{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "04210b87",
   "metadata": {},
   "source": [
    "# Testing the saved model\n",
    "One cell code from ChatGPT."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "839c1262",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Prediction: ai\n",
      "Confidence: 0.7520\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "import torch.nn as nn\n",
    "import torchvision\n",
    "from PIL import Image\n",
    "import os\n",
    "\n",
    "# ----------------------------\n",
    "# 1️⃣ Device\n",
    "# ----------------------------\n",
    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
    "\n",
    "# ----------------------------\n",
    "# 2️⃣ Recreate Model Architecture\n",
    "# ----------------------------\n",
    "weights = torchvision.models.EfficientNet_B0_Weights.DEFAULT\n",
    "model = torchvision.models.efficientnet_b0(weights=None).to(device)\n",
    "\n",
    "# IMPORTANT: Must match training classes\n",
    "class_names = [\"ai\", \"real\"]   # or manually define list\n",
    "output_shape = 2\n",
    "\n",
    "model.classifier = nn.Sequential(\n",
    "    nn.Dropout(p=0.2, inplace=True),\n",
    "    nn.Linear(1280, output_shape, bias=True)\n",
    ").to(device)\n",
    "\n",
    "# ----------------------------\n",
    "# 3️⃣ Load Saved Weights\n",
    "# ----------------------------\n",
    "model.load_state_dict(torch.load(\"models/veriface_v2.pth\", map_location=device))\n",
    "model.eval()\n",
    "\n",
    "# ----------------------------\n",
    "# 4️⃣ Image Transforms (same as training)\n",
    "# ----------------------------\n",
    "auto_transforms = weights.transforms()\n",
    "\n",
    "# ----------------------------\n",
    "# 5️⃣ Prediction Function\n",
    "# ----------------------------\n",
    "def predict_image(image_path):\n",
    "    image = Image.open(image_path).convert(\"RGB\")\n",
    "    image = auto_transforms(image).unsqueeze(0).to(device)\n",
    "\n",
    "    with torch.no_grad():\n",
    "        outputs = model(image)\n",
    "        probs = torch.softmax(outputs, dim=1)\n",
    "        pred_class = torch.argmax(probs, dim=1).item()\n",
    "\n",
    "    return class_names[pred_class], probs[0][pred_class].item()\n",
    "\n",
    "# ----------------------------\n",
    "# 6️⃣ Use It\n",
    "# ----------------------------\n",
    "# image_path = os.path.join(\"dataset\",\"test_data_v2\",\"5c30ab9ee1a34b5889c55619fc713338.jpg\")\n",
    "image_path = os.path.join(\"C:/Users/a/Downloads/sample7.jpg\")\n",
    "label, confidence = predict_image(image_path)\n",
    "\n",
    "print(f\"Prediction: {label}\")\n",
    "print(f\"Confidence: {confidence:.4f}\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "myenv",
   "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": "3.14.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}