Define RSuperviseL model and use MSE as the criterion

RNN_building_blocks.ipynb

@@ -19,6 +19,7 @@
    "source": [
     "import torch\n",
     "from torch.utils.data import Dataset\n",
+    "from torch import optim\n",
     "from torchvision import datasets, transforms\n",
     "import torch.nn.functional as F\n",
     "from torch import nn\n",
@@ -66,7 +67,48 @@
     "\n",
     "# mySeries dataset\n",
     "trainset = mySeries()\n",
-    "trainloader = torch.utils.data.DataLoader(trainset, batch_size=64)\n"
+    "trainloader = torch.utils.data.DataLoader(trainset, batch_size=64)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "outputs": [],
+   "source": [
+    "class RSuperviseL(nn.Module):\n",
+    "  def __init__(self):\n",
+    "    super().__init__()\n",
+    "    self.fc1 = nn.Linear(1, 1)\n",
+    "\n",
+    "  def forward(self, x):\n",
+    "\n",
+    "    self.fc1(x)\n",
+    "    return x\n",
+    "\n",
+    "model = RSuperviseL()"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "criterion = nn.MSELoss()\n",
+    "optimizer = optim.Adadelta(model.parameters(), lr=0.01)\n",
+    "num_epochs = 30\n",
+    "train_tracker, test_tracker, accuracy_tracker = [], [], []"
    ],
    "metadata": {
     "collapsed": false,