Hugging Face's logo

MnLgt
/
yolo-human-parse

Image Classification
Transformers
vision
Inference Endpoints
Model card Files Community
yolo-human-parse
File size: 13,802 Bytes 
6706230
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
 
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os \n",
    "from ultralytics import YOLO\n",
    "from yolo.BodyMask import BodyMask\n",
    "\n",
    "\n",
    "model_id = os.path.abspath(\"yolo-human-parse-epoch-125.pt\")\n",
    "\n",
    "example_images = [\n",
    "    os.path.join(\"sample_images\", f)\n",
    "    for f in os.listdir(\"sample_images\")\n",
    "    if f.endswith((\".png\", \".jpg\", \".jpeg\"))\n",
    "]\n",
    "\n",
    "image = example_images[0]\n",
    "\n",
    "bm = BodyMask(image, model_id=model_id)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bm.display_results()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[0;31mInit signature:\u001b[0m\n",
      "\u001b[0mgr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mImage\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mvalue\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str | PIL.Image.Image | np.ndarray | Callable | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m*\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mformat\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'webp'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mheight\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'int | str | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mwidth\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'int | str | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mimage_mode\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m\"Literal['1', 'L', 'P', 'RGB', 'RGBA', 'CMYK', 'YCbCr', 'LAB', 'HSV', 'I', 'F'] | None\"\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'RGB'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0msources\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m\"list[Literal['upload', 'webcam', 'clipboard']] | Literal['upload', 'webcam', 'clipboard'] | None\"\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mtype\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m\"Literal['numpy', 'pil', 'filepath']\"\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'numpy'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mlabel\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mevery\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'Timer | float | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0minputs\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'Component | Sequence[Component] | set[Component] | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mshow_label\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'bool | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mshow_download_button\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'bool'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mcontainer\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'bool'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mscale\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'int | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mmin_width\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'int'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m160\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0minteractive\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'bool | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mvisible\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'bool'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mstreaming\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'bool'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0melem_id\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0melem_classes\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'list[str] | str | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mrender\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'bool'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mkey\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'int | str | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mmirror_webcam\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'bool'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mshow_share_button\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'bool | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mplaceholder\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mshow_fullscreen_button\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'bool'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mDocstring:\u001b[0m     \n",
      "Creates an image component that can be used to upload images (as an input) or display images (as an output).\n",
      "\n",
      "Demos: sepia_filter, fake_diffusion\n",
      "Guides: image-classification-in-pytorch, image-classification-in-tensorflow, image-classification-with-vision-transformers, create-your-own-friends-with-a-gan\n",
      "\u001b[0;31mInit docstring:\u001b[0m\n",
      "Parameters:\n",
      "    value: A PIL Image, numpy array, path or URL for the default value that Image component is going to take. If callable, the function will be called whenever the app loads to set the initial value of the component.\n",
      "    format: File format (e.g. \"png\" or \"gif\") to save image if it does not already have a valid format (e.g. if the image is being returned to the frontend as a numpy array or PIL Image).  The format should be supported by the PIL library. This parameter has no effect on SVG files.\n",
      "    height: The height of the displayed image, specified in pixels if a number is passed, or in CSS units if a string is passed.\n",
      "    width: The width of the displayed image, specified in pixels if a number is passed, or in CSS units if a string is passed.\n",
      "    image_mode: \"RGB\" if color, or \"L\" if black and white. See https://pillow.readthedocs.io/en/stable/handbook/concepts.html for other supported image modes and their meaning. This parameter has no effect on SVG or GIF files. If set to None, the image_mode will be inferred from the image file.\n",
      "    sources: List of sources for the image. \"upload\" creates a box where user can drop an image file, \"webcam\" allows user to take snapshot from their webcam, \"clipboard\" allows users to paste an image from the clipboard. If None, defaults to [\"upload\", \"webcam\", \"clipboard\"] if streaming is False, otherwise defaults to [\"webcam\"].\n",
      "    type: The format the image is converted before being passed into the prediction function. \"numpy\" converts the image to a numpy array with shape (height, width, 3) and values from 0 to 255, \"pil\" converts the image to a PIL image object, \"filepath\" passes a str path to a temporary file containing the image. If the image is SVG, the `type` is ignored and the filepath of the SVG is returned. To support animated GIFs in input, the `type` should be set to \"filepath\" or \"pil\".\n",
      "    label: The label for this component. Appears above the component and is also used as the header if there are a table of examples for this component. If None and used in a `gr.Interface`, the label will be the name of the parameter this component is assigned to.\n",
      "    every: Continously calls `value` to recalculate it if `value` is a function (has no effect otherwise). Can provide a Timer whose tick resets `value`, or a float that provides the regular interval for the reset Timer.\n",
      "    inputs: Components that are used as inputs to calculate `value` if `value` is a function (has no effect otherwise). `value` is recalculated any time the inputs change.\n",
      "    show_label: if True, will display label.\n",
      "    show_download_button: If True, will display button to download image.\n",
      "    container: If True, will place the component in a container - providing some extra padding around the border.\n",
      "    scale: relative size compared to adjacent Components. For example if Components A and B are in a Row, and A has scale=2, and B has scale=1, A will be twice as wide as B. Should be an integer. scale applies in Rows, and to top-level Components in Blocks where fill_height=True.\n",
      "    min_width: minimum pixel width, will wrap if not sufficient screen space to satisfy this value. If a certain scale value results in this Component being narrower than min_width, the min_width parameter will be respected first.\n",
      "    interactive: if True, will allow users to upload and edit an image; if False, can only be used to display images. If not provided, this is inferred based on whether the component is used as an input or output.\n",
      "    visible: If False, component will be hidden.\n",
      "    streaming: If True when used in a `live` interface, will automatically stream webcam feed. Only valid is source is 'webcam'.\n",
      "    elem_id: An optional string that is assigned as the id of this component in the HTML DOM. Can be used for targeting CSS styles.\n",
      "    elem_classes: An optional list of strings that are assigned as the classes of this component in the HTML DOM. Can be used for targeting CSS styles.\n",
      "    render: If False, component will not render be rendered in the Blocks context. Should be used if the intention is to assign event listeners now but render the component later.\n",
      "    key: if assigned, will be used to assume identity across a re-render. Components that have the same key across a re-render will have their value preserved.\n",
      "    mirror_webcam: If True webcam will be mirrored. Default is True.\n",
      "    show_share_button: If True, will show a share icon in the corner of the component that allows user to share outputs to Hugging Face Spaces Discussions. If False, icon does not appear. If set to None (default behavior), then the icon appears if this Gradio app is launched on Spaces, but not otherwise.\n",
      "    placeholder: Custom text for the upload area. Overrides default upload messages when provided. Accepts new lines and `#` to designate a heading.\n",
      "    show_fullscreen_button: If True, will show a fullscreen icon in the corner of the component that allows user to view the image in fullscreen mode. If False, icon does not appear.\n",
      "\u001b[0;31mFile:\u001b[0m           /opt/homebrew/Caskroom/miniforge/base/envs/lemons/lib/python3.10/site-packages/gradio/components/image.py\n",
      "\u001b[0;31mType:\u001b[0m           ComponentMeta\n",
      "\u001b[0;31mSubclasses:\u001b[0m     "
     ]
    }
   ],
   "source": [
    "import gradio as gr \n",
    "\n",
    "gr.Image?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "lemons",
   "language": "python",
   "name": "lemons"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.14"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}