{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9fe79075-42ab-47f5-a06f-33e948aeb026",
   "metadata": {},
   "outputs": [
    {
     "ename": "",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31mFailed to start the Kernel. \n",
      "\u001b[1;31mUnable to start Kernel '.venv (Python 3.13.2)' due to a timeout waiting for the ports to get used. \n",
      "\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
     ]
    }
   ],
   "source": [
    "import torch as th\n",
    "import glob\n",
    "import cv2\n",
    "import numpy as np\n",
    "import torch\n",
    "from torch.utils.data import Dataset, DataLoader\n",
    "\n",
    "\n",
    "class CustomDataset(Dataset):\n",
    "    def __init__(self, v_path=\"v3\"):\n",
    "        self.imgs_path = v_path\n",
    "        file_list = glob.glob(self.imgs_path + \"*\")\n",
    "        print(file_list)\n",
    "        self.data = []\n",
    "        for class_path in file_list:\n",
    "            class_name = class_path.split(\"/\")[-1]\n",
    "            for img_path in glob.glob(class_path + \"/*.jpg\"):\n",
    "                self.data.append([img_path, class_name])\n",
    "        print(self.data)\n",
    "        self.class_map = {\"Fake\" : 0, \"Real\": 1}\n",
    "        self.img_dim = (224, 224)\n",
    "    def __len__(self):\n",
    "        return len(self.data)\n",
    "    def __getitem__(self, idx):\n",
    "        img_path, class_name = self.data[idx]\n",
    "        img = cv2.imread(img_path)\n",
    "        img = cv2.resize(img, self.img_dim)\n",
    "        class_id = self.class_map[class_name]\n",
    "        img_tensor = torch.from_numpy(img)\n",
    "        img_tensor = img_tensor.permute(2, 0, 1)\n",
    "        class_id = torch.tensor([class_id])\n",
    "        return img_tensor, class_id"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d196725f",
   "metadata": {},
   "outputs": [],
   "source": [
    "dt = CustomDataset(v_path=)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0b97f9f9",
   "metadata": {},
   "outputs": [
    {
     "ename": "",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31mFailed to start the Kernel. \n",
      "\u001b[1;31mUnable to start Kernel '.venv (Python 3.13.2)' due to a timeout waiting for the ports to get used. \n",
      "\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
     ]
    }
   ],
   "source": [
    "import os\n",
    "import torch\n",
    "from torch.utils.data import Dataset, DataLoader\n",
    "from PIL import Image\n",
    "import torchvision.transforms as T\n",
    "\n",
    "class RealFakeDataset(Dataset):\n",
    "    def __init__(self, root_dir, transform=None):\n",
    "\n",
    "        self.root_dir = root_dir\n",
    "        self.transform = transform\n",
    "        \n",
    "        self.samples = []\n",
    "        for label_dir in [\"REAL\", \"FAKE\"]:\n",
    "            label = 1 if label_dir == \"REAL\" else 0\n",
    "            full_dir = os.path.join(self.root_dir, label_dir)\n",
    "            for fname in os.listdir(full_dir):\n",
    "                if fname.lower().endswith(('.jpg', '.jpeg', '.png', '.bmp')):\n",
    "                    img_path = os.path.join(full_dir, fname)\n",
    "                    self.samples.append((img_path, label))\n",
    "\n",
    "    def __len__(self):\n",
    "        return len(self.samples)\n",
    "\n",
    "    def __getitem__(self, idx):\n",
    "        img_path, label = self.samples[idx]\n",
    "        image = Image.open(img_path).convert('RGB')\n",
    "        \n",
    "        if self.transform:\n",
    "            image = self.transform(image)\n",
    "        \n",
    "        return image, label"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8542c314",
   "metadata": {},
   "outputs": [],
   "source": [
    "dataloader = DataLoader(dataset, batch_size=16, shuffle=True, num_workers=2)\n",
    "dataloader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "be7e0cf7",
   "metadata": {},
   "outputs": [
    {
     "ename": "",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31mFailed to start the Kernel. \n",
      "\u001b[1;31mUnable to start Kernel '.venv (Python 3.13.2)' due to a timeout waiting for the ports to get used. \n",
      "\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
     ]
    }
   ],
   "source": [
    "import cv2\n",
    "im = cv2.imread(\"/v3/test/REAL/0000 (3).jpg\")\n",
    "im.shape"
   ]
  }
 ],
 "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": 5
}