{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "552bba22-970a-438b-ac08-ffa77ca61aee",
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import ViTImageProcessor, ViTModel\n",
    "# from datasets import load_dataset\n",
    "from PIL import Image\n",
    "import requests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "0645639a-b497-41af-aefa-9503da880463",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "f772ceaf98c84fecbc848f924bbe3398",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "preprocessor_config.json:   0%|          | 0.00/325 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d58d7b601e2b4859a5f1b54892056749",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "config.json:   0%|          | 0.00/5.43k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "4dedafc3fc8a4dacb134148fa7119c84",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "pytorch_model.bin:   0%|          | 0.00/346M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Some weights of ViTModel were not initialized from the model checkpoint at jsacex/vit-base-patch16-224-in21k-finetuned-lora-food101 and are newly initialized: ['vit.pooler.dense.bias', 'vit.pooler.dense.weight']\n",
      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
     ]
    }
   ],
   "source": [
    "# dataset = load_dataset(\"food101\")\n",
    "# url = 'http://images.cocodataset.org/val2017/000000039769.jpg'\n",
    "# image = Image.open(requests.get(url, stream=True).raw)\n",
    "image = Image.open(r\"image.jpg\")\n",
    "\n",
    "processor = ViTImageProcessor.from_pretrained('jsacex/vit-base-patch16-224-in21k-finetuned-lora-food101')\n",
    "model = ViTModel.from_pretrained('jsacex/vit-base-patch16-224-in21k-finetuned-lora-food101')\n",
    "inputs = processor(images = image, return_tensors=\"pt\")\n",
    "\n",
    "outputs = model(**inputs)\n",
    "last_hidden_states = outputs.last_hidden_state"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "7572729d-839d-4a9d-bc22-2a69bb8e9aaf",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "torch.Size([1, 197, 768])\n"
     ]
    }
   ],
   "source": [
    "print(last_hidden_states.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8eb3fa73-6b0c-4a08-b084-a2bd007f2fe4",
   "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}