rename the saved mnist model to .pt

Author: motus

load/mnist-model.tar renamed to load/mnist-model.pt

@@ -17,10 +17,8 @@
     "    'epoch': args.epochs, # == 10\n",
     "    'model_state_dict': model.state_dict(),\n",
     "    'optimizer_state_dict': optimizer.state_dict()\n",
-    "}, './mnist-model.tar')\n",
-    "```\n",
-    "\n",
-    "(`.tar` extension for saved models is just a PyTorch convention)"
+    "}, './mnist-model.pt')\n",
+    "```"
    ]
   },
   {
@@ -34,26 +32,34 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "dict_keys(['epoch', 'model_state_dict', 'optimizer_state_dict'])"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'dict'>\n",
+      "dict_keys(['epoch', 'model_state_dict', 'optimizer_state_dict'])\n",
+      "epoch = 10\n"
+     ]
     }
    ],
    "source": [
     "import torch\n",
     "\n",
-    "saved_params = torch.load('./mnist-model.tar')\n",
+    "model_state = torch.load('./mnist-model.pt')\n",
     "\n",
-    "saved_params.keys()"
+    "print(type(model_state))\n",
+    "print(model_state.keys())\n",
+    "print('epoch =', model_state['epoch'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "So the `torch.load()` function just reads back the dictionary that was passed to `torch.save()`, and for basic Python types it is not different from Python standard [pickle](https://docs.python.org/3.5/library/pickle.html) module (in fact, it *is* a pickle)."
    ]
   },
   {