pytorch_sample.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "source": [
    "## PyTorch 1.9 Training Sample w/ TensorBoard"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "outputs": [
    {
     "data": {
      "text/plain": "'1.9.0'"
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import torch\n",
    "torch.__version__"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.datasets import load_iris\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "iris = load_iris()\n",
    "x = iris['data']\n",
    "y = iris['target']\n",
    "names = iris['target_names']\n",
    "feature_names = iris['feature_names']\n",
    "\n",
    "scaler = StandardScaler()\n",
    "x_scaled = scaler.fit_transform(x)\n",
    "\n",
    "x_train, x_test, y_train, y_test = train_test_split(x_scaled, y, test_size=0.2, random_state=2021)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "outputs": [
    {
     "data": {
      "text/plain": "Model(\n  (layer1): Linear(in_features=4, out_features=50, bias=True)\n  (layer2): Linear(in_features=50, out_features=50, bias=True)\n  (layer3): Linear(in_features=50, out_features=3, bias=True)\n)"
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from torch.nn import functional as F\n",
    "from torch import nn\n",
    "from torch.autograd import Variable\n",
    "\n",
    "class Model(nn.Module):\n",
    "    def __init__(self, input_dim):\n",
    "        super().__init__()\n",
    "        self.layer1 = nn.Linear(input_dim, 50)\n",
    "        self.layer2 = nn.Linear(50, 50)\n",
    "        self.layer3 = nn.Linear(50, 3)\n",
    "\n",
    "    def forward(self, x):\n",
    "        x = F.relu(self.layer1(x))\n",
    "        x = F.relu(self.layer2(x))\n",
    "        x = F.softmax(self.layer3(x), dim=1)\n",
    "        return x\n",
    "\n",
    "model = Model(x_train.shape[1])\n",
    "optimizer = torch.optim.Adam(model.parameters(), lr=0.001)\n",
    "loss_fn = nn.CrossEntropyLoss()\n",
    "model"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 100/100 [00:00<00:00, 896.43it/s]\n"
     ]
    }
   ],
   "source": [
    "import tqdm\n",
    "import numpy as np\n",
    "from torch.utils.tensorboard import SummaryWriter\n",
    "\n",
    "writer = SummaryWriter(log_dir=\"/tmp/iris/exp1\")\n",
    "\n",
    "EPOCHS = 100\n",
    "x_train = Variable(torch.from_numpy(x_train)).float()\n",
    "y_train = Variable(torch.from_numpy(y_train)).long()\n",
    "x_test = Variable(torch.from_numpy(x_test)).float()\n",
    "y_test = Variable(torch.from_numpy(y_test)).long()\n",
    "\n",
    "loss_list = np.zeros((EPOCHS,))\n",
    "accuracy_list = np.zeros((EPOCHS,))\n",
    "\n",
    "for epoch in tqdm.trange(EPOCHS):\n",
    "    # zero the parameter gradients\n",
    "    optimizer.zero_grad()\n",
    "\n",
    "    # forward + backward + optimize\n",
    "    y_pred = model(x_train)\n",
    "    loss = loss_fn(y_pred, y_train)\n",
    "    loss.backward()\n",
    "    optimizer.step()\n",
    "    loss_list[epoch] = loss.item()\n",
    "    writer.add_scalar('Loss/train', loss.item(), epoch)\n",
    "\n",
    "    with torch.no_grad():\n",
    "        y_pred = model(x_test)\n",
    "        correct = (torch.argmax(y_pred, dim=1) == y_test).type(torch.FloatTensor)\n",
    "        accuracy_list[epoch] = correct.mean()\n",
    "        writer.add_scalar('Accuracy/train', correct.mean(), epoch)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "outputs": [
    {
     "data": {
      "text/plain": "Launching TensorBoard..."
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%load_ext tensorboard\n",
    "%tensorboard --logdir /tmp/iris/exp1"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Known TensorBoard instances:\n",
      "  - port 6006: logdir /tmp/iris/exp1 (started 0:00:01 ago; pid 55477)\n"
     ]
    }
   ],
   "source": [
    "from tensorboard import notebook\n",
    "notebook.list()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Selecting TensorBoard with logdir /tmp/iris/exp1 (started 0:00:02 ago; port 6006, pid 55477).\n"
     ]
    },
    {
     "data": {
      "text/plain": "<IPython.core.display.HTML object>",
      "text/html": "\n      <iframe id=\"tensorboard-frame-771db739d6bd12\" width=\"100%\" height=\"1000\" frameborder=\"0\">\n      </iframe>\n      <script>\n        (function() {\n          const frame = document.getElementById(\"tensorboard-frame-771db739d6bd12\");\n          const url = new URL(\"/\", window.location);\n          const port = 6006;\n          if (port) {\n            url.port = port;\n          }\n          frame.src = url;\n        })();\n      </script>\n    "
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "notebook.display(port=6006, height=1000)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}