locsec/AMMICO
1
Форкнуть 0
зеркало из https://github.com/ssciwr/AMMICO.git synced 2025-11-03 15:36:07 +02:00
Код Задачи Пакеты Проекты Релизы Вики Активность
AMMICO/build/doctrees/nbsphinx/notebooks/Example summary.ipynb

578 строки
41 KiB
Plaintext
Исходник Ответственный История

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Image summary and visual question answering"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"This notebooks shows some preliminary work on Image Captioning and Visual question answering with lavis. It is mainly meant to explore its capabilities and to decide on future research directions. We package our code into a `ammico` package that is imported here:"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"execution": {
"iopub.execute_input": "2023-05-17T07:57:07.559673Z",
"iopub.status.busy": "2023-05-17T07:57:07.559387Z",
"iopub.status.idle": "2023-05-17T07:57:19.981365Z",
"shell.execute_reply": "2023-05-17T07:57:19.980569Z"
},
"tags": []
},
"outputs": [],
"source": [
"from ammico import utils as mutils\n",
"from ammico import display as mdisplay\n",
"import ammico.summary as sm"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Set an image path as input file path."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"execution": {
"iopub.execute_input": "2023-05-17T07:57:19.985929Z",
"iopub.status.busy": "2023-05-17T07:57:19.984966Z",
"iopub.status.idle": "2023-05-17T07:57:19.991128Z",
"shell.execute_reply": "2023-05-17T07:57:19.990348Z"
},
"tags": []
},
"outputs": [],
"source": [
"images = mutils.find_files(\n",
" path=\"data/\",\n",
" limit=10,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"execution": {
"iopub.execute_input": "2023-05-17T07:57:19.994576Z",
"iopub.status.busy": "2023-05-17T07:57:19.994066Z",
"iopub.status.idle": "2023-05-17T07:57:19.997953Z",
"shell.execute_reply": "2023-05-17T07:57:19.997125Z"
},
"tags": []
},
"outputs": [],
"source": [
"mydict = mutils.initialize_dict(images)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create captions for images and directly write to csv"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Here you can choose between two models: \"base\" or \"large\""
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"execution": {
"iopub.execute_input": "2023-05-17T07:57:20.001544Z",
"iopub.status.busy": "2023-05-17T07:57:20.001252Z",
"iopub.status.idle": "2023-05-17T07:57:34.285374Z",
"shell.execute_reply": "2023-05-17T07:57:34.284156Z"
},
"tags": []
},
"outputs": [
{
"ename": "OSError",
"evalue": "Can't load tokenizer for 'bert-base-uncased'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'bert-base-uncased' is the correct path to a directory containing all relevant files for a BertTokenizer tokenizer.",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mOSError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[4], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m obj \u001b[38;5;241m=\u001b[39m sm\u001b[38;5;241m.\u001b[39mSummaryDetector(mydict)\n\u001b[0;32m----> 2\u001b[0m summary_model, summary_vis_processors \u001b[38;5;241m=\u001b[39m \u001b[43mobj\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload_model\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mbase\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 3\u001b[0m \u001b[38;5;66;03m# summary_model, summary_vis_processors = obj.load_model(\"large\")\u001b[39;00m\n",
"File \u001b[0;32m~/work/AMMICO/AMMICO/ammico/summary.py:35\u001b[0m, in \u001b[0;36mSummaryDetector.load_model\u001b[0;34m(self, model_type)\u001b[0m\n\u001b[1;32m 30\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mload_model\u001b[39m(\u001b[38;5;28mself\u001b[39m, model_type):\n\u001b[1;32m 31\u001b[0m select_model \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m 32\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbase\u001b[39m\u001b[38;5;124m\"\u001b[39m: SummaryDetector\u001b[38;5;241m.\u001b[39mload_model_base,\n\u001b[1;32m 33\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlarge\u001b[39m\u001b[38;5;124m\"\u001b[39m: SummaryDetector\u001b[38;5;241m.\u001b[39mload_model_large,\n\u001b[1;32m 34\u001b[0m }\n\u001b[0;32m---> 35\u001b[0m summary_model, summary_vis_processors \u001b[38;5;241m=\u001b[39m \u001b[43mselect_model\u001b[49m\u001b[43m[\u001b[49m\u001b[43mmodel_type\u001b[49m\u001b[43m]\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 36\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m summary_model, summary_vis_processors\n",
"File \u001b[0;32m~/work/AMMICO/AMMICO/ammico/summary.py:13\u001b[0m, in \u001b[0;36mSummaryDetector.load_model_base\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 12\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mload_model_base\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[0;32m---> 13\u001b[0m summary_model, summary_vis_processors, _ \u001b[38;5;241m=\u001b[39m \u001b[43mload_model_and_preprocess\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 14\u001b[0m \u001b[43m \u001b[49m\u001b[43mname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mblip_caption\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 15\u001b[0m \u001b[43m \u001b[49m\u001b[43mmodel_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mbase_coco\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 16\u001b[0m \u001b[43m \u001b[49m\u001b[43mis_eval\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 17\u001b[0m \u001b[43m \u001b[49m\u001b[43mdevice\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msummary_device\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 18\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 19\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m summary_model, summary_vis_processors\n",
"File \u001b[0;32m/opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages/lavis/models/__init__.py:195\u001b[0m, in \u001b[0;36mload_model_and_preprocess\u001b[0;34m(name, model_type, is_eval, device)\u001b[0m\n\u001b[1;32m 192\u001b[0m model_cls \u001b[38;5;241m=\u001b[39m registry\u001b[38;5;241m.\u001b[39mget_model_class(name)\n\u001b[1;32m 194\u001b[0m \u001b[38;5;66;03m# load model\u001b[39;00m\n\u001b[0;32m--> 195\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[43mmodel_cls\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmodel_type\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 197\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_eval:\n\u001b[1;32m 198\u001b[0m model\u001b[38;5;241m.\u001b[39meval()\n",
"File \u001b[0;32m/opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages/lavis/models/base_model.py:70\u001b[0m, in \u001b[0;36mBaseModel.from_pretrained\u001b[0;34m(cls, model_type)\u001b[0m\n\u001b[1;32m 60\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 61\u001b[0m \u001b[38;5;124;03mBuild a pretrained model from default configuration file, specified by model_type.\u001b[39;00m\n\u001b[1;32m 62\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 67\u001b[0m \u001b[38;5;124;03m - model (nn.Module): pretrained or finetuned model, depending on the configuration.\u001b[39;00m\n\u001b[1;32m 68\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 69\u001b[0m model_cfg \u001b[38;5;241m=\u001b[39m OmegaConf\u001b[38;5;241m.\u001b[39mload(\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39mdefault_config_path(model_type))\u001b[38;5;241m.\u001b[39mmodel\n\u001b[0;32m---> 70\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_config\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_cfg\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 72\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m model\n",
"File \u001b[0;32m/opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages/lavis/models/blip_models/blip_caption.py:216\u001b[0m, in \u001b[0;36mBlipCaption.from_config\u001b[0;34m(cls, cfg)\u001b[0m\n\u001b[1;32m 213\u001b[0m prompt \u001b[38;5;241m=\u001b[39m cfg\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mprompt\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[1;32m 214\u001b[0m max_txt_len \u001b[38;5;241m=\u001b[39m cfg\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmax_txt_len\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;241m40\u001b[39m)\n\u001b[0;32m--> 216\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mimage_encoder\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtext_decoder\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mprompt\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprompt\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_txt_len\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmax_txt_len\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 217\u001b[0m model\u001b[38;5;241m.\u001b[39mload_checkpoint_from_config(cfg)\n\u001b[1;32m 219\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m model\n",
"File \u001b[0;32m/opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages/lavis/models/blip_models/blip_caption.py:43\u001b[0m, in \u001b[0;36mBlipCaption.__init__\u001b[0;34m(self, image_encoder, text_decoder, prompt, max_txt_len)\u001b[0m\n\u001b[1;32m 40\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__init__\u001b[39m(\u001b[38;5;28mself\u001b[39m, image_encoder, text_decoder, prompt\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, max_txt_len\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m40\u001b[39m):\n\u001b[1;32m 41\u001b[0m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__init__\u001b[39m()\n\u001b[0;32m---> 43\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtokenizer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minit_tokenizer\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 45\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvisual_encoder \u001b[38;5;241m=\u001b[39m image_encoder\n\u001b[1;32m 46\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtext_decoder \u001b[38;5;241m=\u001b[39m text_decoder\n",
"File \u001b[0;32m/opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages/lavis/models/blip_models/blip.py:22\u001b[0m, in \u001b[0;36mBlipBase.init_tokenizer\u001b[0;34m(cls)\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[38;5;129m@classmethod\u001b[39m\n\u001b[1;32m 21\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minit_tokenizer\u001b[39m(\u001b[38;5;28mcls\u001b[39m):\n\u001b[0;32m---> 22\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m \u001b[43mBertTokenizer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mbert-base-uncased\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 23\u001b[0m tokenizer\u001b[38;5;241m.\u001b[39madd_special_tokens({\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbos_token\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m[DEC]\u001b[39m\u001b[38;5;124m\"\u001b[39m})\n\u001b[1;32m 24\u001b[0m tokenizer\u001b[38;5;241m.\u001b[39madd_special_tokens({\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124madditional_special_tokens\u001b[39m\u001b[38;5;124m\"\u001b[39m: [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m[ENC]\u001b[39m\u001b[38;5;124m\"\u001b[39m]})\n",
"File \u001b[0;32m/opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages/transformers/tokenization_utils_base.py:1788\u001b[0m, in \u001b[0;36mPreTrainedTokenizerBase.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, *init_inputs, **kwargs)\u001b[0m\n\u001b[1;32m 1782\u001b[0m logger\u001b[38;5;241m.\u001b[39minfo(\n\u001b[1;32m 1783\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCan\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt load following files from cache: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00munresolved_files\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m and cannot check if these \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1784\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfiles are necessary for the tokenizer to operate.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1785\u001b[0m )\n\u001b[1;32m 1787\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mall\u001b[39m(full_file_name \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01mfor\u001b[39;00m full_file_name \u001b[38;5;129;01min\u001b[39;00m resolved_vocab_files\u001b[38;5;241m.\u001b[39mvalues()):\n\u001b[0;32m-> 1788\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m(\n\u001b[1;32m 1789\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCan\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt load tokenizer for \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpretrained_model_name_or_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m. If you were trying to load it from \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1790\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mhttps://huggingface.co/models\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m, make sure you don\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt have a local directory with the same name. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1791\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mOtherwise, make sure \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpretrained_model_name_or_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m is the correct path to a directory \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1792\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcontaining all relevant files for a \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m tokenizer.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1793\u001b[0m )\n\u001b[1;32m 1795\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m file_id, file_path \u001b[38;5;129;01min\u001b[39;00m vocab_files\u001b[38;5;241m.\u001b[39mitems():\n\u001b[1;32m 1796\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m file_id \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m resolved_vocab_files:\n",
"\u001b[0;31mOSError\u001b[0m: Can't load tokenizer for 'bert-base-uncased'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'bert-base-uncased' is the correct path to a directory containing all relevant files for a BertTokenizer tokenizer."
]
}
],
"source": [
"obj = sm.SummaryDetector(mydict)\n",
"summary_model, summary_vis_processors = obj.load_model(\"base\")\n",
"# summary_model, summary_vis_processors = obj.load_model(\"large\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"execution": {
"iopub.execute_input": "2023-05-17T07:57:34.289426Z",
"iopub.status.busy": "2023-05-17T07:57:34.288864Z",
"iopub.status.idle": "2023-05-17T07:57:34.334585Z",
"shell.execute_reply": "2023-05-17T07:57:34.333821Z"
},
"tags": []
},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'summary_model' is not defined",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[5], line 3\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key \u001b[38;5;129;01min\u001b[39;00m mydict:\n\u001b[1;32m 2\u001b[0m mydict[key] \u001b[38;5;241m=\u001b[39m sm\u001b[38;5;241m.\u001b[39mSummaryDetector(mydict[key])\u001b[38;5;241m.\u001b[39manalyse_image(\n\u001b[0;32m----> 3\u001b[0m \u001b[43msummary_model\u001b[49m, summary_vis_processors\n\u001b[1;32m 4\u001b[0m )\n",
"\u001b[0;31mNameError\u001b[0m: name 'summary_model' is not defined"
]
}
],
"source": [
"for key in mydict:\n",
" mydict[key] = sm.SummaryDetector(mydict[key]).analyse_image(\n",
" summary_model, summary_vis_processors\n",
" )"
]
},
{
"cell_type": "markdown",
"metadata": {
"tags": []
},
"source": [
"Convert the dictionary of dictionaries into a dictionary with lists:"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"execution": {
"iopub.execute_input": "2023-05-17T07:57:34.342485Z",
"iopub.status.busy": "2023-05-17T07:57:34.337901Z",
"iopub.status.idle": "2023-05-17T07:57:34.351702Z",
"shell.execute_reply": "2023-05-17T07:57:34.350828Z"
},
"tags": []
},
"outputs": [],
"source": [
"outdict = mutils.append_data_to_dict(mydict)\n",
"df = mutils.dump_df(outdict)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Check the dataframe:"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"execution": {
"iopub.execute_input": "2023-05-17T07:57:34.355521Z",
"iopub.status.busy": "2023-05-17T07:57:34.355242Z",
"iopub.status.idle": "2023-05-17T07:57:34.366774Z",
"shell.execute_reply": "2023-05-17T07:57:34.365973Z"
},
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>filename</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>data/102730_eng.png</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>data/102141_2_eng.png</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>data/106349S_por.png</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" filename\n",
"0 data/102730_eng.png\n",
"1 data/102141_2_eng.png\n",
"2 data/106349S_por.png"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head(10)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Write the csv file:"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"execution": {
"iopub.execute_input": "2023-05-17T07:57:34.370375Z",
"iopub.status.busy": "2023-05-17T07:57:34.369877Z",
"iopub.status.idle": "2023-05-17T07:57:34.375313Z",
"shell.execute_reply": "2023-05-17T07:57:34.374633Z"
},
"tags": []
},
"outputs": [],
"source": [
"df.to_csv(\"./data_out.csv\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Manually inspect the summaries\n",
"\n",
"To check the analysis, you can inspect the analyzed elements here. Loading the results takes a moment, so please be patient. If you are sure of what you are doing.\n",
"\n",
"`const_image_summary` - the permanent summarys, which does not change from run to run (analyse_image).\n",
"\n",
"`3_non-deterministic summary` - 3 different summarys examples that change from run to run (analyse_image). "
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"execution": {
"iopub.execute_input": "2023-05-17T07:57:34.378686Z",
"iopub.status.busy": "2023-05-17T07:57:34.378174Z",
"iopub.status.idle": "2023-05-17T07:57:34.417753Z",
"shell.execute_reply": "2023-05-17T07:57:34.416811Z"
},
"tags": []
},
"outputs": [
{
"ename": "AttributeError",
"evalue": "module 'ammico.display' has no attribute 'explore_analysis'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[9], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mmdisplay\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mexplore_analysis\u001b[49m(mydict, identify\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msummary\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
"\u001b[0;31mAttributeError\u001b[0m: module 'ammico.display' has no attribute 'explore_analysis'"
]
}
],
"source": [
"mdisplay.explore_analysis(mydict, identify=\"summary\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Generate answers to free-form questions about images written in natural language. "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Set the list of questions"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"execution": {
"iopub.execute_input": "2023-05-17T07:57:34.421632Z",
"iopub.status.busy": "2023-05-17T07:57:34.421120Z",
"iopub.status.idle": "2023-05-17T07:57:34.424792Z",
"shell.execute_reply": "2023-05-17T07:57:34.424044Z"
}
},
"outputs": [],
"source": [
"list_of_questions = [\n",
" \"How many persons on the picture?\",\n",
" \"Are there any politicians in the picture?\",\n",
" \"Does the picture show something from medicine?\",\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"execution": {
"iopub.execute_input": "2023-05-17T07:57:34.428232Z",
"iopub.status.busy": "2023-05-17T07:57:34.427624Z",
"iopub.status.idle": "2023-05-17T07:58:22.391001Z",
"shell.execute_reply": "2023-05-17T07:58:22.389910Z"
}
},
"outputs": [
{
"ename": "OSError",
"evalue": "Can't load tokenizer for 'bert-base-uncased'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'bert-base-uncased' is the correct path to a directory containing all relevant files for a BertTokenizer tokenizer.",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mOSError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[11], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key \u001b[38;5;129;01min\u001b[39;00m mydict:\n\u001b[0;32m----> 2\u001b[0m mydict[key] \u001b[38;5;241m=\u001b[39m \u001b[43msm\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mSummaryDetector\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmydict\u001b[49m\u001b[43m[\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43manalyse_questions\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlist_of_questions\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/work/AMMICO/AMMICO/ammico/summary.py:63\u001b[0m, in \u001b[0;36mSummaryDetector.analyse_questions\u001b[0;34m(self, list_of_questions)\u001b[0m\n\u001b[1;32m 58\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21manalyse_questions\u001b[39m(\u001b[38;5;28mself\u001b[39m, list_of_questions):\n\u001b[1;32m 59\u001b[0m (\n\u001b[1;32m 60\u001b[0m summary_vqa_model,\n\u001b[1;32m 61\u001b[0m summary_vqa_vis_processors,\n\u001b[1;32m 62\u001b[0m summary_vqa_txt_processors,\n\u001b[0;32m---> 63\u001b[0m ) \u001b[38;5;241m=\u001b[39m \u001b[43mload_model_and_preprocess\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 64\u001b[0m \u001b[43m \u001b[49m\u001b[43mname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mblip_vqa\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 65\u001b[0m \u001b[43m \u001b[49m\u001b[43mmodel_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mvqav2\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 66\u001b[0m \u001b[43m \u001b[49m\u001b[43mis_eval\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 67\u001b[0m \u001b[43m \u001b[49m\u001b[43mdevice\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msummary_device\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 68\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 69\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(list_of_questions) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m 70\u001b[0m path \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msubdict[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfilename\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n",
"File \u001b[0;32m/opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages/lavis/models/__init__.py:195\u001b[0m, in \u001b[0;36mload_model_and_preprocess\u001b[0;34m(name, model_type, is_eval, device)\u001b[0m\n\u001b[1;32m 192\u001b[0m model_cls \u001b[38;5;241m=\u001b[39m registry\u001b[38;5;241m.\u001b[39mget_model_class(name)\n\u001b[1;32m 194\u001b[0m \u001b[38;5;66;03m# load model\u001b[39;00m\n\u001b[0;32m--> 195\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[43mmodel_cls\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmodel_type\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 197\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_eval:\n\u001b[1;32m 198\u001b[0m model\u001b[38;5;241m.\u001b[39meval()\n",
"File \u001b[0;32m/opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages/lavis/models/base_model.py:70\u001b[0m, in \u001b[0;36mBaseModel.from_pretrained\u001b[0;34m(cls, model_type)\u001b[0m\n\u001b[1;32m 60\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 61\u001b[0m \u001b[38;5;124;03mBuild a pretrained model from default configuration file, specified by model_type.\u001b[39;00m\n\u001b[1;32m 62\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 67\u001b[0m \u001b[38;5;124;03m - model (nn.Module): pretrained or finetuned model, depending on the configuration.\u001b[39;00m\n\u001b[1;32m 68\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 69\u001b[0m model_cfg \u001b[38;5;241m=\u001b[39m OmegaConf\u001b[38;5;241m.\u001b[39mload(\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39mdefault_config_path(model_type))\u001b[38;5;241m.\u001b[39mmodel\n\u001b[0;32m---> 70\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_config\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_cfg\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 72\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m model\n",
"File \u001b[0;32m/opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages/lavis/models/blip_models/blip_vqa.py:366\u001b[0m, in \u001b[0;36mBlipVQA.from_config\u001b[0;34m(cls, cfg)\u001b[0m\n\u001b[1;32m 362\u001b[0m text_decoder \u001b[38;5;241m=\u001b[39m XBertLMHeadDecoder\u001b[38;5;241m.\u001b[39mfrom_config(cfg)\n\u001b[1;32m 364\u001b[0m max_txt_len \u001b[38;5;241m=\u001b[39m cfg\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmax_txt_len\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;241m35\u001b[39m)\n\u001b[0;32m--> 366\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m 367\u001b[0m \u001b[43m \u001b[49m\u001b[43mimage_encoder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mimage_encoder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 368\u001b[0m \u001b[43m \u001b[49m\u001b[43mtext_encoder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtext_encoder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 369\u001b[0m \u001b[43m \u001b[49m\u001b[43mtext_decoder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtext_decoder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 370\u001b[0m \u001b[43m \u001b[49m\u001b[43mmax_txt_len\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmax_txt_len\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 371\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 373\u001b[0m model\u001b[38;5;241m.\u001b[39mload_checkpoint_from_config(cfg)\n\u001b[1;32m 375\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m model\n",
"File \u001b[0;32m/opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages/lavis/models/blip_models/blip_vqa.py:45\u001b[0m, in \u001b[0;36mBlipVQA.__init__\u001b[0;34m(self, image_encoder, text_encoder, text_decoder, max_txt_len)\u001b[0m\n\u001b[1;32m 43\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__init__\u001b[39m(\u001b[38;5;28mself\u001b[39m, image_encoder, text_encoder, text_decoder, max_txt_len\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m35\u001b[39m):\n\u001b[1;32m 44\u001b[0m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__init__\u001b[39m()\n\u001b[0;32m---> 45\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtokenizer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minit_tokenizer\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 47\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvisual_encoder \u001b[38;5;241m=\u001b[39m image_encoder\n\u001b[1;32m 49\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtext_encoder \u001b[38;5;241m=\u001b[39m text_encoder\n",
"File \u001b[0;32m/opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages/lavis/models/blip_models/blip.py:22\u001b[0m, in \u001b[0;36mBlipBase.init_tokenizer\u001b[0;34m(cls)\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[38;5;129m@classmethod\u001b[39m\n\u001b[1;32m 21\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minit_tokenizer\u001b[39m(\u001b[38;5;28mcls\u001b[39m):\n\u001b[0;32m---> 22\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m \u001b[43mBertTokenizer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mbert-base-uncased\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 23\u001b[0m tokenizer\u001b[38;5;241m.\u001b[39madd_special_tokens({\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbos_token\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m[DEC]\u001b[39m\u001b[38;5;124m\"\u001b[39m})\n\u001b[1;32m 24\u001b[0m tokenizer\u001b[38;5;241m.\u001b[39madd_special_tokens({\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124madditional_special_tokens\u001b[39m\u001b[38;5;124m\"\u001b[39m: [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m[ENC]\u001b[39m\u001b[38;5;124m\"\u001b[39m]})\n",
"File \u001b[0;32m/opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages/transformers/tokenization_utils_base.py:1788\u001b[0m, in \u001b[0;36mPreTrainedTokenizerBase.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, *init_inputs, **kwargs)\u001b[0m\n\u001b[1;32m 1782\u001b[0m logger\u001b[38;5;241m.\u001b[39minfo(\n\u001b[1;32m 1783\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCan\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt load following files from cache: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00munresolved_files\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m and cannot check if these \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1784\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfiles are necessary for the tokenizer to operate.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1785\u001b[0m )\n\u001b[1;32m 1787\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mall\u001b[39m(full_file_name \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01mfor\u001b[39;00m full_file_name \u001b[38;5;129;01min\u001b[39;00m resolved_vocab_files\u001b[38;5;241m.\u001b[39mvalues()):\n\u001b[0;32m-> 1788\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m(\n\u001b[1;32m 1789\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCan\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt load tokenizer for \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpretrained_model_name_or_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m. If you were trying to load it from \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1790\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mhttps://huggingface.co/models\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m, make sure you don\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt have a local directory with the same name. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1791\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mOtherwise, make sure \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpretrained_model_name_or_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m is the correct path to a directory \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1792\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcontaining all relevant files for a \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m tokenizer.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1793\u001b[0m )\n\u001b[1;32m 1795\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m file_id, file_path \u001b[38;5;129;01min\u001b[39;00m vocab_files\u001b[38;5;241m.\u001b[39mitems():\n\u001b[1;32m 1796\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m file_id \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m resolved_vocab_files:\n",
"\u001b[0;31mOSError\u001b[0m: Can't load tokenizer for 'bert-base-uncased'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'bert-base-uncased' is the correct path to a directory containing all relevant files for a BertTokenizer tokenizer."
]
}
],
"source": [
"for key in mydict:\n",
" mydict[key] = sm.SummaryDetector(mydict[key]).analyse_questions(list_of_questions)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"execution": {
"iopub.execute_input": "2023-05-17T07:58:22.397270Z",
"iopub.status.busy": "2023-05-17T07:58:22.396986Z",
"iopub.status.idle": "2023-05-17T07:58:22.440375Z",
"shell.execute_reply": "2023-05-17T07:58:22.439514Z"
}
},
"outputs": [
{
"ename": "AttributeError",
"evalue": "module 'ammico.display' has no attribute 'explore_analysis'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[12], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mmdisplay\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mexplore_analysis\u001b[49m(mydict, identify\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msummary\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
"\u001b[0;31mAttributeError\u001b[0m: module 'ammico.display' has no attribute 'explore_analysis'"
]
}
],
"source": [
"mdisplay.explore_analysis(mydict, identify=\"summary\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Convert the dictionary of dictionarys into a dictionary with lists:"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"execution": {
"iopub.execute_input": "2023-05-17T07:58:22.444018Z",
"iopub.status.busy": "2023-05-17T07:58:22.443467Z",
"iopub.status.idle": "2023-05-17T07:58:22.447814Z",
"shell.execute_reply": "2023-05-17T07:58:22.447057Z"
}
},
"outputs": [],
"source": [
"outdict2 = mutils.append_data_to_dict(mydict)\n",
"df2 = mutils.dump_df(outdict2)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"execution": {
"iopub.execute_input": "2023-05-17T07:58:22.451680Z",
"iopub.status.busy": "2023-05-17T07:58:22.451163Z",
"iopub.status.idle": "2023-05-17T07:58:22.458395Z",
"shell.execute_reply": "2023-05-17T07:58:22.457632Z"
}
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>filename</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>data/102730_eng.png</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>data/102141_2_eng.png</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>data/106349S_por.png</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" filename\n",
"0 data/102730_eng.png\n",
"1 data/102141_2_eng.png\n",
"2 data/106349S_por.png"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df2.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"execution": {
"iopub.execute_input": "2023-05-17T07:58:22.462659Z",
"iopub.status.busy": "2023-05-17T07:58:22.462233Z",
"iopub.status.idle": "2023-05-17T07:58:22.466883Z",
"shell.execute_reply": "2023-05-17T07:58:22.466222Z"
}
},
"outputs": [],
"source": [
"df2.to_csv(\"./data_out2.csv\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.9.16"
},
"vscode": {
"interpreter": {
"hash": "f1142466f556ab37fe2d38e2897a16796906208adb09fea90ba58bdf8a56f0ba"
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Ссылка в новой задаче Показать git blame Копировать постоянную ссылку