retrained model and got it ready for a demo of over fitting

Week1.ipynb

@@ -20,7 +20,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -38,7 +38,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -85,7 +85,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -144,6 +144,18 @@
     "## Train the Model"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "batch_size = 128\n",
+    "epochs = 15\n",
+    "\n",
+    "model.compile(loss=\"categorical_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 5,
@@ -154,41 +166,41 @@
      "output_type": "stream",
      "text": [
       "Epoch 1/15\n",
-      "422/422 [==============================] - 6s 3ms/step - loss: 0.3744 - accuracy: 0.8868 - val_loss: 0.0892 - val_accuracy: 0.9763\n",
+      "422/422 [==============================] - 4s 3ms/step - loss: 0.3724 - accuracy: 0.8837 - val_loss: 0.0810 - val_accuracy: 0.9785\n",
       "Epoch 2/15\n",
-      "422/422 [==============================] - 1s 3ms/step - loss: 0.1177 - accuracy: 0.9634 - val_loss: 0.0660 - val_accuracy: 0.9817\n",
+      "422/422 [==============================] - 1s 3ms/step - loss: 0.1118 - accuracy: 0.9671 - val_loss: 0.0562 - val_accuracy: 0.9852\n",
       "Epoch 3/15\n",
-      "422/422 [==============================] - 1s 3ms/step - loss: 0.0876 - accuracy: 0.9732 - val_loss: 0.0480 - val_accuracy: 0.9865\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0835 - accuracy: 0.9739 - val_loss: 0.0481 - val_accuracy: 0.9872\n",
       "Epoch 4/15\n",
-      "422/422 [==============================] - 1s 3ms/step - loss: 0.0738 - accuracy: 0.9774 - val_loss: 0.0462 - val_accuracy: 0.9872\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0700 - accuracy: 0.9787 - val_loss: 0.0404 - val_accuracy: 0.9898\n",
       "Epoch 5/15\n",
-      "422/422 [==============================] - 1s 3ms/step - loss: 0.0642 - accuracy: 0.9805 - val_loss: 0.0440 - val_accuracy: 0.9872\n",
+      "422/422 [==============================] - 1s 3ms/step - loss: 0.0604 - accuracy: 0.9815 - val_loss: 0.0381 - val_accuracy: 0.9910\n",
       "Epoch 6/15\n",
-      "422/422 [==============================] - 1s 2ms/step - loss: 0.0585 - accuracy: 0.9818 - val_loss: 0.0373 - val_accuracy: 0.9898\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0559 - accuracy: 0.9826 - val_loss: 0.0354 - val_accuracy: 0.9903\n",
       "Epoch 7/15\n",
-      "422/422 [==============================] - 1s 3ms/step - loss: 0.0544 - accuracy: 0.9832 - val_loss: 0.0348 - val_accuracy: 0.9908\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0505 - accuracy: 0.9829 - val_loss: 0.0338 - val_accuracy: 0.9903\n",
       "Epoch 8/15\n",
-      "422/422 [==============================] - 1s 3ms/step - loss: 0.0495 - accuracy: 0.9845 - val_loss: 0.0342 - val_accuracy: 0.9907\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0484 - accuracy: 0.9847 - val_loss: 0.0296 - val_accuracy: 0.9923\n",
       "Epoch 9/15\n",
-      "422/422 [==============================] - 1s 2ms/step - loss: 0.0462 - accuracy: 0.9853 - val_loss: 0.0313 - val_accuracy: 0.9910\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0443 - accuracy: 0.9860 - val_loss: 0.0333 - val_accuracy: 0.9912\n",
       "Epoch 10/15\n",
-      "422/422 [==============================] - 1s 2ms/step - loss: 0.0444 - accuracy: 0.9858 - val_loss: 0.0320 - val_accuracy: 0.9907\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0422 - accuracy: 0.9869 - val_loss: 0.0308 - val_accuracy: 0.9927\n",
       "Epoch 11/15\n",
-      "422/422 [==============================] - 1s 2ms/step - loss: 0.0418 - accuracy: 0.9872 - val_loss: 0.0303 - val_accuracy: 0.9913\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0397 - accuracy: 0.9874 - val_loss: 0.0321 - val_accuracy: 0.9922\n",
       "Epoch 12/15\n",
-      "422/422 [==============================] - 1s 3ms/step - loss: 0.0410 - accuracy: 0.9874 - val_loss: 0.0276 - val_accuracy: 0.9922\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0375 - accuracy: 0.9875 - val_loss: 0.0269 - val_accuracy: 0.9928\n",
       "Epoch 13/15\n",
-      "422/422 [==============================] - 1s 3ms/step - loss: 0.0381 - accuracy: 0.9875 - val_loss: 0.0292 - val_accuracy: 0.9912\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0355 - accuracy: 0.9886 - val_loss: 0.0296 - val_accuracy: 0.9925\n",
       "Epoch 14/15\n",
-      "422/422 [==============================] - 1s 2ms/step - loss: 0.0368 - accuracy: 0.9879 - val_loss: 0.0291 - val_accuracy: 0.9920\n",
+      "422/422 [==============================] - 1s 2ms/step - loss: 0.0340 - accuracy: 0.9888 - val_loss: 0.0291 - val_accuracy: 0.9928\n",
       "Epoch 15/15\n",
-      "422/422 [==============================] - 1s 2ms/step - loss: 0.0356 - accuracy: 0.9888 - val_loss: 0.0257 - val_accuracy: 0.9925\n"
+      "422/422 [==============================] - 1s 3ms/step - loss: 0.0321 - accuracy: 0.9894 - val_loss: 0.0277 - val_accuracy: 0.9927\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "<keras.callbacks.History at 0x1c9d4871f40>"
+       "<keras.callbacks.History at 0x14a08dfc3d0>"
       ]
      },
      "execution_count": 5,
@@ -197,10 +209,7 @@
     }
    ],
    "source": [
-    "batch_size = 128\n",
-    "epochs = 15\n",
-    "\n",
-    "model.compile(loss=\"categorical_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])\n",
+    "# This line can be run multiple times, but keep in mind that the model will probably be over fitting\n",
     "\n",
     "model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.1)"
    ]
@@ -221,8 +230,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Test loss: 0.026043808087706566\n",
-      "Test accuracy: 0.9907000064849854\n"
+      "Test loss: 0.02324853651225567\n",
+      "Test accuracy: 0.9922000169754028\n"
      ]
     }
    ],

mnist.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6fb1eb48a18fd769f17f093224aa1246b41d132a56a4cbe28e0b73382bd7e28
+oid sha256:6b9d7830249bb932ad3715ba3d277c9415cd8a8a4c6d100eb6a1f8568f58fa8f
 size 455304