Upload 3 files

mnist.ipynb

@@ -0,0 +1,139 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "import torchvision\n",
+    "from torch import nn, optim\n",
+    "from torch.autograd import Variable\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mnist_data = torchvision.datasets.MNIST(\n",
+    "    \"mnist_data\", train=True, transform=torchvision.transforms.ToTensor(), download=True\n",
+    ")\n",
+    "mnist_dataloader = torch.utils.data.DataLoader(mnist_data, batch_size=50)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class Mnet(nn.Module):\n",
+    "    def __init__(self):\n",
+    "        super(Mnet, self).__init__()\n",
+    "        self.linear1 = nn.Linear(28 * 28, 400)\n",
+    "        self.linear2 = nn.Linear(400, 200)\n",
+    "        self.linear3 = nn.Linear(200, 100)\n",
+    "        self.linear4 = nn.Linear(100, 50)\n",
+    "        self.linear5 = nn.Linear(50, 25)\n",
+    "        self.final_linear = nn.Linear(25, 10)\n",
+    "\n",
+    "        self.relu = nn.ReLU()\n",
+    "\n",
+    "    def forward(self, images):\n",
+    "        x = images.view(-1, 28 * 28)\n",
+    "        x = self.relu(self.linear1(x))\n",
+    "        x = self.relu(self.linear2(x))\n",
+    "        x = self.relu(self.linear3(x))\n",
+    "        x = self.relu(self.linear4(x))\n",
+    "        x = self.relu(self.linear5(x))\n",
+    "        x = self.final_linear(x)\n",
+    "        return x"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 50/50 [21:18<00:00, 25.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "final loss: 1.1586851087486139e-06\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from tqdm import tqdm\n",
+    "model = Mnet()\n",
+    "cec_loss = nn.CrossEntropyLoss()\n",
+    "params = model.parameters()\n",
+    "optimizer = optim.Adam(params=params, lr=0.001)\n",
+    "\n",
+    "n_epochs = 50\n",
+    "n_iterations = 0\n",
+    "\n",
+    "for e in tqdm(range(n_epochs)):\n",
+    "    for i, (images, labels) in enumerate(mnist_dataloader):\n",
+    "        output = model(images)\n",
+    "\n",
+    "        model.zero_grad()\n",
+    "        loss = cec_loss(output, labels)\n",
+    "        loss.backward()\n",
+    "\n",
+    "        optimizer.step()\n",
+    "        n_iterations+=1\n",
+    "\n",
+    "print(f'final loss: {loss.item()}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "torch.save(model, \"mnistmodel.pt\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

mnist_test.ipynb

@@ -0,0 +1,335 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch, torchvision\n",
+    "from torch import nn"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class Mnet(nn.Module):\n",
+    "    def __init__(self):\n",
+    "        super(Mnet, self).__init__()\n",
+    "        self.linear1 = nn.Linear(28 * 28, 400)\n",
+    "        self.linear2 = nn.Linear(400, 200)\n",
+    "        self.linear3 = nn.Linear(200, 100)\n",
+    "        self.linear4 = nn.Linear(100, 50)\n",
+    "        self.linear5 = nn.Linear(50, 25)\n",
+    "        self.final_linear = nn.Linear(25, 10)\n",
+    "\n",
+    "        self.relu = nn.ReLU()\n",
+    "\n",
+    "    def forward(self, images):\n",
+    "        x = images.view(-1, 28 * 28)\n",
+    "        x = self.relu(self.linear1(x))\n",
+    "        x = self.relu(self.linear2(x))\n",
+    "        x = self.relu(self.linear3(x))\n",
+    "        x = self.relu(self.linear4(x))\n",
+    "        x = self.relu(self.linear5(x))\n",
+    "        x = self.final_linear(x)\n",
+    "        return x"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = torch.load(\"mnistmodel.pt\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "T = torchvision.transforms.Compose([torchvision.transforms.ToTensor()])\n",
+    "test_data = torchvision.datasets.MNIST(\"mnist_data\", train=False, transform=T, download=True)\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "#image, label = test_data[9016]\n",
+    "#print(label)\n",
+    "#plt.imshow(image[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "wrong answer 149\n",
+      "wrong answer 151\n",
+      "wrong answer 247\n",
+      "wrong answer 259\n",
+      "wrong answer 268\n",
+      "wrong answer 340\n",
+      "wrong answer 445\n",
+      "wrong answer 495\n",
+      "wrong answer 582\n",
+      "wrong answer 684\n",
+      "wrong answer 720\n",
+      "wrong answer 844\n",
+      "wrong answer 938\n",
+      "wrong answer 947\n",
+      "wrong answer 1014\n",
+      "wrong answer 1039\n",
+      "wrong answer 1200\n",
+      "wrong answer 1226\n",
+      "wrong answer 1232\n",
+      "wrong answer 1242\n",
+      "wrong answer 1247\n",
+      "wrong answer 1260\n",
+      "wrong answer 1289\n",
+      "wrong answer 1319\n",
+      "wrong answer 1328\n",
+      "wrong answer 1393\n",
+      "wrong answer 1414\n",
+      "wrong answer 1425\n",
+      "wrong answer 1530\n",
+      "wrong answer 1553\n",
+      "wrong answer 1569\n",
+      "wrong answer 1681\n",
+      "wrong answer 1717\n",
+      "wrong answer 1751\n",
+      "wrong answer 1754\n",
+      "wrong answer 1790\n",
+      "wrong answer 1800\n",
+      "wrong answer 1850\n",
+      "wrong answer 1878\n",
+      "wrong answer 1880\n",
+      "wrong answer 1901\n",
+      "wrong answer 1952\n",
+      "wrong answer 2024\n",
+      "wrong answer 2109\n",
+      "wrong answer 2118\n",
+      "wrong answer 2130\n",
+      "wrong answer 2135\n",
+      "wrong answer 2224\n",
+      "wrong answer 2293\n",
+      "wrong answer 2369\n",
+      "wrong answer 2387\n",
+      "wrong answer 2406\n",
+      "wrong answer 2414\n",
+      "wrong answer 2422\n",
+      "wrong answer 2488\n",
+      "wrong answer 2582\n",
+      "wrong answer 2597\n",
+      "wrong answer 2648\n",
+      "wrong answer 2654\n",
+      "wrong answer 2720\n",
+      "wrong answer 2863\n",
+      "wrong answer 2877\n",
+      "wrong answer 2896\n",
+      "wrong answer 2921\n",
+      "wrong answer 2927\n",
+      "wrong answer 2939\n",
+      "wrong answer 2953\n",
+      "wrong answer 2979\n",
+      "wrong answer 3060\n",
+      "wrong answer 3073\n",
+      "wrong answer 3117\n",
+      "wrong answer 3263\n",
+      "wrong answer 3284\n",
+      "wrong answer 3394\n",
+      "wrong answer 3422\n",
+      "wrong answer 3475\n",
+      "wrong answer 3503\n",
+      "wrong answer 3520\n",
+      "wrong answer 3558\n",
+      "wrong answer 3565\n",
+      "wrong answer 3567\n",
+      "wrong answer 3597\n",
+      "wrong answer 3727\n",
+      "wrong answer 3767\n",
+      "wrong answer 3776\n",
+      "wrong answer 3796\n",
+      "wrong answer 3808\n",
+      "wrong answer 3811\n",
+      "wrong answer 3817\n",
+      "wrong answer 3818\n",
+      "wrong answer 3869\n",
+      "wrong answer 3893\n",
+      "wrong answer 3906\n",
+      "wrong answer 3941\n",
+      "wrong answer 3943\n",
+      "wrong answer 3970\n",
+      "wrong answer 3985\n",
+      "wrong answer 4000\n",
+      "wrong answer 4065\n",
+      "wrong answer 4075\n",
+      "wrong answer 4140\n",
+      "wrong answer 4163\n",
+      "wrong answer 4176\n",
+      "wrong answer 4199\n",
+      "wrong answer 4224\n",
+      "wrong answer 4248\n",
+      "wrong answer 4289\n",
+      "wrong answer 4350\n",
+      "wrong answer 4369\n",
+      "wrong answer 4437\n",
+      "wrong answer 4497\n",
+      "wrong answer 4504\n",
+      "wrong answer 4536\n",
+      "wrong answer 4547\n",
+      "wrong answer 4571\n",
+      "wrong answer 4601\n",
+      "wrong answer 4731\n",
+      "wrong answer 4740\n",
+      "wrong answer 4761\n",
+      "wrong answer 4807\n",
+      "wrong answer 4823\n",
+      "wrong answer 4833\n",
+      "wrong answer 4956\n",
+      "wrong answer 4966\n",
+      "wrong answer 5078\n",
+      "wrong answer 5265\n",
+      "wrong answer 5331\n",
+      "wrong answer 5457\n",
+      "wrong answer 5586\n",
+      "wrong answer 5676\n",
+      "wrong answer 5734\n",
+      "wrong answer 5749\n",
+      "wrong answer 5887\n",
+      "wrong answer 5888\n",
+      "wrong answer 5955\n",
+      "wrong answer 5973\n",
+      "wrong answer 6011\n",
+      "wrong answer 6059\n",
+      "wrong answer 6555\n",
+      "wrong answer 6571\n",
+      "wrong answer 6597\n",
+      "wrong answer 6603\n",
+      "wrong answer 6625\n",
+      "wrong answer 6641\n",
+      "wrong answer 6651\n",
+      "wrong answer 6755\n",
+      "wrong answer 6783\n",
+      "wrong answer 6847\n",
+      "wrong answer 7434\n",
+      "wrong answer 7921\n",
+      "wrong answer 8094\n",
+      "wrong answer 8246\n",
+      "wrong answer 8311\n",
+      "wrong answer 8382\n",
+      "wrong answer 8408\n",
+      "wrong answer 8456\n",
+      "wrong answer 8522\n",
+      "wrong answer 8527\n",
+      "wrong answer 9009\n",
+      "wrong answer 9015\n",
+      "wrong answer 9024\n",
+      "wrong answer 9280\n",
+      "wrong answer 9587\n",
+      "wrong answer 9634\n",
+      "wrong answer 9664\n",
+      "wrong answer 9669\n",
+      "wrong answer 9679\n",
+      "wrong answer 9729\n",
+      "wrong answer 9745\n",
+      "wrong answer 9749\n",
+      "wrong answer 9768\n",
+      "wrong answer 9770\n",
+      "wrong answer 9792\n",
+      "wrong answer 9808\n",
+      "wrong answer 9858\n",
+      "9825 10000\n"
+     ]
+    }
+   ],
+   "source": [
+    "#정답률\n",
+    "\n",
+    "total_test = len(test_data)\n",
+    "correct_answer = 0\n",
+    "\n",
+    "for i, (image, label) in enumerate(test_data):\n",
+    "    output = model(image)\n",
+    "    s = nn.Softmax(dim=1)\n",
+    "    output = s(output)\n",
+    "    a = torch.argmax(output)\n",
+    "    if label == a.item():\n",
+    "        correct_answer+=1\n",
+    "    else:\n",
+    "        print('wrong answer', i)\n",
+    "\n",
+    "print(correct_answer, total_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "computer's guess: 3, answer: 3\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#틀린 1문제\n",
+    "\n",
+    "def testexam(i: int):\n",
+    "    image, label = test_data[i]\n",
+    "    output = model(image)\n",
+    "    s = nn.Softmax(dim=1)\n",
+    "    output = s(output)\n",
+    "    a = torch.argmax(output)\n",
+    "    print(f\"computer's guess: {a.item()}, answer: {label}\")\n",
+    "    plt.imshow(image[0])\n",
+    "\n",
+    "\n",
+    "testexam(9975)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

mnistmodel.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d66f60842989d3986d6616676cfd4f2ac19b31a60f34d150bf59bd78a8b3cee2
+size 1689506