File size: 2,481 Bytes
7f17661
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import gradio as gr\n",
    "import numpy as np\n",
    "from PIL import Image\n",
    "from transformers import MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# feature_extractor = MaskFormerFeatureExtractor.from_pretrained(\"facebook/maskformer-swin-tiny-coco\")\n",
    "# model = MaskFormerForInstanceSegmentation.from_pretrained(\"facebook/maskformer-swin-tiny-coco\")\n",
    "feature_extractor = MaskFormerFeatureExtractor.from_pretrained(\"facebook/maskformer-swin-large-coco\")\n",
    "model = MaskFormerForInstanceSegmentation.from_pretrained(\"facebook/maskformer-swin-large-coco\")\n",
    "\n",
    "with Image.open(\"../color-filter-calculator/assets/Artshack_screen.jpg\") as img:\n",
    "    img_size = (img.height, img.width)\n",
    "    inputs = feature_extractor(images=img, 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 = feature_extractor.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])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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
}