{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import argparse\n",
    "import torch\n",
    "import torch.nn as nn\n",
    "import torch.nn.functional as F\n",
    "import torch.optim as optim\n",
    "from torchvision import datasets, transforms"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Training settings\n",
    "batch_size = 64\n",
    "\n",
    "# MNIST Dataset\n",
    "train_dataset = datasets.MNIST(root='./data/',\n",
    "                               train=True,\n",
    "                               transform=transforms.ToTensor(),\n",
    "                               download=True)\n",
    "\n",
    "test_dataset = datasets.MNIST(root='./data/',\n",
    "                              train=False,\n",
    "                              transform=transforms.ToTensor())\n",
    "\n",
    "# Data Loader (Input Pipeline)\n",
    "train_loader = torch.utils.data.DataLoader(dataset=train_dataset,\n",
    "                                           batch_size=batch_size,\n",
    "                                           shuffle=True)\n",
    "\n",
    "test_loader = torch.utils.data.DataLoader(dataset=test_dataset,\n",
    "                                          batch_size=batch_size,\n",
    "                                          shuffle=False)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "class Net(nn.Module):\n",
    "\n",
    "    def __init__(self):\n",
    "        super(Net, self).__init__()\n",
    "        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)\n",
    "        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)\n",
    "        self.mp = nn.MaxPool2d(2)\n",
    "        self.fc = nn.Linear(320, 10)\n",
    "\n",
    "    def forward(self, x):\n",
    "        in_size = x.size(0)\n",
    "        x = F.relu(self.mp(self.conv1(x)))\n",
    "        x = F.relu(self.mp(self.conv2(x)))\n",
    "        x = x.view(in_size, -1)  # flatten the tensor\n",
    "        x = self.fc(x)\n",
    "        return F.log_softmax(x,dim=1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = Net()\n",
    "\n",
    "optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)\n",
    "criterion = nn.CrossEntropyLoss()\n",
    "\n",
    "\n",
    "def train(epoch):\n",
    "    model.train()\n",
    "    for batch_idx, (data, target) in enumerate(train_loader):\n",
    "        data, target = data, target\n",
    "        optimizer.zero_grad()\n",
    "        output = model(data)\n",
    "        loss = criterion(output, target)\n",
    "        loss.backward()\n",
    "        optimizer.step()\n",
    "        if batch_idx % 1000 == 0:\n",
    "            print('Train Epoch: {} [{}/{} ({:.0f}%)]\\tLoss: {:.6f}'.format(\n",
    "                epoch, batch_idx * len(data), len(train_loader.dataset),\n",
    "                100. * batch_idx / len(train_loader), loss.item()))\n",
    "\n",
    "\n",
    "def test():\n",
    "    model.eval()\n",
    "    test_loss = 0\n",
    "    correct = 0\n",
    "    for data, target in test_loader:\n",
    "        data, target = data, target\n",
    "        output = model(data)\n",
    "        # sum up batch loss\n",
    "        test_loss += criterion(output, target).item()\n",
    "        # get the index of the max log-probability\n",
    "        pred = output.data.max(1, keepdim=True)[1]\n",
    "        correct += pred.eq(target.data.view_as(pred)).cpu().sum()\n",
    "\n",
    "    test_loss /= len(test_loader.dataset)\n",
    "    print('\\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\\n'.format(\n",
    "        test_loss, correct, len(test_loader.dataset),\n",
    "        100. * correct / len(test_loader.dataset)))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train Epoch: 1 [0/60000 (0%)]\tLoss: 2.308939\n",
      "\n",
      "Test set: Average loss: 0.0028, Accuracy: 9469/10000 (94%)\n",
      "\n",
      "Train Epoch: 2 [0/60000 (0%)]\tLoss: 0.201025\n",
      "\n",
      "Test set: Average loss: 0.0017, Accuracy: 9676/10000 (96%)\n",
      "\n",
      "Train Epoch: 3 [0/60000 (0%)]\tLoss: 0.118083\n",
      "\n",
      "Test set: Average loss: 0.0013, Accuracy: 9774/10000 (97%)\n",
      "\n",
      "Train Epoch: 4 [0/60000 (0%)]\tLoss: 0.044904\n",
      "\n",
      "Test set: Average loss: 0.0011, Accuracy: 9786/10000 (97%)\n",
      "\n",
      "Train Epoch: 5 [0/60000 (0%)]\tLoss: 0.029464\n",
      "\n",
      "Test set: Average loss: 0.0011, Accuracy: 9801/10000 (98%)\n",
      "\n",
      "Train Epoch: 6 [0/60000 (0%)]\tLoss: 0.015576\n",
      "\n",
      "Test set: Average loss: 0.0010, Accuracy: 9802/10000 (98%)\n",
      "\n",
      "Train Epoch: 7 [0/60000 (0%)]\tLoss: 0.034443\n",
      "\n",
      "Test set: Average loss: 0.0008, Accuracy: 9825/10000 (98%)\n",
      "\n",
      "Train Epoch: 8 [0/60000 (0%)]\tLoss: 0.006708\n",
      "\n",
      "Test set: Average loss: 0.0008, Accuracy: 9832/10000 (98%)\n",
      "\n",
      "Train Epoch: 9 [0/60000 (0%)]\tLoss: 0.211187\n",
      "\n",
      "Test set: Average loss: 0.0008, Accuracy: 9821/10000 (98%)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "for epoch in range(1, 10):\n",
    "    train(epoch)\n",
    "    test()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Environment (conda_pytorch_p36)",
   "language": "python",
   "name": "conda_pytorch_p36"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}