{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "28e561c1-96da-4fc9-9261-16c4562b057b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import gradio as gr\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import torch\n",
    "from torch.utils.data import Dataset, DataLoader\n",
    "from transformers import AutoModel, AutoTokenizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "10ff0dd7-7cd1-4eb8-824e-56b3d640b271",
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import BlipForConditionalGeneration, AutoProcessor\n",
    "\n",
    "model = BlipForConditionalGeneration.from_pretrained(\"cassmussard/BLIP_airbnb\")\n",
    "processor = AutoProcessor.from_pretrained(\"Salesforce/blip-image-captioning-base\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fd119e29-aaf4-4aec-af80-77b8e11fb82f",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.eval()\n",
    "def predict(image):\n",
    "    inputs = processor(images=image, return_tensors=\"pt\")\n",
    "    pixel_values = inputs[\"pixel_values\"]\n",
    "    generated_ids = model.generate(pixel_values=pixel_values, max_length=50)\n",
    "    generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]\n",
    "    return generated_caption"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "435fdb1e-167f-45dc-bbbb-b8d0e05becbb",
   "metadata": {},
   "outputs": [],
   "source": [
    "iface = gr.Interface(fn=predict, \n",
    "                inputs=\"image\", \n",
    "                outputs='label',\n",
    "                live=True,\n",
    "                description=\"Draw a number on the sketchpad to see the model's prediction.\",\n",
    "                ).launch(debug=True, share=True);\n",
    "iface.launch(share=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e4ffb76c-667e-4a4e-8fa5-bc3d12e61e83",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "venv",
   "language": "python",
   "name": "venv"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}