Spaces:
Running
on
T4
Running
on
T4
File size: 8,919 Bytes
707dfbd 58a221d 707dfbd 58a221d 707dfbd 58a221d 707dfbd |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing imscdr_ac_in___8.png...\n",
"Status Code: 500\n",
"Response Text: {\"detail\":\"conv2d() received an invalid combination of arguments - got (str, Parameter, NoneType, tuple, tuple, tuple, int), but expected one of:\\n * (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, tuple of ints padding, tuple of ints dilation, int groups)\\n didn't match because some of the arguments have invalid types: (!str!, !Parameter!, !NoneType!, !tuple of (int, int)!, !tuple of (int, int)!, !tuple of (int, int)!, int)\\n * (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, str padding, tuple of ints dilation, int groups)\\n didn't match because some of the arguments have invalid types: (!str!, !Parameter!, !NoneType!, !tuple of (int, int)!, !tuple of (int, int)!, !tuple of (int, int)!, int)\\n\"}\n",
"Finished processing imscdr_ac_in___8.png in 10.38 seconds\n",
"Processing imscdr_ac_in___9.png...\n",
"Status Code: 500\n",
"Response Text: <!DOCTYPE html>\n",
"<html class=\"\">\n",
"<head>\n",
" <meta charset=\"utf-8\"/>\n",
" <meta\n",
" name=\"viewport\"\n",
" content=\"width=device-width, initial-scale=1.0, user-scalable=no\"\n",
" />\n",
" <meta\n",
" name=\"description\"\n",
" content=\"We’re on a journey to advance and democratize artificial intelligence through open source and open science.\"\n",
" />\n",
" <meta property=\"fb:app_id\" content=\"1321688464574422\"/>\n",
" <meta name=\"twitter:card\" content=\"summary_large_image\"/>\n",
" <meta name=\"twitter:site\" content=\"@huggingface\"/>\n",
" <meta\n",
" property=\"og:title\"\n",
" content=\"Hugging Face – The AI community building the future.\"\n",
" />\n",
" <meta property=\"og:type\" content=\"website\"/>\n",
"\n",
" <title>Hugging Face – The AI community building the future.</title>\n",
" <style>\n",
" body {\n",
" margin: 0;\n",
" }\n",
"\n",
" main {\n",
" background-color: white;\n",
" min-height: 100vh;\n",
" padding: 7rem 1rem 8rem 1rem;\n",
" text-align: center;\n",
" font-family: Source Sans Pro, ui-sans-serif, system-ui, -apple-system,\n",
" BlinkMacSystemFont, Segoe UI, Roboto, Helvetica Neue, Arial, Noto Sans,\n",
" sans-serif, Apple Color Emoji, Segoe UI Emoji, Segoe UI Symbol,\n",
" Noto Color Emoji;\n",
" }\n",
"\n",
" img {\n",
" width: 6rem;\n",
" height: 6rem;\n",
" margin: 0 auto 1rem;\n",
" }\n",
"\n",
" h1 {\n",
" font-size: 3.75rem;\n",
" line-height: 1;\n",
" color: rgba(31, 41, 55, 1);\n",
" font-weight: 700;\n",
" box-sizing: border-box;\n",
" margin: 0 auto;\n",
" }\n",
"\n",
" p {\n",
" color: rgba(107, 114, 128, 1);\n",
" font-size: 1.125rem;\n",
" line-height: 1.75rem;\n",
" max-width: 28rem;\n",
" box-sizing: border-box;\n",
" margin: 0 auto;\n",
" }\n",
"\n",
" .dark main {\n",
" background-color: rgb(11, 15, 25);\n",
" }\n",
"\n",
" .dark h1 {\n",
" color: rgb(209, 213, 219);\n",
" }\n",
"\n",
" .dark p {\n",
" color: rgb(156, 163, 175);\n",
" }\n",
" </style>\n",
" <script>\n",
" // On page load or when changing themes, best to add inline in `head` to avoid FOUC\n",
" const key = \"_tb_global_settings\";\n",
" let theme = window.matchMedia(\"(prefers-color-scheme: dark)\").matches\n",
" ? \"dark\"\n",
" : \"light\";\n",
" try {\n",
" const storageTheme = JSON.parse(window.localStorage.getItem(key)).theme;\n",
" if (storageTheme) {\n",
" theme = storageTheme === \"dark\" ? \"dark\" : \"light\";\n",
" }\n",
" } catch (e) {\n",
" }\n",
" if (theme === \"dark\") {\n",
" document.documentElement.classList.add(\"dark\");\n",
" } else {\n",
" document.documentElement.classList.remove(\"dark\");\n",
" }\n",
" </script>\n",
"</head>\n",
"\n",
"<body>\n",
"<main>\n",
" <img\n",
" src=\"https://huggingface.co/front/assets/huggingface_logo.svg\"\n",
" alt=\"\"\n",
" />\n",
" <div>\n",
" <h1>500</h1>\n",
" <p>Sorry, there is an error on our side.</p>\n",
" </div>\n",
"</main>\n",
"</body>\n",
"</html>\n",
"\n",
"Finished processing imscdr_ac_in___9.png in 11.36 seconds\n",
"{}\n"
]
}
],
"source": [
"import os\n",
"import requests\n",
"import base64\n",
"from PIL import Image\n",
"import time\n",
"\n",
"api_url = \"https://banao-tech-omniapi.hf.space/process_image\"\n",
"\n",
"def process_image_folder(input_folder, output_folder, box_threshold=0.03, iou_threshold=0.1):\n",
" if not os.path.exists(output_folder):\n",
" os.makedirs(output_folder)\n",
"\n",
" results = {}\n",
" image_files = [f for f in os.listdir(input_folder) if f.lower().endswith(('.jpg', '.jpeg', '.png'))]\n",
"\n",
" for image_file in image_files:\n",
" image_path = os.path.join(input_folder, image_file)\n",
" print(f\"Processing {image_file}...\")\n",
"\n",
" start_time = time.time()\n",
"\n",
" try:\n",
" with open(image_path, \"rb\") as img_file:\n",
" files = {\"image_file\": img_file}\n",
" data = {\n",
" \"box_threshold\": box_threshold,\n",
" \"iou_threshold\": iou_threshold,\n",
" }\n",
" response = requests.post(api_url, files=files, data=data)\n",
" print(\"Status Code:\", response.status_code)\n",
" print(\"Response Text:\", response.text)\n",
"\n",
" if response.status_code == 200:\n",
" result = response.json()\n",
" results[image_file] = {\n",
" \"parsed_content_list\": result.get(\"parsed_content_list\", []),\n",
" \"label_coordinates\": result.get(\"label_coordinates\", []),\n",
" }\n",
" output_image_data = base64.b64decode(result[\"image\"])\n",
" output_image_path = os.path.join(output_folder, f\"labeled_{image_file}\")\n",
" with open(output_image_path, \"wb\") as img_file:\n",
" img_file.write(output_image_data)\n",
"\n",
" except Exception as e:\n",
" print(f\"Error processing {image_file}: {e}\")\n",
"\n",
" end_time = time.time()\n",
" print(f\"Finished processing {image_file} in {end_time - start_time:.2f} seconds\")\n",
"\n",
" return results\n",
"\n",
"# # Example call\n",
"res = process_image_folder('test', 'output_folder')\n",
"print(res)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{}"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"res"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "audit",
"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": "3.11.10"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|