File size: 28,734 Bytes
7820b0f |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Resolving data files: 100%|██████████| 41/41 [00:00<00:00, 217679.07it/s]\n",
"Resolving data files: 100%|██████████| 44/44 [00:00<00:00, 150.82it/s]\n",
"Resolving data files: 100%|██████████| 30/30 [00:00<00:00, 207638.81it/s]\n",
"Resolving data files: 100%|██████████| 41/41 [00:00<00:00, 170771.07it/s]\n",
"Resolving data files: 100%|██████████| 44/44 [00:00<00:00, 173.94it/s]\n",
"Resolving data files: 100%|██████████| 30/30 [00:00<00:00, 213995.10it/s]\n",
"Downloading data: 100%|██████████| 539M/539M [00:27<00:00, 19.7MB/s]\n",
"Downloading data: 100%|██████████| 531M/531M [00:36<00:00, 14.7MB/s]\n",
"Downloading data: 100%|██████████| 458M/458M [00:33<00:00, 13.6MB/s]\n",
"Downloading data: 100%|██████████| 480M/480M [00:35<00:00, 13.7MB/s]\n",
"Downloading data: 100%|██████████| 567M/567M [00:40<00:00, 14.0MB/s]\n",
"Downloading data: 100%|██████████| 591M/591M [00:41<00:00, 14.2MB/s]\n",
"Downloading data: 100%|██████████| 565M/565M [00:41<00:00, 13.6MB/s]\n",
"Downloading data: 100%|██████████| 500M/500M [00:33<00:00, 15.0MB/s]\n",
"Downloading data: 100%|██████████| 483M/483M [00:35<00:00, 13.7MB/s]\n",
"Downloading data: 100%|██████████| 694M/694M [00:47<00:00, 14.5MB/s]\n",
"Downloading data: 100%|██████████| 513M/513M [00:36<00:00, 14.2MB/s]\n",
"Downloading data: 100%|██████████| 620M/620M [00:45<00:00, 13.7MB/s]\n",
"Downloading data: 100%|██████████| 528M/528M [00:35<00:00, 14.8MB/s]\n",
"Downloading data: 100%|██████████| 365M/365M [00:25<00:00, 14.2MB/s]\n",
"Downloading data: 100%|██████████| 54.1M/54.1M [00:03<00:00, 15.3MB/s]\n",
"Downloading data: 100%|██████████| 55.6M/55.6M [00:04<00:00, 12.7MB/s]\n",
"Downloading data: 100%|██████████| 53.3M/53.3M [00:03<00:00, 17.4MB/s]\n",
"Downloading data: 100%|██████████| 54.6M/54.6M [00:03<00:00, 15.8MB/s]\n",
"Downloading data: 100%|██████████| 37.4M/37.4M [00:02<00:00, 14.7MB/s]\n",
"Downloading data: 100%|██████████| 41.4M/41.4M [00:02<00:00, 15.0MB/s]\n",
"Downloading data: 100%|██████████| 50.7M/50.7M [00:04<00:00, 12.0MB/s]\n",
"Downloading data: 100%|██████████| 52.0M/52.0M [00:04<00:00, 12.7MB/s]\n",
"Downloading data: 100%|██████████| 45.3M/45.3M [00:03<00:00, 14.3MB/s]\n",
"Downloading data: 100%|██████████| 46.7M/46.7M [00:03<00:00, 12.8MB/s]\n",
"Downloading data: 100%|██████████| 45.4M/45.4M [00:03<00:00, 12.3MB/s]\n",
"Downloading data: 100%|██████████| 63.0M/63.0M [00:04<00:00, 15.7MB/s]\n",
"Downloading data: 100%|██████████| 44.2M/44.2M [00:03<00:00, 14.0MB/s]\n",
"Downloading data: 100%|██████████| 43.1M/43.1M [00:03<00:00, 11.3MB/s]\n",
"Downloading data: 100%|██████████| 46.0M/46.0M [00:02<00:00, 16.8MB/s]\n",
"Downloading data: 100%|██████████| 42.9M/42.9M [00:03<00:00, 13.0MB/s]\n",
"Downloading data: 100%|██████████| 44.4M/44.4M [00:02<00:00, 19.7MB/s]\n",
"Downloading data: 100%|██████████| 53.7M/53.7M [00:03<00:00, 16.0MB/s]\n",
"Downloading data: 100%|██████████| 42.8M/42.8M [00:01<00:00, 22.9MB/s]\n",
"Downloading data: 100%|██████████| 56.0M/56.0M [00:03<00:00, 14.3MB/s]\n",
"Downloading data: 100%|██████████| 520M/520M [00:36<00:00, 14.4MB/s]\n",
"Downloading data: 100%|██████████| 470M/470M [00:31<00:00, 14.8MB/s]\n",
"Downloading data: 100%|██████████| 510M/510M [00:35<00:00, 14.4MB/s]\n",
"Downloading data: 100%|██████████| 529M/529M [00:34<00:00, 15.2MB/s]\n",
"Downloading data: 100%|██████████| 552M/552M [00:37<00:00, 14.9MB/s]\n",
"Downloading data: 100%|██████████| 497M/497M [00:32<00:00, 15.1MB/s]\n",
"Downloading data: 100%|██████████| 524M/524M [00:35<00:00, 14.8MB/s]\n",
"Downloading data: 100%|██████████| 559M/559M [00:39<00:00, 14.0MB/s]\n",
"Downloading data: 100%|██████████| 534M/534M [00:36<00:00, 14.7MB/s]\n",
"Downloading data: 100%|██████████| 441M/441M [00:27<00:00, 16.2MB/s]\n",
"Downloading data: 100%|██████████| 625M/625M [00:41<00:00, 15.1MB/s]\n",
"Downloading data: 100%|██████████| 666M/666M [00:45<00:00, 14.6MB/s]\n",
"Downloading data: 100%|██████████| 579M/579M [00:40<00:00, 14.5MB/s]\n",
"Downloading data: 100%|██████████| 552M/552M [00:34<00:00, 16.2MB/s]\n",
"Downloading data: 100%|██████████| 607M/607M [00:39<00:00, 15.4MB/s]\n",
"Downloading data: 100%|██████████| 716M/716M [00:50<00:00, 14.3MB/s]\n",
"Downloading data: 100%|██████████| 606M/606M [00:39<00:00, 15.3MB/s]\n",
"Downloading data: 100%|██████████| 572M/572M [00:36<00:00, 15.5MB/s]\n",
"Downloading data: 100%|██████████| 654M/654M [00:44<00:00, 14.7MB/s]\n",
"Downloading data: 100%|██████████| 105M/105M [00:07<00:00, 14.5MB/s]\n",
"Downloading data: 100%|██████████| 57.5M/57.5M [00:04<00:00, 13.9MB/s]\n",
"Downloading data: 100%|██████████| 58.5M/58.5M [00:03<00:00, 17.0MB/s]\n",
"Downloading data: 100%|██████████| 56.1M/56.1M [00:03<00:00, 15.3MB/s]\n",
"Downloading data: 100%|██████████| 45.1M/45.1M [00:02<00:00, 17.3MB/s]\n",
"Downloading data: 100%|██████████| 44.6M/44.6M [00:02<00:00, 18.4MB/s]\n",
"Downloading data: 100%|██████████| 51.7M/51.7M [00:03<00:00, 13.7MB/s]\n",
"Downloading data: 100%|██████████| 61.3M/61.3M [00:03<00:00, 15.5MB/s]\n",
"Downloading data: 100%|██████████| 52.9M/52.9M [00:02<00:00, 17.8MB/s]\n",
"Downloading data: 100%|██████████| 51.7M/51.7M [00:03<00:00, 15.6MB/s]\n",
"Downloading data: 100%|██████████| 44.2M/44.2M [00:03<00:00, 14.2MB/s]\n",
"Downloading data: 100%|██████████| 52.2M/52.2M [00:03<00:00, 16.7MB/s]\n",
"Downloading data: 100%|██████████| 49.0M/49.0M [00:02<00:00, 17.3MB/s]\n",
"Downloading data: 100%|██████████| 50.5M/50.5M [00:03<00:00, 13.1MB/s]\n",
"Downloading data: 100%|██████████| 47.7M/47.7M [00:02<00:00, 20.3MB/s]\n",
"Downloading data: 100%|██████████| 46.8M/46.8M [00:02<00:00, 17.3MB/s]\n",
"Downloading data: 100%|██████████| 47.0M/47.0M [00:03<00:00, 14.1MB/s]\n",
"Downloading data: 100%|██████████| 46.5M/46.5M [00:03<00:00, 13.9MB/s]\n",
"Downloading data: 100%|██████████| 59.4M/59.4M [00:03<00:00, 16.6MB/s]\n",
"Downloading data: 100%|██████████| 58.6M/58.6M [00:03<00:00, 16.4MB/s]\n",
"Downloading data: 100%|██████████| 60.6M/60.6M [00:04<00:00, 14.9MB/s]\n",
"Downloading data: 100%|██████████| 60.5M/60.5M [00:03<00:00, 15.6MB/s]\n",
"Downloading data: 100%|██████████| 60.4M/60.4M [00:03<00:00, 18.4MB/s]\n",
"Downloading data: 100%|██████████| 54.1M/54.1M [00:03<00:00, 15.4MB/s]\n",
"Downloading data: 100%|██████████| 59.6M/59.6M [00:04<00:00, 14.7MB/s]\n",
"Downloading data: 100%|██████████| 476M/476M [00:32<00:00, 14.5MB/s]\n",
"Downloading data: 100%|██████████| 491M/491M [00:33<00:00, 14.7MB/s]\n",
"Downloading data: 100%|██████████| 535M/535M [00:35<00:00, 14.9MB/s]\n",
"Downloading data: 100%|██████████| 506M/506M [00:35<00:00, 14.2MB/s]\n",
"Downloading data: 100%|██████████| 487M/487M [00:31<00:00, 15.4MB/s]\n",
"Downloading data: 100%|██████████| 532M/532M [00:36<00:00, 14.6MB/s]\n",
"Downloading data: 100%|██████████| 561M/561M [00:34<00:00, 16.2MB/s]\n",
"Downloading data: 100%|██████████| 560M/560M [00:35<00:00, 15.6MB/s]\n",
"Downloading data: 100%|██████████| 550M/550M [00:36<00:00, 15.2MB/s]\n",
"Downloading data: 100%|██████████| 445M/445M [00:28<00:00, 15.5MB/s]\n",
"Downloading data: 100%|██████████| 57.8M/57.8M [00:04<00:00, 14.3MB/s]\n",
"Downloading data: 100%|██████████| 55.6M/55.6M [00:03<00:00, 16.7MB/s]\n",
"Downloading data: 100%|██████████| 51.4M/51.4M [00:03<00:00, 16.7MB/s]\n",
"Downloading data: 100%|██████████| 56.5M/56.5M [00:05<00:00, 9.58MB/s]\n",
"Downloading data: 100%|██████████| 40.7M/40.7M [00:01<00:00, 25.5MB/s]\n",
"Downloading data: 100%|██████████| 44.9M/44.9M [00:02<00:00, 19.3MB/s]\n",
"Downloading data: 100%|██████████| 50.1M/50.1M [00:03<00:00, 13.7MB/s]\n",
"Downloading data: 100%|██████████| 52.8M/52.8M [00:03<00:00, 16.1MB/s]\n",
"Downloading data: 100%|██████████| 48.0M/48.0M [00:02<00:00, 17.8MB/s]\n",
"Downloading data: 100%|██████████| 45.3M/45.3M [00:03<00:00, 12.1MB/s]\n",
"Downloading data: 100%|██████████| 46.4M/46.4M [00:02<00:00, 16.4MB/s]\n",
"Downloading data: 100%|██████████| 43.7M/43.7M [00:03<00:00, 13.1MB/s]\n",
"Downloading data: 100%|██████████| 43.7M/43.7M [00:02<00:00, 15.9MB/s]\n",
"Downloading data: 100%|██████████| 45.9M/45.9M [00:02<00:00, 16.6MB/s]\n",
"Downloading data: 100%|██████████| 45.4M/45.4M [00:03<00:00, 13.8MB/s]\n",
"Downloading data: 100%|██████████| 46.1M/46.1M [00:03<00:00, 15.2MB/s]\n",
"Downloading data: 100%|██████████| 45.7M/45.7M [00:03<00:00, 15.0MB/s]\n",
"Downloading data: 100%|██████████| 45.0M/45.0M [00:03<00:00, 14.7MB/s]\n",
"Downloading data: 100%|██████████| 47.9M/47.9M [00:02<00:00, 16.2MB/s]\n",
"Downloading data: 100%|██████████| 54.8M/54.8M [00:04<00:00, 13.4MB/s]\n",
"Generating train split: 100%|██████████| 18000/18000 [01:37<00:00, 184.78 examples/s]\n",
"Generating validation split: 100%|██████████| 20715/20715 [01:38<00:00, 210.47 examples/s]\n",
"Generating test split: 100%|██████████| 13354/13354 [00:50<00:00, 264.34 examples/s]\n"
]
}
],
"source": [
"from datasets import load_dataset\n",
"\n",
"data = load_dataset(\"ideepankarsharma2003/AIGeneratedImages_Midjourney\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Saving the dataset (24/24 shards): 100%|██████████| 18000/18000 [01:38<00:00, 183.49 examples/s] \n",
"Saving the dataset (25/25 shards): 100%|██████████| 20715/20715 [01:42<00:00, 202.85 examples/s]\n",
"Saving the dataset (13/13 shards): 100%|██████████| 13354/13354 [00:44<00:00, 302.42 examples/s]\n"
]
}
],
"source": [
"data.save_to_disk(\"dataset\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"DatasetDict({\n",
" train: Dataset({\n",
" features: ['image', 'label'],\n",
" num_rows: 18000\n",
" })\n",
" validation: Dataset({\n",
" features: ['image', 'label'],\n",
" num_rows: 20715\n",
" })\n",
" test: Dataset({\n",
" features: ['image', 'label'],\n",
" num_rows: 13354\n",
" })\n",
"})"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"ename": "ImportError",
"evalue": "To support decoding images, please install 'Pillow'.",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mImportError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[7], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mdata\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mtrain\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\n",
"File \u001b[0;32m~/AI_Image_Classification/venv/lib/python3.10/site-packages/datasets/arrow_dataset.py:2800\u001b[0m, in \u001b[0;36mDataset.__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m 2798\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__getitem__\u001b[39m(\u001b[38;5;28mself\u001b[39m, key): \u001b[38;5;66;03m# noqa: F811\u001b[39;00m\n\u001b[1;32m 2799\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Can be used to index columns (by string names) or rows (by integer index or iterable of indices or bools).\"\"\"\u001b[39;00m\n\u001b[0;32m-> 2800\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_getitem\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/AI_Image_Classification/venv/lib/python3.10/site-packages/datasets/arrow_dataset.py:2785\u001b[0m, in \u001b[0;36mDataset._getitem\u001b[0;34m(self, key, **kwargs)\u001b[0m\n\u001b[1;32m 2783\u001b[0m formatter \u001b[38;5;241m=\u001b[39m get_formatter(format_type, features\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_info\u001b[38;5;241m.\u001b[39mfeatures, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mformat_kwargs)\n\u001b[1;32m 2784\u001b[0m pa_subtable \u001b[38;5;241m=\u001b[39m query_table(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_data, key, indices\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_indices \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_indices \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[0;32m-> 2785\u001b[0m formatted_output \u001b[38;5;241m=\u001b[39m \u001b[43mformat_table\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 2786\u001b[0m \u001b[43m \u001b[49m\u001b[43mpa_subtable\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mformatter\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mformatter\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mformat_columns\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mformat_columns\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43moutput_all_columns\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_all_columns\u001b[49m\n\u001b[1;32m 2787\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2788\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m formatted_output\n",
"File \u001b[0;32m~/AI_Image_Classification/venv/lib/python3.10/site-packages/datasets/formatting/formatting.py:629\u001b[0m, in \u001b[0;36mformat_table\u001b[0;34m(table, key, formatter, format_columns, output_all_columns)\u001b[0m\n\u001b[1;32m 627\u001b[0m python_formatter \u001b[38;5;241m=\u001b[39m PythonFormatter(features\u001b[38;5;241m=\u001b[39mformatter\u001b[38;5;241m.\u001b[39mfeatures)\n\u001b[1;32m 628\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m format_columns \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 629\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mformatter\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpa_table\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mquery_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mquery_type\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 630\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m query_type \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcolumn\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m 631\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m key \u001b[38;5;129;01min\u001b[39;00m format_columns:\n",
"File \u001b[0;32m~/AI_Image_Classification/venv/lib/python3.10/site-packages/datasets/formatting/formatting.py:396\u001b[0m, in \u001b[0;36mFormatter.__call__\u001b[0;34m(self, pa_table, query_type)\u001b[0m\n\u001b[1;32m 394\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\u001b[38;5;28mself\u001b[39m, pa_table: pa\u001b[38;5;241m.\u001b[39mTable, query_type: \u001b[38;5;28mstr\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Union[RowFormat, ColumnFormat, BatchFormat]:\n\u001b[1;32m 395\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m query_type \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrow\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[0;32m--> 396\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mformat_row\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpa_table\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 397\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m query_type \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcolumn\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m 398\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mformat_column(pa_table)\n",
"File \u001b[0;32m~/AI_Image_Classification/venv/lib/python3.10/site-packages/datasets/formatting/formatting.py:437\u001b[0m, in \u001b[0;36mPythonFormatter.format_row\u001b[0;34m(self, pa_table)\u001b[0m\n\u001b[1;32m 435\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m LazyRow(pa_table, \u001b[38;5;28mself\u001b[39m)\n\u001b[1;32m 436\u001b[0m row \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpython_arrow_extractor()\u001b[38;5;241m.\u001b[39mextract_row(pa_table)\n\u001b[0;32m--> 437\u001b[0m row \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpython_features_decoder\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode_row\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrow\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 438\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m row\n",
"File \u001b[0;32m~/AI_Image_Classification/venv/lib/python3.10/site-packages/datasets/formatting/formatting.py:215\u001b[0m, in \u001b[0;36mPythonFeaturesDecoder.decode_row\u001b[0;34m(self, row)\u001b[0m\n\u001b[1;32m 214\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecode_row\u001b[39m(\u001b[38;5;28mself\u001b[39m, row: \u001b[38;5;28mdict\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28mdict\u001b[39m:\n\u001b[0;32m--> 215\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfeatures\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode_example\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrow\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfeatures \u001b[38;5;28;01melse\u001b[39;00m row\n",
"File \u001b[0;32m~/AI_Image_Classification/venv/lib/python3.10/site-packages/datasets/features/features.py:1929\u001b[0m, in \u001b[0;36mFeatures.decode_example\u001b[0;34m(self, example, token_per_repo_id)\u001b[0m\n\u001b[1;32m 1915\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecode_example\u001b[39m(\u001b[38;5;28mself\u001b[39m, example: \u001b[38;5;28mdict\u001b[39m, token_per_repo_id: Optional[Dict[\u001b[38;5;28mstr\u001b[39m, Union[\u001b[38;5;28mstr\u001b[39m, \u001b[38;5;28mbool\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m]]] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[1;32m 1916\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Decode example with custom feature decoding.\u001b[39;00m\n\u001b[1;32m 1917\u001b[0m \n\u001b[1;32m 1918\u001b[0m \u001b[38;5;124;03m Args:\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1926\u001b[0m \u001b[38;5;124;03m `dict[str, Any]`\u001b[39;00m\n\u001b[1;32m 1927\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m-> 1929\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m {\n\u001b[1;32m 1930\u001b[0m column_name: decode_nested_example(feature, value, token_per_repo_id\u001b[38;5;241m=\u001b[39mtoken_per_repo_id)\n\u001b[1;32m 1931\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_column_requires_decoding[column_name]\n\u001b[1;32m 1932\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m value\n\u001b[1;32m 1933\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m column_name, (feature, value) \u001b[38;5;129;01min\u001b[39;00m zip_dict(\n\u001b[1;32m 1934\u001b[0m {key: value \u001b[38;5;28;01mfor\u001b[39;00m key, value \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mitems() \u001b[38;5;28;01mif\u001b[39;00m key \u001b[38;5;129;01min\u001b[39;00m example}, example\n\u001b[1;32m 1935\u001b[0m )\n\u001b[1;32m 1936\u001b[0m }\n",
"File \u001b[0;32m~/AI_Image_Classification/venv/lib/python3.10/site-packages/datasets/features/features.py:1930\u001b[0m, in \u001b[0;36m<dictcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 1915\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecode_example\u001b[39m(\u001b[38;5;28mself\u001b[39m, example: \u001b[38;5;28mdict\u001b[39m, token_per_repo_id: Optional[Dict[\u001b[38;5;28mstr\u001b[39m, Union[\u001b[38;5;28mstr\u001b[39m, \u001b[38;5;28mbool\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m]]] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[1;32m 1916\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Decode example with custom feature decoding.\u001b[39;00m\n\u001b[1;32m 1917\u001b[0m \n\u001b[1;32m 1918\u001b[0m \u001b[38;5;124;03m Args:\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1926\u001b[0m \u001b[38;5;124;03m `dict[str, Any]`\u001b[39;00m\n\u001b[1;32m 1927\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[1;32m 1929\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m {\n\u001b[0;32m-> 1930\u001b[0m column_name: \u001b[43mdecode_nested_example\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfeature\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtoken_per_repo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken_per_repo_id\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1931\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_column_requires_decoding[column_name]\n\u001b[1;32m 1932\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m value\n\u001b[1;32m 1933\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m column_name, (feature, value) \u001b[38;5;129;01min\u001b[39;00m zip_dict(\n\u001b[1;32m 1934\u001b[0m {key: value \u001b[38;5;28;01mfor\u001b[39;00m key, value \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mitems() \u001b[38;5;28;01mif\u001b[39;00m key \u001b[38;5;129;01min\u001b[39;00m example}, example\n\u001b[1;32m 1935\u001b[0m )\n\u001b[1;32m 1936\u001b[0m }\n",
"File \u001b[0;32m~/AI_Image_Classification/venv/lib/python3.10/site-packages/datasets/features/features.py:1339\u001b[0m, in \u001b[0;36mdecode_nested_example\u001b[0;34m(schema, obj, token_per_repo_id)\u001b[0m\n\u001b[1;32m 1336\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(schema, (Audio, Image)):\n\u001b[1;32m 1337\u001b[0m \u001b[38;5;66;03m# we pass the token to read and decode files from private repositories in streaming mode\u001b[39;00m\n\u001b[1;32m 1338\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m obj \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m schema\u001b[38;5;241m.\u001b[39mdecode:\n\u001b[0;32m-> 1339\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mschema\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode_example\u001b[49m\u001b[43m(\u001b[49m\u001b[43mobj\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtoken_per_repo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken_per_repo_id\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1340\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m obj\n",
"File \u001b[0;32m~/AI_Image_Classification/venv/lib/python3.10/site-packages/datasets/features/image.py:155\u001b[0m, in \u001b[0;36mImage.decode_example\u001b[0;34m(self, value, token_per_repo_id)\u001b[0m\n\u001b[1;32m 153\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mPIL\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mImage\u001b[39;00m\n\u001b[1;32m 154\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 155\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mTo support decoding images, please install \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mPillow\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 157\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m token_per_repo_id \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 158\u001b[0m token_per_repo_id \u001b[38;5;241m=\u001b[39m {}\n",
"\u001b[0;31mImportError\u001b[0m: To support decoding images, please install 'Pillow'."
]
}
],
"source": [
"data['train'][0]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "venv",
"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": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|