkz+MK3fsKr/3mKO2//Gjd884dUVE/iztu/ztITz+CzX71tzP0Yj8I8NzNriphSWYDbJcuV6RSORKlv7WNPs09K50xQQa6b04+eRI7bdO30foxzyLLyjVhe1RNzJ/Cn2Eavx8WJ86uIzbB88uH7CAYHOfWc94xoz/Hmcvyp59DW3EBr8362rF/F5nVvc8pZ74rbN3PgZzeuXTnmTrY07efbN32MwICf791x/5iCD8DTj/2Fpvq9XHvjLQA8/9QjnHL2uzjrwvexaMmJfPCq63nx338jGk1Nym2vP8T63R08t2of63a14+uXhIVU8/UHWb+rnWff3sf63R0SfCYox+3k5IXViYLPCxgHzGVl8AFJQpgoHWPhcCGw7NALZUVeTphXxdvbWoenLTraWwCIRuP3DEUj4aHvETramke5XWTE7Q+ntbmB79z0Mfx9vXzvF38ecxJBR1szf/ndT/jMV26jqLh0uG3OvMXDt6momkQwOIivp5OS0oox3e+RCEd09jb3sre5l/IiLzNqCqktz5dTapMkGtVp6uxnT1OvFNlNIpdT45SF1Yn2vb2DccRCVn+qkhHQxAUwnkgtsRcmledz3NyDFQumzpgDwIv//vuI2/X1+njrlRcoKCympnYaU2fMBeDl554gHB75CfTFp/8GwJwFxwy39ff52F+3C1/3yAy81uYGvv35K+jr7eHWO/7EnPlHj/kf9buff5f5i4/nrAvfN9xWVl5F3e5tw3+v27UNl9tDUXHZmO93ojp8AVZvb+O5VfWs39VOa5dfFsSPQCSq09rlZ/2udp5bVc+qbW0SfJJI0+DE+dUUm+912wO8hyyodHA4UgkhOXwYp6heRUxSQlG+h7wcF82dfqZMn8PyZx5j1esv0tRQR09XO++sfIW7fvItOlqbuObGW5i3aCml5ZXU7d7GxnfeZOUrLzAw0M+eoeSFl5//J/MWLeXj139zeBPpKy88ya1f+jieHC9HH3cyYOwj+sanL6e1aT8XXnoFbk8Oe3dtHfFVUlaONzc/7h/z+vKn+efD9/Ltn9xHQeHBVO2oHuWJh+6hr7eHfbu388iffslp576Hk8+8KGW/2EQiUZ3uviD72/rZ3dRDd98g0aiO1+NKtNCb9QZDEZo6+tle3826Xe3sa+2juy8oATwFjj+qkknl8a8toB0jgakuvT3KTDIFlzyvAdcCfyamXM+06kIiUZ31wI9//xiP/OGXrF/9Oq++8BSeHC8z5y7g2htv4ZSz3jX8M1/+7i94csEfePm5J3jonjuI6jpV1bVcftX1fOjjNxx2M6ivp5uWpnoA/vW3uGUqAG6788G4mnL9fT5+f8f3+Nh1X4qr9Xbuuy+nq6OVZx57gMHAACedcSHXfeG/x/bbSaFwRKdpaE8RQFlRDjVleUwqy6Mg13TDX9boGwjS3DlAc6dfRjhpsmhGGVMqC8wu+YH3Yuz5EUgWXCp8Gvid2YWdDT1s2pt4o6pIvoJcN9WluVSV5lGS78FjvhisjGA4QndfkLZuI+hIQdD0ml1bxOKZcdsDASLApcC/09ujzCYBKDVM07MBtu7rYlt9d5q7Iw7Iy3FRUuChpCCHkoIcim0clILhCD19Qbr7BunuC9LdP4g/MLbkFJF8kyvyOWGeaXVrMGZH/pi+3tiDBKDU+SZgult0895OdjT0pLk7IhE7BCUJNpmtqjSXk+abVrcG41DL/01zl2xBAlBq/Q/wHbMLG3Z3sLtJyWPeleBxOfB6XHg9zuGvnAN/dzvxelzkeJwTPmgvEtUZDEYIBMMEQpGDfw5GDn6FwoettC6sU1uRz/FzKxMFn98AN5LFe31GIwEotTTgJ8BXzC6u3dlOXUvWZ2LamtvlwOtx4nY60DQNTQPH0PcDm4h1XUfXITr0Xdd1QpEog8GInJtjc9OrC1kyuzzRQYv/AD6Msf4jTEgASj0N+DVwfewFXddZs6NtXCeqCiEywygJBwCvYBwsJ6mHo5AAlB4O4F6Mmk8j6LrOqm1tNHZIEBLCLuZPK2Xe1JJEl18C3odsND0sCUDp4wQeAD4Se0HXddbv7mBvszxfhch0R88sY1ZtcaLLT2JMu8nIZwwkAKWXG3gU49NRnG31XWzdJynaQmQiDVg6t4KpVaYHyoFxouk1gGy+GiMJQOmXAzwBmNav2dvcy/pd7ZIyI0QGcWgaJ8xLWF4H4LfADYBklYyDBCBr5AEPAxebXWzq6Gf19jap0SVEBnA6NE5aUE1lSW6im/wQuAVJtR43CUDWcWGU7PmE2cUOX4CVW1okTVcIC7mdDk5eWE1ZUcLTeW/GCEDiCEgAspYG3IaxUzpO30CIt7a0SD0vISzg9RiHyRXnmx6poGNMud2V3l6pRQJQZrgR43TVuN1swXCEt7e20t4jSTVCpEtpYQ4nzq/C6zE9MCACXI2R1SomQAJQ5vgQ8Bcg7vyAaFQfPr9FCJFa06oKOGZ2RaIyS4MYr9Un09srNUkAyiz/3969B8d51Wcc//5Wu7quZFvWxbLk+yXGNo6N46S4TbE9LYSkU4akZSZNkxic4JQODEMppdMLSQsUwh9loJRpE0ICbTOUBNpMQ0pLSGiGlqRpAnFx4rvsxhf5IsmWrPvu6R/nXXst7dW6vCvp+czsrPPu0atjxdpnz/ue8zvb8OU75mV68cCb3ew92jWlHRKZLcxg/dKca3x68VsqPDd1vZrZFECl5xrgaWBFphdPnrvIqwfOMpzQ5ASRiVIejXDdmiYa52Sd6XYSv37vv6euVzOfAqg0NeBHQjdmerFvYISX95+mq2dwanslMgPNjZez5Zomqitj2Zq8BLwXODF1vZodFEClqwL4W+CuTC8mneONY10ceFP7ColcraULalm/bH6ubTUeA+5DpXUmRaSYxmY2z8wGzMyZ2W9PVqcE8Dc7dwJ/nOnFiBlrl9Szdd0CKkps8zSRUlcWMd62upFrs082SAAfxe9kqvCZJEWNgMwsNV24HTjqnNs+Sf2SK92Gr6ad8e7o4FCCVw6c4XR3/9T2SmQaqq2KsWVNE7XVYyacpnTiC4o+O3W9mp2KDaBX8f9z/hn4IrDKOXdokvo2Icys1jk3E8pMLwMeB27I1uDg8fPsPdqJrqqKZNbWWMO1KxqIlmW9+PMq8BvA4anr1exV8CU4M3sbsBF/TfTv8RVf35+l7XYze9rMzgWX7A6b2dfMrGFUu9vM7Dkz6zazPjPbZ2ZfMrPy4PWdweW+bRm+x/Nm1j7qWHtwfJOZfd/MzgOvBa/VmtmnzexFMztrZoNmdtDMPmdm1RnOb2Z2b9C+N3jsMbM/C16/NejbPVl+Bj8Pzj++PZsvO4KflPA5stScWtk6hxvfupCayoyL50RmrYpYGVuuaWLz6qZc4fM3wFYUPlOmmHtAu4CLwJPOuXP4qcJ3m9kV5zCz3fih6wZ8mYoP4wNrM9CW1u4zwBNAE/CX+Out/wTcjC/WebUWAz8EjgK/D3w5ON4K3AO8jC9/8zHgFeATwHcznOeb+EkADvhMcK4f4j8dATwFnML/XK5gZr8ArAUecRM7y2MYX3vqXUBHpgbzait4x7WttDZkrdorMqssaoyzY1MrC7P/TvQBd6LJBlOuoEtwZlaJn4L4lHNuZ3DsPQSB4Zx7JjjWBhwKHludc92jzhNxziXN7HrgRfyCrpudcwNpbQzAOefMbCfwdWC7c+75Ued6HljqnFuadqwdWALc65x7eFT78uC0w6OO/zn+Rv8NzrmXgmPvw1er/jvgbudcMq19JPXfZvZZfCCsc87tTWvzEH50uNg5N1lTN5uBb+C3/c3oaEcPew6fU1VtmZUqy8vYuKKB5vqcn2ffwH+o/PnU9ErSFToCuhW/Ov+xtGNPA6e5sprzb+JLyTwwOnwA0t7I7wie/zA9fII2bpyjhk58aI3+3kOp8DGzaDCjrwH4QdAk/d5Kqn8fTw+fUX8HgIfwI6RLoyAzq8HvevrMJIYP+BHQu/EjuJFMDZY017JtYyuNc7JW8hWZkZY017JjU1u+8Hkc2ILCJzSFBtAu4AzwppmtNLOVwFLg34FfT7u3syp4fjXP+Vbh37h/Vlx3C3LIOZfI9IKZfcjMXsNPce7E/52eD15OL3+zCjjpnMt4mSvFOXcEH2B3mllqFdv7gFrg4axfOHGSwBeAX8LfIxojXhVj6/oWNq9upLJc07VlZquuiLJ13QI2rmwgFs369nYW/yHxDnx5HQlJ3gAys2XAdqAR2A8cSHvcgR/xpNYEpW645xvBWAFt8p0n2532vozf0OxjwFfwJTV2A7cAv4pfawNX/iwK7R/4+0SN+BpR4MP6FH6EOFVeBDbhLxtm1NYYZ8emNpYvrBtbcltkBljeUsf2Ta25No4DP+pZC/wj2kAudIVMl3o//g35XmDMZTXg0/g33S8C+4Jjm/ABlc0+4Cb8RIWXcrTrDJ7rM7y2jOL2Xr8Tv37p3aPu6dyUpX/vMbPmfKMg/JT008AuM/tf4BeBzzvnMl4Wm0Tngdvxo9IvA2N+C2PRCG9dNp/FTXFeO3SOTpXykRkgXhVj48oG5mffNA78B8/fwf++SonIOQIKZrjtBPY45x52zj0x+oH/RLHezLbgZ7UNAZ8ys7oM50t9+P6H4PmzZjZmt6e0dvuD518Z9frtwMKC/oaXJfCfeC4NAMwsCnwyQ9vUPh8PZpjld8UAIriv9Ch+ZtqngsNfK7JvE8UF33sz8ONsjebUVHDjhoVsWtlAefbLFCIlzfBLD7ZtXJgvfB4B1qHwKTn5RkDvBBaR+w31SeB+YJdz7j4z+yj+UtceM/sGfjp0K76S7AeAnzrnXjKzzwN/APyPmX0Lf9lqGX5GyvVAt3Nun5n9ANgdvPH/FL8W6b3AQSBr9cAMngD+AnjGzL4D1AG/RYZRlHPu20Gf7gJWmdlTQBewGh8060d9yUP4adq3Az9yzuUa/U2F14Ffxvf/C/jipmMsbq5lQX01e492cbRjJqzVldliQX01a5fMy1XNAOAY/srNv01Nr6RYOadhm9m38YGwwTm3J0e7ffhpwS3OuX4zeyf+Dfl6fFHNE/i1QZ8M1hClvu52/G6gG/Cjsf8D/hX4hHNuKGizAH9J6V1Bmxfwa3i+SuZp2O3OuW0Z+liGnzG2Cx+qp/D3TL4O7MXP3Ls/rX0EP2TfBazBj6CO4NdBPZDh/M8CO4C7nHPfzPazCkE9fh3TbjLsuJrS1TPIzw6d5fzFoSnrmEix6usqWLeknvrcIx6Av8Zf3dAnqxKmatgTxMy+B7wdWOicK8WibFvwob05WwPnHO2nenj9aJf2G5KSUlsdY+2SehbknlYNfg3iLuBHk98rGS8F0AQIpqXvA77inPtI2P3JoQz4IP5SZNZtH4dHEhw6cYHDJy4oiCRUVeVlrFk8j0VNcfJUtUriK6r8KVlmwkrpUQCNg5ndALwF+Ejw/BbnXHuonSpMM/AgWfYaShkeSXL45AUOnTjP8IiCSKZOLBphVdsclrfUURbJO1HmP4CPo91Kpx0F0DiY2aP4N/HD+PtW3wm3R0W7EX+tfPSkiiuMJIIgOn6eIQWRTKKyiLG8pY5VbXOIRfMunN6Dv8/zDFrTMy0pgCSGH8HdD8RzNRxJJDly8gIHT5xnaFhBJBPHgEXNcdYsmkdVRd7liceAP8Evl8hY9USmBwWQpLThi7J+gDzT20cSSdpP9XDw+HkGh/X7L1cvVhZhcXOc5S11VFfmXVXRiV/4/lVUtXpGUADJaIvwlzXuwZdZyiqRSNLe4YNoYEhBJIWrrYqxrKWORU3xXPvzpPTjJxg8iK/4ITOEAkiyacOvm/ogfi1XVolkkqMdvRw5eYHe/mKqI8ls0zyviuUtc2ial7NeW0oCvwj+AfxaQplhFECSz0L8ouL7gLyr/86c76f9ZA8nOy9qa3ABIFpmLG6qZVlLHfGqgouXPAn8EZfrS8oMpACSQi3AT3X9EBkKnY42MJTgWEcP7R099A9OdV1WKQU1lVGWt9SxuLm2kMts4GeyfQ9/n+cnk9o5KQkKIClWE/B7wO8Ceff9ds5xuqufY6d7ONXZT1L/3ma8xrlVrGipy7cZXLoefMHQv8LXeJRZQgEkV6sBX5Pvw+SZvp0yNJzg+NmLHDvdQ3evas7NJHPj5bQ2xGltqClkGnXKAXydx0dRzbZZSQEk4zUPvxj3PnzR1oL09A1x7HQvb57p1Qy6aSpeFaO1oYa2xngx93YAvg98CV94WAvKZjEFkEwUA96BD6JbKWKrjK6eQTq6+ujo6tPIqMTVVsVomV9Ny/wa5sZzTo4c7SLwGH7E88akdE6mHQWQTIZm/ILW3cCSYr5wYGiEjq5+Orr6ONPdz0hC/z7DNi9eEYRONfGqnEvDMjmCv7fzCJl3VJZZTAEkkykCbMfvqnsbBcyeS5dMOs5dGKCjq49TnX1cHNBsuqkQi0aYX1dJ09wqFtRXF3NPJ2UEf5ntIeBfULkcyUIBJFOlDr+54U58EdSi9fYP+0t1nX2cuzBAUv90J0RVeRnz51RSX1fJ/LpK6nLvMpqNw+/B8zh+Dc+53M1FFEASjhXA3fhR0dqrOcFIIklX7yDne4fo7h2ku3dQI6QC1VbFLoXN/LpKqiuLHuGkexkfOt8Cjk9IB2XWUABJ2JYBNwO/hr9cV9Sd7XTDIwm6LwWSf+6b5YtgzWBOTfmlsKmvq6Qilnebg1wc8F/Ad4PHoYnop8xOCiApJTXADuAWfCC1jveEQ8MJui9eHiV19w7NyMoM5bEI8coY8aoYNVWxtD9HC9nQLZ9h4Fl84DwFnBrvCUVAASSly4AN+DC6BXh7cGzchkeS9A+O+MfQCP2DibQ/j9A/lCBZgjeYomVGTYaQiVdFC9m8rVivAy8Az+E3fFMVaplwCiCZLhqAm/BhdBMwdzK/2eDw5VAaSAuowaEEI0lHIulIJJLBsyORTBY8KSJaZkTLIsSiEWKp52hkzLFo2mvVFVEqy8d1ryaXBPAKPnBeAH4MnJmsbyaSogCS6SgCrAY2A9cFj00UUJtuMjnnSDr/nPpv5/APHBEzYtEIZhMykBuPfnyxz1Tg/AToDbVHMispgGSmKAOuYWwoFbX2aIY6B/wnlwPnFUAlJyR0CiCZyaL4+nTXcTmYNlLAvkbT0AC+uOcBYP+ox1n87DWRkqIAktkmgi8VtCjHoyVoV2qS+NI2owNmP/AmKuwp04wCSGSsGD6EMoVTHf5eU3XwqEl7LnQqWj9+Vll32nN3nmNn8eGjS2cyYyiARCZODB9C2R4j+EAZDKuDIqVEASQiIqEoxevcIiIyCyiAREQkFAogEREJhQJIRERCoQASEZFQKIBERCQUCiAREQmFAkhEREKhABIRkVAogEREJBQKIBERCYUCSEREQqEAEhGRUCiAREQkFAogEREJhQJIRERCoQASEZFQKIBERCQUCiAREQmFAkhEREKhABIRkVAogEREJBQKIBERCYUCSEREQqEAEhGRUCiAREQkFAogEREJhQJIRERCoQASEZFQKIBERCQUCiAREQmFAkhEREKhABIRkVAogEREJBT/D6Ue26uVteVJAAAAAElFTkSuQmCC\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 432x432 with 1 Axes>"
       ]
@@ -691,16 +684,44 @@
      "output_type": "display_data"
     },
     {
-     "ename": "TypeError",
-     "evalue": "confusion_matrix() got an unexpected keyword argument 'normalize'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-20-362e872d02fc>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     16\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     17\u001b[0m \u001b[0;31m# ooo.display_confusion_matrix(y_test,y_pred,labels=range(2),color='orange',font_size='20pt')\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 18\u001b[0;31m \u001b[0mooo\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdisplay_confusion_matrix\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_test\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0my_pred\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mlabels\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[0;32m/gpfsdswork/projects/rech/mlh/uja62cb/fidle/fidle/pwk.py\u001b[0m in \u001b[0;36mdisplay_confusion_matrix\u001b[0;34m(y_true, y_pred, labels, color, font_size, title)\u001b[0m\n\u001b[1;32m    323\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mtitle\u001b[0m \u001b[0;34m!=\u001b[0m \u001b[0;32mNone\u001b[0m \u001b[0;34m:\u001b[0m  \u001b[0mdisplay\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mMarkdown\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtitle\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    324\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 325\u001b[0;31m     \u001b[0mcm\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mconfusion_matrix\u001b[0m\u001b[0;34m(\u001b[0m \u001b[0my_true\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0my_pred\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnormalize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"true\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlabels\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mlabels\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    326\u001b[0m     \u001b[0mdf\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcm\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    327\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mTypeError\u001b[0m: confusion_matrix() got an unexpected keyword argument 'normalize'"
-     ]
+     "data": {
+      "text/html": [
+       "<style  type=\"text/css\" >\n",
+       "    #T_8216dc86_535b_11ea_968f_0df50868c732row0_col0 {\n",
+       "            background-color:  #008000;\n",
+       "            color:  #f1f1f1;\n",
+       "            font-size:  12pt;\n",
+       "        }    #T_8216dc86_535b_11ea_968f_0df50868c732row0_col1 {\n",
+       "            background-color:  #e5ffe5;\n",
+       "            color:  #000000;\n",
+       "            font-size:  12pt;\n",
+       "        }    #T_8216dc86_535b_11ea_968f_0df50868c732row1_col0 {\n",
+       "            background-color:  #e5ffe5;\n",
+       "            color:  #000000;\n",
+       "            font-size:  12pt;\n",
+       "        }    #T_8216dc86_535b_11ea_968f_0df50868c732row1_col1 {\n",
+       "            background-color:  #008000;\n",
+       "            color:  #f1f1f1;\n",
+       "            font-size:  12pt;\n",
+       "        }</style><table id=\"T_8216dc86_535b_11ea_968f_0df50868c732\" ><thead>    <tr>        <th class=\"blank level0\" ></th>        <th class=\"col_heading level0 col0\" >0</th>        <th class=\"col_heading level0 col1\" >1</th>    </tr></thead><tbody>\n",
+       "                <tr>\n",
+       "                        <th id=\"T_8216dc86_535b_11ea_968f_0df50868c732level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
+       "                        <td id=\"T_8216dc86_535b_11ea_968f_0df50868c732row0_col0\" class=\"data row0 col0\" >0.88</td>\n",
+       "                        <td id=\"T_8216dc86_535b_11ea_968f_0df50868c732row0_col1\" class=\"data row0 col1\" >0.12</td>\n",
+       "            </tr>\n",
+       "            <tr>\n",
+       "                        <th id=\"T_8216dc86_535b_11ea_968f_0df50868c732level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
+       "                        <td id=\"T_8216dc86_535b_11ea_968f_0df50868c732row1_col0\" class=\"data row1 col0\" >0.12</td>\n",
+       "                        <td id=\"T_8216dc86_535b_11ea_968f_0df50868c732row1_col1\" class=\"data row1 col1\" >0.88</td>\n",
+       "            </tr>\n",
+       "    </tbody></table>"
+      ],
+      "text/plain": [
+       "<pandas.io.formats.style.Styler at 0x7fa14488b110>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
     }
    ],
    "source": [
@@ -725,18 +746,12 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "source": [
+    "---\n",
+    "![](../fidle/img/00-Fidle-logo-01_s.png)"
+   ]
   }
  ],
  "metadata": {
@@ -755,7 +770,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.5"
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,
diff --git a/IMDB/02-Prediction.ipynb b/IMDB/02-Prediction.ipynb
index 3c93a70..f3eafda 100644
--- a/IMDB/02-Prediction.ipynb
+++ b/IMDB/02-Prediction.ipynb
@@ -4,17 +4,21 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Text Embedding - IMDB dataset\n",
-    "=============================\n",
-    "---\n",
-    "Introduction au Deep Learning  (IDLE) - S. Arias, E. Maldonado, JL. Parouty - CNRS/SARI/DEVLOG - 2020  \n",
+    "![Fidle](../fidle/img/00-Fidle-header-01.png)\n",
+    "\n",
+    "# <!-- TITLE --> Text embedding with IMDB - Reloaded\n",
+    "<!-- DESC --> Example of reusing a previously saved model\n",
+    "<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
     "\n",
-    "## Reviews analysis :\n",
+    "## Objectives :\n",
+    " - The objective is to guess whether film reviews are **positive or negative** based on the analysis of the text. \n",
+    " - For this, we will use our **previously saved model**.\n",
     "\n",
-    "The objective is to guess whether our new and personals films reviews are **positive or negative** .  \n",
-    "For this, we will use our previously saved model.\n",
+    "Original dataset can be find **[there](http://ai.stanford.edu/~amaas/data/sentiment/)**  \n",
+    "Note that [IMDb.com](https://imdb.com) offers several easy-to-use [datasets](https://www.imdb.com/interfaces/)  \n",
+    "For simplicity's sake, we'll use the dataset directly [embedded in Keras](https://www.tensorflow.org/api_docs/python/tf/keras/datasets)\n",
     "\n",
-    "What we're going to do:\n",
+    "## What we're going to do :\n",
     "\n",
     " - Preparing the data\n",
     " - Retrieve our saved model\n",
@@ -34,14 +38,49 @@
    "metadata": {},
    "outputs": [
     {
-     "ename": "ModuleNotFoundError",
-     "evalue": "No module named 'seaborn'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-1-94e372328354>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      7\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmatplotlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpyplot\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      8\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmatplotlib\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 9\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mseaborn\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0msns\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     10\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mpandas\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     11\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'seaborn'"
+     "data": {
+      "text/html": [
+       "<style>\n",
+       "\n",
+       "div.warn {    \n",
+       "    background-color: #fcf2f2;\n",
+       "    border-color: #dFb5b4;\n",
+       "    border-left: 5px solid #dfb5b4;\n",
+       "    padding: 0.5em;\n",
+       "    font-weight: bold;\n",
+       "    font-size: 1.1em;;\n",
+       "    }\n",
+       "\n",
+       "\n",
+       "\n",
+       "div.nota {    \n",
+       "    background-color: #DAFFDE;\n",
+       "    border-left: 5px solid #92CC99;\n",
+       "    padding: 0.5em;\n",
+       "    }\n",
+       "\n",
+       "\n",
+       "\n",
+       "</style>\n",
+       "\n"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "FIDLE 2020 - Practical Work Module\n",
+      "Version              : 0.2.9\n",
+      "Run time             : Wednesday 19 February 2020, 22:08:28\n",
+      "TensorFlow version   : 2.0.0\n",
+      "Keras version        : 2.2.4-tf\n"
      ]
     }
    ],
@@ -77,12 +116,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
     "reviews = [ \"This film is particularly nice, a must see.\",\n",
-    "             \"Some films are classics and cannot be ignored.\",\n",
+    "             \"Some films are great classics and cannot be ignored.\",\n",
     "             \"This movie is just abominable and doesn't deserve to be seen!\"]"
    ]
   },
@@ -95,7 +134,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -113,7 +152,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -155,9 +194,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 13,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Text review      : This film is particularly nice, a must see.\n",
+      "x_train[0]       : [1, 2, 22, 9, 572, 2, 6, 215, 2, 0, 0, 0, 0, 0] (...)\n",
+      "Translation      : <start> <unknown> film is particularly <unknown> a must <unknown> <pad> <pad> <pad> <pad> <pad> (...)\n",
+      "\n",
+      "Text review      : Some films are great classics and cannot be ignored.\n",
+      "x_train[1]       : [1, 2, 108, 26, 87, 2239, 5, 566, 30, 2, 0, 0, 0, 0, 0] (...)\n",
+      "Translation      : <start> <unknown> films are great classics and cannot be <unknown> <pad> <pad> <pad> <pad> <pad> (...)\n",
+      "\n",
+      "Text review      : This movie is just abominable and doesn't deserve to be seen!\n",
+      "x_train[2]       : [1, 2, 20, 9, 43, 2, 5, 152, 1833, 8, 30, 2, 0, 0, 0, 0, 0] (...)\n",
+      "Translation      : <start> <unknown> movie is just <unknown> and doesn't deserve to be <unknown> <pad> <pad> <pad> <pad> <pad> (...)\n"
+     ]
+    }
+   ],
    "source": [
     "def translate(x):\n",
     "    return ' '.join( [index_word.get(i,'?') for i in x] )\n",
@@ -178,7 +236,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -194,7 +252,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -210,30 +268,34 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "This film is particularly nice, a must see.                            => POSITIVE (0.54)\n",
+      "\n",
+      "Some films are great classics and cannot be ignored.                   => POSITIVE (0.61)\n",
+      "\n",
+      "This movie is just abominable and doesn't deserve to be seen!          => NEGATIVE (0.33)\n"
+     ]
+    }
+   ],
    "source": [
     "for i in range(nb_reviews):\n",
     "    print(f'\\n{reviews[i]:<70} =>',('NEGATIVE' if y_pred[i][0]<0.5 else 'POSITIVE'),f'({y_pred[i][0]:.2f})')"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "a=[1]+[i for i in range(3)]\n",
-    "a"
+    "---\n",
+    "![](../fidle/img/00-Fidle-logo-01_s.png)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -252,7 +314,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.5"
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,
diff --git a/IMDB/03-LSTM-Keras.ipynb b/IMDB/03-LSTM-Keras.ipynb
index 42a2639..db456f1 100644
--- a/IMDB/03-LSTM-Keras.ipynb
+++ b/IMDB/03-LSTM-Keras.ipynb
@@ -4,24 +4,25 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Text Embedding - IMDB dataset\n",
-    "=============================\n",
-    "---\n",
-    "Introduction au Deep Learning  (IDLE) - S. Arias, E. Maldonado, JL. Parouty - CNRS/SARI/DEVLOG - 2020  \n",
+    "![Fidle](../fidle/img/00-Fidle-header-01.png)\n",
     "\n",
-    "## Text classification using **Text embedding** :\n",
+    "# <!-- TITLE --> Text embedding/LSTM model with IMDB\n",
+    "<!-- DESC --> Still the same problem, but with a network combining embedding and LSTM\n",
+    "<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
     "\n",
-    "The objective is to guess whether film reviews are **positive or negative** based on the analysis of the text. \n",
+    "## Objectives :\n",
+    " - The objective is to guess whether film reviews are **positive or negative** based on the analysis of the text. \n",
+    " - Use of a model combining embedding and LSTM\n",
     "\n",
     "Original dataset can be find **[there](http://ai.stanford.edu/~amaas/data/sentiment/)**  \n",
     "Note that [IMDb.com](https://imdb.com) offers several easy-to-use [datasets](https://www.imdb.com/interfaces/)  \n",
     "For simplicity's sake, we'll use the dataset directly [embedded in Keras](https://www.tensorflow.org/api_docs/python/tf/keras/datasets)\n",
     "\n",
-    "What we're going to do:\n",
+    "## What we're going to do :\n",
     "\n",
     " - Retrieve data\n",
     " - Preparing the data\n",
-    " - Build a model\n",
+    " - Build a Embedding/LSTM model\n",
     " - Train the model\n",
     " - Evaluate the result\n"
    ]
@@ -411,11 +412,12 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "source": [
+    "---\n",
+    "![](../fidle/img/00-Fidle-logo-01_s.png)"
+   ]
   }
  ],
  "metadata": {
@@ -434,7 +436,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.5"
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,
diff --git a/LinearReg/01-Linear-Regression.ipynb b/LinearReg/01-Linear-Regression.ipynb
index 0b53e4d..73e0abb 100644
--- a/LinearReg/01-Linear-Regression.ipynb
+++ b/LinearReg/01-Linear-Regression.ipynb
@@ -6,13 +6,15 @@
    "source": [
     "![header1](../fidle/img/00-Fidle-header-01.png)\n",
     "\n",
-    "Linear regression with direct resolution\n",
-    "========================================\n",
-    "An example of direct linear regression.\n",
+    "# <!-- TITLE --> Linear regression with direct resolution\n",
+    "<!-- DESC --> Direct determination of linear regression \n",
+    "<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
     "\n",
     "## Objectives :\n",
     " - Just one, the illustration of a direct resolution :-)\n",
     "\n",
+    "## What we're going to do :\n",
+    "\n",
     "Equation : $ Y = X.\\theta + N$  \n",
     "Where N is a noise vector\n",
     "and $\\theta = (a,b)$ a vector as y = a.x + b"
diff --git a/LinearReg/02-Gradient-descent.ipynb b/LinearReg/02-Gradient-descent.ipynb
index 11f9643..00f722e 100644
--- a/LinearReg/02-Gradient-descent.ipynb
+++ b/LinearReg/02-Gradient-descent.ipynb
@@ -6,13 +6,16 @@
    "source": [
     "![header1](../fidle/img/00-Fidle-header-01.png)\n",
     "\n",
-    "Gradient descent\n",
-    "================\n",
-    "An example of gradient descent in the simple case of a linear regression.\n",
+    "# <!-- TITLE --> Linear regression with gradient descent\n",
+    "<!-- DESC --> An example of gradient descent in the simple case of a linear regression.\n",
+    "<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
+    "\n",
     "\n",
     "## Objectives :\n",
     " - To illustrate the iterative approach of a gradient descent\n",
     "\n",
+    "## What we're going to do :\n",
+    "\n",
     "Equation : $ Y = X.\\theta + N$  \n",
     "Where N is a noise vector\n",
     "and $\\theta = (a,b)$ a vector as y = a.x + b\n",
diff --git a/LinearReg/03-Polynomial-Regression.ipynb b/LinearReg/03-Polynomial-Regression.ipynb
index 415dc33..bdb2c5b 100644
--- a/LinearReg/03-Polynomial-Regression.ipynb
+++ b/LinearReg/03-Polynomial-Regression.ipynb
@@ -6,13 +6,15 @@
    "source": [
     "![header1](../fidle/img/00-Fidle-header-01.png)\n",
     "\n",
-    "# Polynomial regression\n",
-    "An example of polynomial regression.\n",
+    "# <!-- TITLE --> Complexity Syndrome\n",
+    "<!-- DESC --> Illustration of the problem of complexity with the polynomial regression\n",
+    "<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
     "\n",
     "## Objectives :\n",
-    " - Just one, the illustration of a polynomial regression :-)\n",
-    " \n",
+    " - Visualizing and understanding under and overfitting\n",
     " \n",
+    "## What we're going to do :\n",
+    "\n",
     "We are looking for a polynomial function to approximate the observed series :  \n",
     "$ y = a_n\\cdot x^n + \\dots + a_i\\cdot x^i + \\dots + a_1\\cdot x + b $  \n",
     "\n",
diff --git a/LinearReg/04-Logistic-Regression.ipynb b/LinearReg/04-Logistic-Regression.ipynb
index e6ad34d..2e3e74c 100644
--- a/LinearReg/04-Logistic-Regression.ipynb
+++ b/LinearReg/04-Logistic-Regression.ipynb
@@ -6,17 +6,19 @@
    "source": [
     "![header1](../fidle/img/00-Fidle-header-01.png)\n",
     "\n",
-    "# Logistic regression, in pure tensorflow\n",
-    "Logistic Regression with Mini-Batch Gradient Descent using pure TensorFlow.  \n",
-    "Note: This notebook use tensoflow 2 in compatibility mode 1.  \n",
-    "A good reason to use Keras ;-)\n",
+    "# <!-- TITLE --> Logistic regression, in pure Tensorflow\n",
+    "<!-- DESC --> Logistic Regression with Mini-Batch Gradient Descent using pure TensorFlow. \n",
+    "<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
     "\n",
     "## Objectives :\n",
-    "A logistic regression has the objective of providing a probability of belonging to a class.  \n",
+    " - A logistic regression has the objective of providing a probability of belonging to a class.  \n",
+    " - Découvrir une implémentation 100% Tensorflow ..et apprendre à aimer Keras\n",
+    "\n",
+    "## What we're going to do :\n",
+    "\n",
     "X contains characteristics  \n",
     "y contains the probability of membership (1 or 0)  \n",
     "\n",
-    "## Principe :\n",
     "We'll look for a value of $\\theta$ such that the linear regression $\\theta^{T}X$ can be used to calculate our probability:  \n",
     "\n",
     "$\\hat{p} = h_\\theta(X) = \\sigma(\\theta^T{X})$  \n",
diff --git a/README.md b/README.md
index 88e6b3d..7eea359 100644
--- a/README.md
+++ b/README.md
@@ -6,26 +6,53 @@
 This repository contains all the documents and links of the **Fidle Training**.  
 
 The objectives of this training, co-organized by the Formation Permanente CNRS and the SARI and DEVLOG networks, are :
- - Understanding the **bases** of deep learning neural networks (Deep Learning)
+ - Understanding the **bases of deep learning** neural networks (Deep Learning)
  - Develop a **first experience** through simple and representative examples
  - Understand the different types of networks, their **architectures** and their **use cases**.
- - Understanding Tensorflow/Kera**s and Jupyter lab** technologies on the GPU
+ - Understanding **Tensorflow/Keras and Jupyter lab** technologies on the GPU
  - Apprehend the **academic computing environments** Tier-2 (meso) and/or Tier-1 (national)
 
-## Support and notebooks
+## Course materials
 Get the **[support of the presentations](Bientot)**  
-Note that useful information is also available in the **[wiki](https://gricad-gitlab.univ-grenoble-alpes.fr/talks/fidle/-/wikis/home)**  
+Useful information is also available in the [wiki](https://gricad-gitlab.univ-grenoble-alpes.fr/talks/fidle/-/wikis/home)
 
-All examples and practical work are available as Jupyter notebooks :
+**Jupyter notebooks :**
 
+<!-- DO NOT REMOVE THIS TAG !!! -->
 <!-- INDEX -->
 <!-- INDEX_BEGIN -->
+1. [Linear regression with direct resolution](LinearReg/01-Linear-Regression.ipynb)<br>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Direct determination of linear regression 
+1. [Linear regression with gradient descent](LinearReg/02-Gradient-descent.ipynb)<br>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;An example of gradient descent in the simple case of a linear regression.
+1. [Complexity Syndrome](LinearReg/03-Polynomial-Regression.ipynb)<br>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Illustration of the problem of complexity with the polynomial regression
+1. [Logistic regression, in pure Tensorflow](LinearReg/04-Logistic-Regression.ipynb)<br>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Logistic Regression with Mini-Batch Gradient Descent using pure TensorFlow. 
 1. [Regression with a Dense Network (DNN)](BHPD/01-DNN-Regression.ipynb)<br>
 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;A Simple regression with a Dense Neural Network (DNN) - BHPD dataset
 1. [Regression with a Dense Network (DNN) - Advanced code](BHPD/02-DNN-Regression-Premium.ipynb)<br>
 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;More advanced example of DNN network code - BHPD dataset
 1. [CNN with GTSRB dataset - Data analysis and preparation](GTSRB/01-Preparation-of-data.ipynb)<br>
 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Episode 1: Data analysis and creation of a usable dataset
+1. [CNN with GTSRB dataset - First convolutions](GTSRB/02-First-convolutions.ipynb)<br>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Episode 2 : First convolutions and first results
+1. [CNN with GTSRB dataset - Monitoring ](GTSRB/03-Tracking-and-visualizing.ipynb)<br>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Episode 3: Monitoring and analysing training, managing checkpoints
+1. [CNN with GTSRB dataset - Data augmentation ](GTSRB/04-Data-augmentation.ipynb)<br>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Episode 4: Improving the results with data augmentation
+1. [CNN with GTSRB dataset - Full convolutions ](GTSRB/05-Full-convolutions.ipynb)<br>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Episode 5: A lot of models, a lot of datasets and a lot of results.
+1. [CNN with GTSRB dataset - Full convolutions as a batch](GTSRB/06-Full-convolutions-batch.ipynb)<br>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Episode 6 : Run Full convolution notebook as a batch
+1. [Tensorboard with/from Jupyter ](GTSRB/99-Scripts-Tensorboard.ipynb)<br>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;4 ways to use Tensorboard from the Jupyter environment
+1. [Text embedding with IMDB](IMDB/01-Embedding-Keras.ipynb)<br>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;A very classical example of word embedding for text classification (sentiment analysis)
+1. [Text embedding with IMDB - Reloaded](IMDB/02-Prediction.ipynb)<br>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Example of reusing a previously saved model
+1. [Text embedding/LSTM model with IMDB](IMDB/03-LSTM-Keras.ipynb)<br>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Still the same problem, but with a network combining embedding and LSTM
 <!-- INDEX_END -->
 
 
diff --git a/fidle/pwk.py b/fidle/pwk.py
index 6186a4f..cf8f29a 100644
--- a/fidle/pwk.py
+++ b/fidle/pwk.py
@@ -27,7 +27,7 @@ from sklearn.metrics import confusion_matrix
 import pandas as pd
 import matplotlib
 import matplotlib.pyplot as plt
-# import seaborn as sn     #IDRIS : module en cours d'installation
+import seaborn as sn     #IDRIS : module en cours d'installation
 
 from IPython.display import display,Markdown,HTML
 
-- 
GitLab