{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import gradio as gr\n",
    "import numpy as np\n",
    "from os import environ\n",
    "from PIL import Image as PImage\n",
    "from torchvision import transforms as T\n",
    "from transformers import MaskFormerForInstanceSegmentation, MaskFormerImageProcessor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "ade_mean=[0.485, 0.456, 0.406]\n",
    "ade_std=[0.229, 0.224, 0.225]\n",
    "\n",
    "model_id = f\"thiagohersan/maskformer-satellite-trees\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# preprocessor = MaskFormerImageProcessor.from_pretrained(model_id)\n",
    "preprocessor = MaskFormerImageProcessor(\n",
    "    do_resize=False,\n",
    "    do_normalize=False,\n",
    "    do_rescale=False,\n",
    "    ignore_index=255,\n",
    "    reduce_labels=False\n",
    ")\n",
    "\n",
    "hf_token = environ.get('HFTOKEN') or True\n",
    "model = MaskFormerForInstanceSegmentation.from_pretrained(model_id, use_auth_token=hf_token)\n",
    "\n",
    "test_transform = T.Compose([\n",
    "    T.ToTensor(),\n",
    "    T.Normalize(mean=ade_mean, std=ade_std)\n",
    "])\n",
    "\n",
    "with PImage.open(\"../color-filter-calculator/assets/Artshack_screen.jpg\") as img:\n",
    "    img_size = (img.height, img.width)\n",
    "    norm_image = test_transform(np.array(img))\n",
    "    inputs = preprocessor(images=norm_image, return_tensors=\"pt\")\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "outputs = model(**inputs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "results = preprocessor.post_process_semantic_segmentation(outputs=outputs, target_sizes=[img_size])[0]\n",
    "results = results.numpy()\n",
    "\n",
    "labels = np.unique(results)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for label_id in labels:\n",
    "    print(model.config.id2label[label_id])"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.8.15 ('hf-gradio')",
   "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": "3.8.15"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "4888b226c77b860705e4be316b14a092026f41c3585ee0ddb38f3008c0cb495e"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}