{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2e9496e9-ec07-445f-b29d-fc44aabb377d",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from PIL import Image\n",
    "import torch\n",
    "import torch.nn as nn\n",
    "import torch.nn.functional as F\n",
    "import torch.optim as optim\n",
    "import torchvision\n",
    "import torchvision.transforms as transforms"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9b17757b-76c5-4562-a2be-e3a50201c9ee",
   "metadata": {},
   "outputs": [],
   "source": [
    "transform = transforms.Compose([\n",
    "    transforms.ToTensor(),\n",
    "    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))                            \n",
    "])                              "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5b898116-e9a8-429d-8491-67db5a65d358",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_data = torchvision.datasets.CIFAR10(root='./data', train=True, transform=transform, download=True)\n",
    "test_data = torchvision.datasets.CIFAR10(root='./data', train=False, transform=transform, download=True)\n",
    "\n",
    "train_loader = torch.utils.data.DataLoader(train_data, batch_size=32, shuffle=True, num_workers=2)\n",
    "test_loader = torch.utils.data.DataLoader(test_data, batch_size=32, shuffle=True, num_workers=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "49712fae-dfe6-4b6f-92ea-2e97a965c15c",
   "metadata": {},
   "outputs": [],
   "source": [
    "image, label = train_data[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d783e1a5-3410-4992-88a6-230dd2ec85dd",
   "metadata": {},
   "outputs": [],
   "source": [
    "image.size()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8ef21399-f2f2-46f4-8268-f60f36bbb533",
   "metadata": {},
   "outputs": [],
   "source": [
    "class_names = ['plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "192ff676-c4b8-4611-9338-ec9b35a502d5",
   "metadata": {},
   "outputs": [],
   "source": [
    "class NeuralNet(nn.Module):\n",
    "    def  __init__(self):\n",
    "        super().__init__()\n",
    "        self.conv1 = nn.Conv2d(3, 12, 5) # (12, 28, 28)\n",
    "        self.pool = nn.MaxPool2d(2, 2) # (12, 14, 14)\n",
    "        self.conv2 = nn.Conv2d(12, 24, 5) # (24, 10, 10) -> (24, 5, 5) -> Flatten (25 * 5 * 5)\n",
    "        self.fc1 = nn.Linear(24 * 5 * 5, 120)\n",
    "        self.fc2 = nn.Linear(120, 84)\n",
    "        self.fc3 = nn.Linear(84, 10)\n",
    "\n",
    "    def forward(self, x):\n",
    "        x = self.pool(F.relu(self.conv1(x)))\n",
    "        x = self.pool(F.relu(self.conv2(x)))\n",
    "        x = torch.flatten(x, 1)\n",
    "        x = F.relu(self.fc1(x))\n",
    "        x = F.relu(self.fc2(x))\n",
    "        x = self.fc3(x)\n",
    "        return x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f48dd819-9196-4aa5-92c4-ddcc644c6aa9",
   "metadata": {},
   "outputs": [],
   "source": [
    "net = NeuralNet()\n",
    "loss_function = nn.CrossEntropyLoss()\n",
    "optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3a91ce0c-e71d-4bfb-b945-47edfc8ca8d6",
   "metadata": {},
   "outputs": [],
   "source": [
    "for epoch in range(60):\n",
    "    print(f'Training epoch {epoch}...')\n",
    "\n",
    "    running_loss = 0.0\n",
    "\n",
    "    for i, data in enumerate(train_loader):\n",
    "        inputs, labels = data\n",
    "        optimizer.zero_grad()\n",
    "        outputs = net(inputs)\n",
    "        loss = loss_function(outputs, labels)\n",
    "        loss.backward()\n",
    "        optimizer.step()\n",
    "        \n",
    "        running_loss += loss.item()\n",
    "\n",
    "    print(f'Loss: {running_loss / len(train_loader):0.4f}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "aa5b2497-90a7-44a9-9985-427b920945eb",
   "metadata": {},
   "outputs": [],
   "source": [
    "torch.save(net.state_dict(), 'trained_net.pth')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ff62419f-ead5-4244-9a5e-a21d568bdca8",
   "metadata": {},
   "outputs": [],
   "source": [
    "net = NeuralNet()\n",
    "net.load_state_dict(torch.load('trained_net.pth'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "eb1d4385-d4da-454f-9d8c-d844aa7b24df",
   "metadata": {},
   "outputs": [],
   "source": [
    "correct = 0\n",
    "total = 0\n",
    "net.eval()\n",
    "with torch.no_grad():\n",
    "    for data in test_loader:\n",
    "        images, labels = data\n",
    "        outputs = net(images)\n",
    "        _, predicted = torch.max(outputs, 1)\n",
    "        total += labels.size(0)\n",
    "        correct += (predicted == labels).sum().item()\n",
    "\n",
    "accuracy = 100 * correct / total\n",
    "print(f'Accuracy: {accuracy}%')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1a4f098f-b1ea-46b7-a7d6-769f80292f5f",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "new_transform = transforms.Compose([\n",
    "    transforms.Resize((32, 32)),  \n",
    "    transforms.ToTensor(),\n",
    "    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))\n",
    "])\n",
    "\n",
    "def load_image(image_path):\n",
    "    image = Image.open(image_path)\n",
    "    image = new_transform(image)\n",
    "    image = image.unsqueeze(0)\n",
    "    return image\n",
    "\n",
    "image_paths = ['item1.jpg', 'item2.jpg', 'item3.jpg']\n",
    "images = [load_image(img) for img in image_paths]\n",
    "\n",
    "net.eval()\n",
    "with torch.no_grad():\n",
    "    for image in images:\n",
    "        output = net(image)\n",
    "        _, predicted = torch.max(output, 1)\n",
    "        print(f'Prediction: {class_names[predicted.item()]}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f2f456ec-90af-4d17-8665-b4c3f18e5056",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}