{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Successfully installed huggingface_hub-0.30.1 kagglehub-0.3.11 safetensors-0.5.3 timm-1.0.15 torchvision-0.21.0 tqdm-4.67.1\n"
     ]
    }
   ],
   "source": [
    "! pip install timm kagglehub"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting tensorboard\n",
      "  Downloading tensorboard-2.19.0-py3-none-any.whl.metadata (1.8 kB)\n",
      "Collecting absl-py>=0.4 (from tensorboard)\n",
      "  Downloading absl_py-2.2.2-py3-none-any.whl.metadata (2.6 kB)\n",
      "Collecting grpcio>=1.48.2 (from tensorboard)\n",
      "  Downloading grpcio-1.71.0-cp313-cp313-macosx_10_14_universal2.whl.metadata (3.8 kB)\n",
      "Collecting markdown>=2.6.8 (from tensorboard)\n",
      "  Downloading Markdown-3.7-py3-none-any.whl.metadata (7.0 kB)\n",
      "Requirement already satisfied: numpy>=1.12.0 in /Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages (from tensorboard) (2.1.3)\n",
      "Requirement already satisfied: packaging in /Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages (from tensorboard) (24.2)\n",
      "Collecting protobuf!=4.24.0,>=3.19.6 (from tensorboard)\n",
      "  Downloading protobuf-6.30.2-cp39-abi3-macosx_10_9_universal2.whl.metadata (593 bytes)\n",
      "Requirement already satisfied: setuptools>=41.0.0 in /Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages (from tensorboard) (78.1.0)\n",
      "Requirement already satisfied: six>1.9 in /Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages (from tensorboard) (1.17.0)\n",
      "Collecting tensorboard-data-server<0.8.0,>=0.7.0 (from tensorboard)\n",
      "  Downloading tensorboard_data_server-0.7.2-py3-none-any.whl.metadata (1.1 kB)\n",
      "Collecting werkzeug>=1.0.1 (from tensorboard)\n",
      "  Downloading werkzeug-3.1.3-py3-none-any.whl.metadata (3.7 kB)\n",
      "Requirement already satisfied: MarkupSafe>=2.1.1 in /Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages (from werkzeug>=1.0.1->tensorboard) (3.0.2)\n",
      "Downloading tensorboard-2.19.0-py3-none-any.whl (5.5 MB)\n",
      "\u001b[2K   \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.5/5.5 MB\u001b[0m \u001b[31m299.7 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m kB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m:06\u001b[0m\n",
      "\u001b[?25hDownloading absl_py-2.2.2-py3-none-any.whl (135 kB)\n",
      "Downloading grpcio-1.71.0-cp313-cp313-macosx_10_14_universal2.whl (11.3 MB)\n",
      "\u001b[2K   \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.3/11.3 MB\u001b[0m \u001b[31m381.9 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m1m379.1 kB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\n",
      "\u001b[?25hDownloading Markdown-3.7-py3-none-any.whl (106 kB)\n",
      "Downloading protobuf-6.30.2-cp39-abi3-macosx_10_9_universal2.whl (417 kB)\n",
      "Downloading tensorboard_data_server-0.7.2-py3-none-any.whl (2.4 kB)\n",
      "Downloading werkzeug-3.1.3-py3-none-any.whl (224 kB)\n",
      "Installing collected packages: werkzeug, tensorboard-data-server, protobuf, markdown, grpcio, absl-py, tensorboard\n",
      "Successfully installed absl-py-2.2.2 grpcio-1.71.0 markdown-3.7 protobuf-6.30.2 tensorboard-2.19.0 tensorboard-data-server-0.7.2 werkzeug-3.1.3\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "pip install tensorboard"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Downloading from https://www.kaggle.com/api/v1/datasets/download/birdy654/cifake-real-and-ai-generated-synthetic-images?dataset_version_number=3...\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████████████████████████████████████████████████| 105M/105M [00:12<00:00, 8.88MB/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Extracting files...\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Path to dataset files: /Users/spass/.cache/kagglehub/datasets/birdy654/cifake-real-and-ai-generated-synthetic-images/versions/3\n"
     ]
    }
   ],
   "source": [
    "import kagglehub\n",
    "path = kagglehub.dataset_download(\"birdy654/cifake-real-and-ai-generated-synthetic-images\")\n",
    "print(\"Path to dataset files:\", path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "mv /Users/spass/.cache/kagglehub/datasets/birdy654/cifake-real-and-ai-generated-synthetic-images/versions/3 ./v3/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "import os\n",
    "#import cv2\n",
    "from PIL import Image\n",
    "from torch.utils.data import Dataset\n",
    "from torchvision import transforms\n",
    "from torch.utils.data import DataLoader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "#Dataset class    1 for real, 0 for fake\n",
    "class RealFakeDataset(Dataset):\n",
    "    def __init__(self, root_dir, split='train', transform=None):\n",
    "        self.root_dir = root_dir\n",
    "        self.split = split\n",
    "        self.transform = transform\n",
    "        self.real_images = self._load_images(os.path.join(root_dir, split, 'REAL'))\n",
    "        self.fake_images = self._load_images(os.path.join(root_dir, split, 'FAKE'))\n",
    "        self.all_images = self.real_images + self.fake_images\n",
    "\n",
    "    def _load_images(self, folder):\n",
    "        images = []\n",
    "        for filename in os.listdir(folder):\n",
    "            if filename.endswith(('.jpg', '.jpeg')):\n",
    "                images.append(os.path.join(folder, filename))\n",
    "        return images\n",
    "\n",
    "    def __len__(self):\n",
    "        return len(self.all_images)\n",
    "\n",
    "    def __getitem__(self, idx):\n",
    "        img_path = self.all_images[idx]\n",
    "        image = Image.open(img_path).convert('RGB')\n",
    "        label = 1 if 'real' in img_path else 0 \n",
    "\n",
    "        if self.transform:\n",
    "            image = self.transform(image)\n",
    "\n",
    "        return image, label\n",
    "\n",
    "transform = transforms.Compose([\n",
    "    transforms.Resize((128, 128)),\n",
    "    transforms.ToTensor(),\n",
    "])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "#model\n",
    "import torch.nn as nn\n",
    "class ViTBinaryClassifier(nn.Module):\n",
    "    def __init__(self, pretrained=True):\n",
    "        super(ViTBinaryClassifier, self).__init__()\n",
    "        self.backbone = timm.create_model(\"vit_medium_patch16_224\", pretrained=pretrained)\n",
    "        in_features = self.backbone.head.in_features\n",
    "        self.backbone.head = nn.Identity() \n",
    "        self.classifier = nn.Sequential(\n",
    "            nn.Linear(in_features, 512),\n",
    "            nn.BatchNorm1d(512),\n",
    "            nn.ReLU(),\n",
    "            nn.Dropout(0.3),\n",
    "            nn.Linear(512, 128),\n",
    "            nn.BatchNorm1d(128),\n",
    "            nn.ReLU(),\n",
    "            nn.Dropout(0.3),\n",
    "            nn.Linear(128, 1),\n",
    "            nn.Sigmoid() \n",
    "        )\n",
    "        \n",
    "    def forward(self, x):\n",
    "        features = self.backbone(x)\n",
    "        out = self.classifier(features)\n",
    "        return out"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "def train(model, train_loader, criterion, optimizer, device, epoch, writer):\n",
    "    model.train()\n",
    "    running_loss = 0.0\n",
    "    total = 0\n",
    "    correct = 0\n",
    "    \n",
    "    for batch_idx, (images, labels) in enumerate(train_loader):\n",
    "        images = images.to(device)\n",
    "        labels = labels.float().to(device).unsqueeze(1)\n",
    "        \n",
    "        optimizer.zero_grad()\n",
    "        outputs = model(images)\n",
    "        loss = criterion(outputs, labels)\n",
    "        loss.backward()\n",
    "        optimizer.step()\n",
    "        \n",
    "        running_loss += loss.item()\n",
    "        total += labels.size(0)\n",
    "        predicted = (outputs > 0.5).float()\n",
    "        correct += (predicted == labels).sum().item()\n",
    "    \n",
    "    avg_loss = running_loss / len(train_loader)\n",
    "    accuracy = correct / total\n",
    "    print(f\"Epoch {epoch} Train Loss: {avg_loss:.4f}, Accuracy: {accuracy:.4f}\")\n",
    "    \n",
    "    # Logging to TensorBoard and WandB\n",
    "    writer.add_scalar(\"Train/Loss\", avg_loss, epoch)\n",
    "    writer.add_scalar(\"Train/Accuracy\", accuracy, epoch)\n",
    "    wandb.log({\"Train Loss\": avg_loss, \"Train Accuracy\": accuracy, \"epoch\": epoch})\n",
    "    \n",
    "    return avg_loss, accuracy\n",
    "\n",
    "def test(model, test_loader, criterion, device, epoch, writer):\n",
    "    model.eval()\n",
    "    running_loss = 0.0\n",
    "    total = 0\n",
    "    correct = 0\n",
    "    \n",
    "    with torch.no_grad():\n",
    "        for images, labels in test_loader:\n",
    "            images = images.to(device)\n",
    "            labels = labels.float().to(device).unsqueeze(1)\n",
    "            outputs = model(images)\n",
    "            loss = criterion(outputs, labels)\n",
    "            running_loss += loss.item()\n",
    "            \n",
    "            predicted = (outputs > 0.5).float()\n",
    "            total += labels.size(0)\n",
    "            correct += (predicted == labels).sum().item()\n",
    "    \n",
    "    avg_loss = running_loss / len(test_loader)\n",
    "    accuracy = correct / total\n",
    "    print(f\"Epoch {epoch} Test Loss: {avg_loss:.4f}, Accuracy: {accuracy:.4f}\")\n",
    "    \n",
    "    writer.add_scalar(\"Test/Loss\", avg_loss, epoch)\n",
    "    writer.add_scalar(\"Test/Accuracy\", accuracy, epoch)\n",
    "    wandb.log({\"Test Loss\": avg_loss, \"Test Accuracy\": accuracy, \"epoch\": epoch})\n",
    "    \n",
    "    return avg_loss, accuracy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [
    {
     "ename": "FileNotFoundError",
     "evalue": "[Errno 2] No such file or directory: './train/REAL'",
     "output_type": "error",
     "traceback": [
      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
      "\u001b[31mFileNotFoundError\u001b[39m                         Traceback (most recent call last)",
      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[18]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m dataset = \u001b[43mRealFakeDataset\u001b[49m\u001b[43m(\u001b[49m\u001b[43mroot_dir\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43m.\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msplit\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mtrain\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtransform\u001b[49m\u001b[43m=\u001b[49m\u001b[43mtransform\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m      2\u001b[39m dataloader = DataLoader(dataset, batch_size=\u001b[32m16\u001b[39m, shuffle=\u001b[38;5;28;01mTrue\u001b[39;00m)\n",
      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[16]\u001b[39m\u001b[32m, line 7\u001b[39m, in \u001b[36mRealFakeDataset.__init__\u001b[39m\u001b[34m(self, root_dir, split, transform)\u001b[39m\n\u001b[32m      5\u001b[39m \u001b[38;5;28mself\u001b[39m.split = split\n\u001b[32m      6\u001b[39m \u001b[38;5;28mself\u001b[39m.transform = transform\n\u001b[32m----> \u001b[39m\u001b[32m7\u001b[39m \u001b[38;5;28mself\u001b[39m.real_images = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_load_images\u001b[49m\u001b[43m(\u001b[49m\u001b[43mos\u001b[49m\u001b[43m.\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m.\u001b[49m\u001b[43mjoin\u001b[49m\u001b[43m(\u001b[49m\u001b[43mroot_dir\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msplit\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mREAL\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m      8\u001b[39m \u001b[38;5;28mself\u001b[39m.fake_images = \u001b[38;5;28mself\u001b[39m._load_images(os.path.join(root_dir, split, \u001b[33m'\u001b[39m\u001b[33mFAKE\u001b[39m\u001b[33m'\u001b[39m))\n\u001b[32m      9\u001b[39m \u001b[38;5;28mself\u001b[39m.all_images = \u001b[38;5;28mself\u001b[39m.real_images + \u001b[38;5;28mself\u001b[39m.fake_images\n",
      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[16]\u001b[39m\u001b[32m, line 13\u001b[39m, in \u001b[36mRealFakeDataset._load_images\u001b[39m\u001b[34m(self, folder)\u001b[39m\n\u001b[32m     11\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34m_load_images\u001b[39m(\u001b[38;5;28mself\u001b[39m, folder):\n\u001b[32m     12\u001b[39m     images = []\n\u001b[32m---> \u001b[39m\u001b[32m13\u001b[39m     \u001b[38;5;28;01mfor\u001b[39;00m filename \u001b[38;5;129;01min\u001b[39;00m \u001b[43mos\u001b[49m\u001b[43m.\u001b[49m\u001b[43mlistdir\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfolder\u001b[49m\u001b[43m)\u001b[49m:\n\u001b[32m     14\u001b[39m         \u001b[38;5;28;01mif\u001b[39;00m filename.endswith((\u001b[33m'\u001b[39m\u001b[33m.jpg\u001b[39m\u001b[33m'\u001b[39m, \u001b[33m'\u001b[39m\u001b[33m.jpeg\u001b[39m\u001b[33m'\u001b[39m)):\n\u001b[32m     15\u001b[39m             images.append(os.path.join(folder, filename))\n",
      "\u001b[31mFileNotFoundError\u001b[39m: [Errno 2] No such file or directory: './train/REAL'"
     ]
    }
   ],
   "source": [
    "dataset = RealFakeDataset(root_dir='./', split='train', transform=transform)\n",
    "dataloader = DataLoader(dataset, batch_size=16, shuffle=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'optimizer' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
      "\u001b[31mNameError\u001b[39m                                 Traceback (most recent call last)",
      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[19]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m \u001b[43moptimizer\u001b[49m\n",
      "\u001b[31mNameError\u001b[39m: name 'optimizer' is not defined"
     ]
    }
   ],
   "source": [
    "optimizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "wandb.init(project=\"vit_variable_resolution\", entity=\"your_wandb_entity\")  # Set your wandb entity if needed\n",
    "writer = SummaryWriter(log_dir=\"./runs/vit_variable_resolution\")\n",
    "\n",
    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
    "\n",
    "# Define transforms for normalization (the resizing is handled in the dataset)\n",
    "transform = transforms.Compose([\n",
    "    transforms.ToTensor(),\n",
    "    transforms.Normalize(mean=[0.485, 0.456, 0.406],  # Using ImageNet stats\n",
    "                            std=[0.229, 0.224, 0.225])\n",
    "])\n",
    "\n",
    "# Create dataset instances\n",
    "train_dataset = VariableResolutionDataset(root_dir=\"data/train\", resolutions=[224, 256, 288], transform=transform)\n",
    "test_dataset = VariableResolutionDataset(root_dir=\"data/test\", resolutions=[224, 256, 288], transform=transform)\n",
    "\n",
    "# Create DataLoaders\n",
    "train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True, num_workers=4)\n",
    "test_loader = DataLoader(test_dataset, batch_size=32, shuffle=False, num_workers=4)\n",
    "\n",
    "# Initialize model, criterion, and optimizer\n",
    "model = ViTBinaryClassifier(pretrained=True).to(device)\n",
    "criterion = nn.BCELoss()\n",
    "optimizer = optim.Adam(model.parameters(), lr=3e-4)\n",
    "\n",
    "num_epochs = 10\n",
    "for epoch in range(1, num_epochs+1):\n",
    "    train_loss, train_acc = train(model, train_loader, criterion, optimizer, device, epoch, writer)\n",
    "    test_loss, test_acc = test(model, test_loader, criterion, device, epoch, writer)\n",
    "\n",
    "# Save model checkpoint\n",
    "torch.save(model.state_dict(), \"vit_binary_classifier.pth\")\n",
    "writer.close()\n",
    "wandb.finish()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'model' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
      "\u001b[31mNameError\u001b[39m                                 Traceback (most recent call last)",
      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[21]\u001b[39m\u001b[32m, line 2\u001b[39m\n\u001b[32m      1\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mtorch\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01moptim\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01moptim\u001b[39;00m\n\u001b[32m----> \u001b[39m\u001b[32m2\u001b[39m optim.Adam(\u001b[43mmodel\u001b[49m.parameters(), lr=\u001b[32m3e-4\u001b[39m)\n",
      "\u001b[31mNameError\u001b[39m: name 'model' is not defined"
     ]
    }
   ],
   "source": [
    "import torch.optim as optim\n",
    "optim.Adam(model.parameters(), lr=3e-4)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "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": "3.13.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}