{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Identified food: Granny Smith\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "from PIL import Image\n",
    "from transformers import ViTFeatureExtractor, ViTForImageClassification\n",
    "import warnings\n",
    "\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "model_name = \"google/vit-base-patch16-224\"\n",
    "feature_extractor = ViTFeatureExtractor.from_pretrained(model_name)\n",
    "model = ViTForImageClassification.from_pretrained(model_name)\n",
    "\n",
    "def identify_food(image_path):\n",
    "    \"\"\"Identify the food item in the image.\"\"\"\n",
    "    image = Image.open(image_path)\n",
    "    inputs = feature_extractor(images=image, return_tensors=\"pt\")\n",
    "    outputs = model(**inputs)\n",
    "    logits = outputs.logits\n",
    "    predicted_class_idx = logits.argmax(-1).item()\n",
    "    predicted_label = model.config.id2label[predicted_class_idx]\n",
    "    food_name = predicted_label.split(',')[0]\n",
    "    return food_name\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.12.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}