diff --git a/GTSRB/03-Tracking-and-visualizing.ipynb b/GTSRB/03-Tracking-and-visualizing.ipynb
index c29e62ed168df10f3a28348d91b75325efd55b40..9e11231ca2cf6d9ce4c7c93c8154a4d42555d035 100644
--- a/GTSRB/03-Tracking-and-visualizing.ipynb
+++ b/GTSRB/03-Tracking-and-visualizing.ipynb
@@ -23,7 +23,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -32,7 +32,7 @@
      "text": [
       "IDLE 2020 - Practical Work Module\n",
       "  Version            : 0.1.1\n",
-      "  Run time           : Monday 6 January 2020, 15:56:03\n",
+      "  Run time           : Monday 6 January 2020, 20:52:54\n",
       "  Matplotlib style   : idle/talk.mplstyle\n",
       "  TensorFlow version : 2.0.0\n",
       "  Keras version      : 2.2.4-tf\n"
@@ -67,7 +67,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -76,8 +76,8 @@
      "text": [
       "Dataset loaded, size=247.6 Mo\n",
       "\n",
-      "CPU times: user 0 ns, sys: 328 ms, total: 328 ms\n",
-      "Wall time: 342 ms\n"
+      "CPU times: user 0 ns, sys: 297 ms, total: 297 ms\n",
+      "Wall time: 330 ms\n"
      ]
     }
    ],
@@ -115,7 +115,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -172,44 +172,48 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
-    "batch_size  =  128\n",
+    "batch_size  =  64\n",
     "num_classes =  43\n",
-    "epochs      =  5"
+    "epochs      =  20"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Model: \"sequential_10\"\n",
+      "Model: \"sequential\"\n",
       "_________________________________________________________________\n",
       "Layer (type)                 Output Shape              Param #   \n",
       "=================================================================\n",
-      "conv2d_11 (Conv2D)           (None, 23, 23, 96)        960       \n",
+      "conv2d (Conv2D)              (None, 23, 23, 96)        960       \n",
+      "_________________________________________________________________\n",
+      "max_pooling2d (MaxPooling2D) (None, 11, 11, 96)        0         \n",
       "_________________________________________________________________\n",
-      "max_pooling2d_20 (MaxPooling (None, 11, 11, 96)        0         \n",
+      "conv2d_1 (Conv2D)            (None, 9, 9, 192)         166080    \n",
       "_________________________________________________________________\n",
-      "max_pooling2d_21 (MaxPooling (None, 5, 5, 96)          0         \n",
+      "max_pooling2d_1 (MaxPooling2 (None, 4, 4, 192)         0         \n",
       "_________________________________________________________________\n",
-      "flatten_10 (Flatten)         (None, 2400)              0         \n",
+      "flatten (Flatten)            (None, 3072)              0         \n",
       "_________________________________________________________________\n",
-      "dense_31 (Dense)             (None, 2400)              5762400   \n",
+      "dense (Dense)                (None, 3072)              9440256   \n",
       "_________________________________________________________________\n",
-      "dense_32 (Dense)             (None, 500)               1200500   \n",
+      "dense_1 (Dense)              (None, 500)               1536500   \n",
       "_________________________________________________________________\n",
-      "dense_33 (Dense)             (None, 43)                21543     \n",
+      "dense_2 (Dense)              (None, 500)               250500    \n",
+      "_________________________________________________________________\n",
+      "dense_3 (Dense)              (None, 43)                21543     \n",
       "=================================================================\n",
-      "Total params: 6,985,403\n",
-      "Trainable params: 6,985,403\n",
+      "Total params: 11,415,839\n",
+      "Trainable params: 11,415,839\n",
       "Non-trainable params: 0\n",
       "_________________________________________________________________\n"
      ]
@@ -219,12 +223,11 @@
     "model = keras.models.Sequential()\n",
     "model.add( keras.layers.Conv2D(96, (3,3), activation='relu', input_shape=(img_lx, img_ly, img_lz)))\n",
     "model.add( keras.layers.MaxPooling2D((2, 2)))\n",
+    "model.add( keras.layers.Conv2D(192, (3, 3), activation='relu'))\n",
     "model.add( keras.layers.MaxPooling2D((2, 2)))\n",
-    "# model.add( keras.layers.Conv2D(192, (3, 3), activation='relu'))\n",
-    "# model.add( keras.layers.MaxPooling2D((2, 2)))\n",
     "model.add( keras.layers.Flatten()) \n",
-    "model.add( keras.layers.Dense(2400, activation='relu'))\n",
-    "# model.add( keras.layers.Dense(500, activation='relu'))\n",
+    "model.add( keras.layers.Dense(3072, activation='relu'))\n",
+    "model.add( keras.layers.Dense(500, activation='relu'))\n",
     "model.add( keras.layers.Dense(500, activation='relu'))\n",
     "model.add( keras.layers.Dense(43, activation='softmax'))\n",
     "model.summary()\n",
@@ -248,14 +251,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
     "# reload(ooo)\n",
     "# ---- Callback for tensorboard\n",
     "log_dir=\"./run/logs/\" + ooo.tag_now()\n",
-    "tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir)"
+    "tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)"
    ]
   },
   {
@@ -267,33 +270,63 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Train on 39209 samples, validate on 12630 samples\n",
-      "Epoch 1/5\n",
-      "39209/39209 [==============================] - 23s 586us/sample - loss: 1.4107 - accuracy: 0.6116 - val_loss: 0.7740 - val_accuracy: 0.8112\n",
-      "Epoch 2/5\n",
-      "39209/39209 [==============================] - 25s 632us/sample - loss: 0.3571 - accuracy: 0.8982 - val_loss: 0.6292 - val_accuracy: 0.8446\n",
-      "Epoch 3/5\n",
-      "39209/39209 [==============================] - 25s 643us/sample - loss: 0.1988 - accuracy: 0.9445 - val_loss: 0.5845 - val_accuracy: 0.8658\n",
-      "Epoch 4/5\n",
-      "39209/39209 [==============================] - 25s 644us/sample - loss: 0.1316 - accuracy: 0.9641 - val_loss: 0.5571 - val_accuracy: 0.8779\n",
-      "Epoch 5/5\n",
-      "39209/39209 [==============================] - 28s 704us/sample - loss: 0.1001 - accuracy: 0.9724 - val_loss: 0.5844 - val_accuracy: 0.8629\n",
-      "CPU times: user 12min 44s, sys: 39.9 s, total: 13min 24s\n",
-      "Wall time: 2min 5s\n"
+      "Train on 3000 samples, validate on 12630 samples\n",
+      "Epoch 1/20\n",
+      "3000/3000 [==============================] - 12s 4ms/sample - loss: 3.4839 - accuracy: 0.0740 - val_loss: 3.1409 - val_accuracy: 0.1995\n",
+      "Epoch 2/20\n",
+      "3000/3000 [==============================] - 12s 4ms/sample - loss: 2.4676 - accuracy: 0.3067 - val_loss: 2.1162 - val_accuracy: 0.3968\n",
+      "Epoch 3/20\n",
+      "3000/3000 [==============================] - 13s 4ms/sample - loss: 1.4458 - accuracy: 0.5543 - val_loss: 1.4468 - val_accuracy: 0.5862\n",
+      "Epoch 4/20\n",
+      "3000/3000 [==============================] - 14s 5ms/sample - loss: 0.9291 - accuracy: 0.7067 - val_loss: 1.1903 - val_accuracy: 0.6622\n",
+      "Epoch 5/20\n",
+      "3000/3000 [==============================] - 14s 5ms/sample - loss: 0.6027 - accuracy: 0.8030 - val_loss: 0.8067 - val_accuracy: 0.7900\n",
+      "Epoch 6/20\n",
+      "3000/3000 [==============================] - 14s 5ms/sample - loss: 0.3835 - accuracy: 0.8670 - val_loss: 0.8453 - val_accuracy: 0.7925\n",
+      "Epoch 7/20\n",
+      "3000/3000 [==============================] - 14s 5ms/sample - loss: 0.2666 - accuracy: 0.9157 - val_loss: 0.7578 - val_accuracy: 0.8256\n",
+      "Epoch 8/20\n",
+      "3000/3000 [==============================] - 14s 5ms/sample - loss: 0.2045 - accuracy: 0.9307 - val_loss: 0.8074 - val_accuracy: 0.8300\n",
+      "Epoch 9/20\n",
+      "3000/3000 [==============================] - 14s 5ms/sample - loss: 0.1370 - accuracy: 0.9567 - val_loss: 0.7071 - val_accuracy: 0.8588\n",
+      "Epoch 10/20\n",
+      "3000/3000 [==============================] - 12s 4ms/sample - loss: 0.0964 - accuracy: 0.9707 - val_loss: 0.7275 - val_accuracy: 0.8622\n",
+      "Epoch 11/20\n",
+      "3000/3000 [==============================] - 13s 4ms/sample - loss: 0.0654 - accuracy: 0.9803 - val_loss: 0.7073 - val_accuracy: 0.8661\n",
+      "Epoch 12/20\n",
+      "3000/3000 [==============================] - 13s 4ms/sample - loss: 0.0806 - accuracy: 0.9757 - val_loss: 0.8265 - val_accuracy: 0.8637\n",
+      "Epoch 13/20\n",
+      "3000/3000 [==============================] - 13s 4ms/sample - loss: 0.0854 - accuracy: 0.9743 - val_loss: 0.7547 - val_accuracy: 0.8635\n",
+      "Epoch 14/20\n",
+      "3000/3000 [==============================] - 14s 5ms/sample - loss: 0.0463 - accuracy: 0.9860 - val_loss: 0.7248 - val_accuracy: 0.8846\n",
+      "Epoch 15/20\n",
+      "3000/3000 [==============================] - 14s 5ms/sample - loss: 0.0425 - accuracy: 0.9917 - val_loss: 0.7266 - val_accuracy: 0.8785\n",
+      "Epoch 16/20\n",
+      "3000/3000 [==============================] - 12s 4ms/sample - loss: 0.0322 - accuracy: 0.9923 - val_loss: 0.7501 - val_accuracy: 0.8777\n",
+      "Epoch 17/20\n",
+      "3000/3000 [==============================] - 14s 5ms/sample - loss: 0.0375 - accuracy: 0.9870 - val_loss: 0.7782 - val_accuracy: 0.8811\n",
+      "Epoch 18/20\n",
+      "3000/3000 [==============================] - 14s 5ms/sample - loss: 0.0557 - accuracy: 0.9857 - val_loss: 0.6846 - val_accuracy: 0.8760\n",
+      "Epoch 19/20\n",
+      "3000/3000 [==============================] - 14s 5ms/sample - loss: 0.0100 - accuracy: 0.9987 - val_loss: 0.7676 - val_accuracy: 0.8873\n",
+      "Epoch 20/20\n",
+      "3000/3000 [==============================] - 14s 5ms/sample - loss: 0.0025 - accuracy: 1.0000 - val_loss: 0.7481 - val_accuracy: 0.8993\n",
+      "CPU times: user 17min 9s, sys: 5min 55s, total: 23min 4s\n",
+      "Wall time: 4min 29s\n"
      ]
     }
    ],
    "source": [
     "%%time\n",
     "\n",
-    "history = model.fit(  x_train, y_train,\n",
+    "history = model.fit(  x_train[:3000], y_train[:3000],\n",
     "                      batch_size=batch_size,\n",
     "                      epochs=epochs,\n",
     "                      verbose=1,\n",
@@ -310,18 +343,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Test loss      : 0.4795\n",
-      "Test accuracy  : 0.8982\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "score = model.evaluate(x_test, y_test, verbose=0)\n",
     "\n",
@@ -339,34 +363,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 576x432 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 576x432 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "ooo.plot_history(history)"
    ]
diff --git a/GTSRB/run/logs/2020-01-06_21h00m17s/train/events.out.tfevents.1578340818.Oban.497.380.v2 b/GTSRB/run/logs/2020-01-06_21h00m17s/train/events.out.tfevents.1578340818.Oban.497.380.v2
new file mode 100644
index 0000000000000000000000000000000000000000..be538f188fbc909ec7e313864d985c8a7572f32c
Binary files /dev/null and b/GTSRB/run/logs/2020-01-06_21h00m17s/train/events.out.tfevents.1578340818.Oban.497.380.v2 differ
diff --git a/GTSRB/run/logs/2020-01-06_21h00m17s/train/events.out.tfevents.1578340819.Oban.profile-empty b/GTSRB/run/logs/2020-01-06_21h00m17s/train/events.out.tfevents.1578340819.Oban.profile-empty
new file mode 100644
index 0000000000000000000000000000000000000000..8a39d83078b75df259e50cf6a6b238156eb30817
Binary files /dev/null and b/GTSRB/run/logs/2020-01-06_21h00m17s/train/events.out.tfevents.1578340819.Oban.profile-empty differ
diff --git a/GTSRB/run/logs/2020-01-06_21h00m17s/train/plugins/profile/2020-01-06_21-00-19/local.trace b/GTSRB/run/logs/2020-01-06_21h00m17s/train/plugins/profile/2020-01-06_21-00-19/local.trace
new file mode 100644
index 0000000000000000000000000000000000000000..39c92776a4219e7e59f20dc55d7d75daa7bf3187
Binary files /dev/null and b/GTSRB/run/logs/2020-01-06_21h00m17s/train/plugins/profile/2020-01-06_21-00-19/local.trace differ
diff --git a/GTSRB/run/logs/2020-01-06_21h00m17s/validation/events.out.tfevents.1578340830.Oban.497.2052.v2 b/GTSRB/run/logs/2020-01-06_21h00m17s/validation/events.out.tfevents.1578340830.Oban.497.2052.v2
new file mode 100644
index 0000000000000000000000000000000000000000..7aa8f0a84af8e971ee0b08d06bbfbabfde6f2bdd
Binary files /dev/null and b/GTSRB/run/logs/2020-01-06_21h00m17s/validation/events.out.tfevents.1578340830.Oban.497.2052.v2 differ