locsec/AMMICO
1
Форкнуть 0
зеркало из https://github.com/ssciwr/AMMICO.git synced 2025-10-31 22:16:05 +02:00
Код Задачи Пакеты Проекты Релизы Вики Активность
AMMICO/build/doctrees/nbsphinx/notebooks/Example summary.ipynb

2375 строки
55 KiB
Plaintext
Исходник Ответственный История

{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Image summary and visual question answering"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"This notebooks shows how to generate image captions and use the visual question answering with [LAVIS](https://github.com/salesforce/LAVIS). \n",
"\n",
"The first cell is only run on google colab and installs the [ammico](https://github.com/ssciwr/AMMICO) package.\n",
"\n",
"After that, we can import `ammico` and read in the files given a folder path."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:57:40.471566Z",
"iopub.status.busy": "2023-06-14T17:57:40.470552Z",
"iopub.status.idle": "2023-06-14T17:57:40.479784Z",
"shell.execute_reply": "2023-06-14T17:57:40.479228Z"
}
},
"outputs": [],
"source": [
"# if running on google colab\n",
"# flake8-noqa-cell\n",
"import os\n",
"\n",
"if \"google.colab\" in str(get_ipython()):\n",
" # update python version\n",
" # install setuptools\n",
" # %pip install setuptools==61 -qqq\n",
" # install ammico\n",
" %pip install git+https://github.com/ssciwr/ammico.git -qqq\n",
" # mount google drive for data and API key\n",
" from google.colab import drive\n",
"\n",
" drive.mount(\"/content/drive\")"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:57:40.482843Z",
"iopub.status.busy": "2023-06-14T17:57:40.482198Z",
"iopub.status.idle": "2023-06-14T17:57:51.419141Z",
"shell.execute_reply": "2023-06-14T17:57:51.418473Z"
},
"tags": []
},
"outputs": [],
"source": [
"import ammico\n",
"from ammico import utils as mutils\n",
"from ammico import display as mdisplay\n",
"import ammico.summary as sm"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:57:51.422490Z",
"iopub.status.busy": "2023-06-14T17:57:51.421852Z",
"iopub.status.idle": "2023-06-14T17:57:51.426521Z",
"shell.execute_reply": "2023-06-14T17:57:51.425961Z"
},
"tags": []
},
"outputs": [],
"source": [
"# Here you need to provide the path to your google drive folder\n",
"# or local folder containing the images\n",
"images = mutils.find_files(\n",
" path=\"data/\",\n",
" limit=10,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:57:51.429189Z",
"iopub.status.busy": "2023-06-14T17:57:51.428852Z",
"iopub.status.idle": "2023-06-14T17:57:51.432029Z",
"shell.execute_reply": "2023-06-14T17:57:51.431394Z"
},
"tags": []
},
"outputs": [],
"source": [
"mydict = mutils.initialize_dict(images)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create captions for images and directly write to csv"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Here you can choose between two models: \"base\" or \"large\". This will generate the caption for each image and directly put the results in a dataframe. This dataframe can be exported as a csv file.\n",
"\n",
"The results are written into the columns `const_image_summary` - this will always be the same result (as always the same seed will be used). The column `3_non-deterministic summary` displays three different answers generated with different seeds, these are most likely different when you run the analysis again."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:57:51.435313Z",
"iopub.status.busy": "2023-06-14T17:57:51.434728Z",
"iopub.status.idle": "2023-06-14T17:58:19.346682Z",
"shell.execute_reply": "2023-06-14T17:58:19.345925Z"
},
"tags": []
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 0%| | 0.00/2.50G [00:00<?, ?B/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 0%| | 6.99M/2.50G [00:00<00:36, 73.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 15.3M/2.50G [00:00<00:32, 81.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 23.0M/2.50G [00:00<00:33, 79.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 30.9M/2.50G [00:00<00:32, 80.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 40.0M/2.50G [00:00<00:32, 82.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 48.0M/2.50G [00:00<00:33, 78.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 56.0M/2.50G [00:00<00:33, 78.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 72.0M/2.50G [00:00<00:29, 89.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 85.5M/2.50G [00:00<00:25, 104MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▎ | 95.5M/2.50G [00:01<00:25, 100MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▍ | 105M/2.50G [00:01<00:37, 69.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▍ | 120M/2.50G [00:01<00:29, 86.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▌ | 136M/2.50G [00:01<00:24, 104MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 6%|▌ | 152M/2.50G [00:01<00:22, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 7%|▋ | 170M/2.50G [00:01<00:19, 132MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 7%|▋ | 184M/2.50G [00:01<00:18, 136MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 8%|▊ | 202M/2.50G [00:02<00:16, 150MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 9%|▊ | 224M/2.50G [00:02<00:14, 171MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 9%|▉ | 241M/2.50G [00:02<00:15, 161MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|█ | 257M/2.50G [00:02<00:14, 163MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 11%|█ | 273M/2.50G [00:02<00:16, 150MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 11%|█ | 287M/2.50G [00:02<00:16, 141MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 12%|█▏ | 301M/2.50G [00:02<00:17, 132MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 13%|█▎ | 322M/2.50G [00:02<00:15, 154MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 13%|█▎ | 337M/2.50G [00:02<00:15, 146MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 14%|█▍ | 359M/2.50G [00:03<00:13, 168MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 15%|█▍ | 376M/2.50G [00:03<00:14, 158MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 16%|█▌ | 398M/2.50G [00:03<00:12, 178MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 16%|█▋ | 417M/2.50G [00:03<00:12, 183MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 17%|█▋ | 438M/2.50G [00:03<00:11, 195MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 18%|█▊ | 457M/2.50G [00:03<00:12, 174MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 19%|█▊ | 479M/2.50G [00:03<00:11, 189MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|█▉ | 501M/2.50G [00:03<00:10, 199MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|██ | 521M/2.50G [00:03<00:10, 204MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 21%|██ | 543M/2.50G [00:04<00:10, 211MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 22%|██▏ | 563M/2.50G [00:04<00:10, 204MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 23%|██▎ | 584M/2.50G [00:04<00:09, 208MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 24%|██▎ | 606M/2.50G [00:04<00:09, 215MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 24%|██▍ | 628M/2.50G [00:04<00:09, 218MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 25%|██▌ | 648M/2.50G [00:04<00:09, 215MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 26%|██▌ | 670M/2.50G [00:04<00:09, 219MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 691M/2.50G [00:04<00:09, 212MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 28%|██▊ | 713M/2.50G [00:04<00:08, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 29%|██▊ | 735M/2.50G [00:04<00:08, 221MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 30%|██▉ | 757M/2.50G [00:05<00:08, 223MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 30%|███ | 778M/2.50G [00:05<00:10, 186MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 31%|███ | 800M/2.50G [00:05<00:09, 197MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 32%|███▏ | 822M/2.50G [00:05<00:08, 205MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 33%|███▎ | 843M/2.50G [00:05<00:08, 211MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 34%|███▍ | 865M/2.50G [00:05<00:08, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 35%|███▍ | 886M/2.50G [00:05<00:09, 195MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 35%|███▌ | 906M/2.50G [00:05<00:10, 169MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 36%|███▌ | 923M/2.50G [00:06<00:10, 171MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 37%|███▋ | 944M/2.50G [00:06<00:09, 184MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 38%|███▊ | 965M/2.50G [00:06<00:08, 195MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 38%|███▊ | 987M/2.50G [00:06<00:08, 204MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 39%|███▉ | 0.98G/2.50G [00:06<00:07, 210MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 40%|████ | 1.01G/2.50G [00:06<00:07, 213MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 41%|████ | 1.03G/2.50G [00:06<00:07, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 42%|████▏ | 1.05G/2.50G [00:06<00:07, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 43%|████▎ | 1.07G/2.50G [00:06<00:06, 222MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 44%|████▎ | 1.09G/2.50G [00:06<00:06, 224MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 44%|████▍ | 1.11G/2.50G [00:07<00:06, 219MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 45%|████▌ | 1.13G/2.50G [00:07<00:06, 213MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 46%|████▌ | 1.15G/2.50G [00:07<00:06, 218MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 47%|████▋ | 1.17G/2.50G [00:07<00:06, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 48%|████▊ | 1.19G/2.50G [00:07<00:06, 218MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 49%|████▊ | 1.21G/2.50G [00:07<00:06, 220MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 49%|████▉ | 1.24G/2.50G [00:07<00:06, 224MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 50%|█████ | 1.26G/2.50G [00:07<00:05, 226MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 51%|█████ | 1.28G/2.50G [00:07<00:05, 227MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 52%|█████▏ | 1.30G/2.50G [00:07<00:05, 227MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 53%|█████▎ | 1.32G/2.50G [00:08<00:05, 215MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 54%|█████▎ | 1.34G/2.50G [00:08<00:05, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 54%|█████▍ | 1.36G/2.50G [00:08<00:05, 218MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 55%|█████▌ | 1.38G/2.50G [00:08<00:05, 221MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 56%|█████▌ | 1.40G/2.50G [00:08<00:05, 221MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 57%|█████▋ | 1.43G/2.50G [00:08<00:05, 221MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 58%|█████▊ | 1.45G/2.50G [00:08<00:05, 222MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 59%|█████▊ | 1.47G/2.50G [00:08<00:04, 224MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 59%|█████▉ | 1.49G/2.50G [00:09<00:09, 120MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 60%|██████ | 1.51G/2.50G [00:09<00:07, 140MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 61%|██████ | 1.53G/2.50G [00:09<00:06, 157MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 62%|██████▏ | 1.55G/2.50G [00:09<00:05, 173MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 63%|██████▎ | 1.57G/2.50G [00:09<00:06, 162MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 64%|██████▎ | 1.59G/2.50G [00:09<00:05, 178MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 64%|██████▍ | 1.61G/2.50G [00:09<00:05, 177MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 65%|██████▌ | 1.63G/2.50G [00:09<00:05, 174MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 66%|██████▌ | 1.65G/2.50G [00:10<00:07, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 67%|██████▋ | 1.67G/2.50G [00:10<00:06, 137MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 67%|██████▋ | 1.69G/2.50G [00:10<00:05, 155MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 68%|██████▊ | 1.70G/2.50G [00:10<00:06, 131MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 69%|██████▊ | 1.72G/2.50G [00:10<00:06, 135MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 69%|██████▉ | 1.73G/2.50G [00:10<00:06, 128MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 70%|███████ | 1.75G/2.50G [00:10<00:05, 151MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 71%|███████ | 1.77G/2.50G [00:11<00:04, 159MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 72%|███████▏ | 1.79G/2.50G [00:11<00:04, 177MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 72%|███████▏ | 1.81G/2.50G [00:11<00:03, 191MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 73%|███████▎ | 1.83G/2.50G [00:11<00:04, 162MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 74%|███████▍ | 1.85G/2.50G [00:11<00:04, 152MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 75%|███████▍ | 1.87G/2.50G [00:11<00:03, 173MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▌ | 1.89G/2.50G [00:11<00:03, 173MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▋ | 1.91G/2.50G [00:11<00:03, 187MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 77%|███████▋ | 1.93G/2.50G [00:12<00:03, 197MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 78%|███████▊ | 1.95G/2.50G [00:12<00:02, 205MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 79%|███████▉ | 1.97G/2.50G [00:12<00:03, 171MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|███████▉ | 1.99G/2.50G [00:12<00:02, 185MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|████████ | 2.01G/2.50G [00:12<00:02, 194MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 81%|████████▏ | 2.04G/2.50G [00:12<00:02, 203MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 82%|████████▏ | 2.06G/2.50G [00:12<00:02, 210MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 83%|████████▎ | 2.08G/2.50G [00:12<00:02, 213MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 84%|████████▍ | 2.10G/2.50G [00:12<00:01, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 85%|████████▍ | 2.12G/2.50G [00:13<00:04, 95.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 85%|████████▌ | 2.13G/2.50G [00:13<00:04, 90.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 86%|████████▌ | 2.16G/2.50G [00:13<00:03, 113MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 87%|████████▋ | 2.18G/2.50G [00:13<00:02, 134MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 88%|████████▊ | 2.19G/2.50G [00:14<00:02, 115MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 89%|████████▊ | 2.22G/2.50G [00:14<00:02, 136MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 89%|████████▉ | 2.23G/2.50G [00:15<00:05, 52.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|████████▉ | 2.25G/2.50G [00:15<00:03, 68.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 91%|█████████ | 2.27G/2.50G [00:15<00:03, 70.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 91%|█████████▏| 2.29G/2.50G [00:15<00:02, 91.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 2.30G/2.50G [00:15<00:02, 88.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 93%|█████████▎| 2.32G/2.50G [00:15<00:01, 112MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▎| 2.34G/2.50G [00:15<00:01, 131MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▍| 2.36G/2.50G [00:16<00:01, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 95%|█████████▍| 2.37G/2.50G [00:16<00:01, 110MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 95%|█████████▌| 2.39G/2.50G [00:16<00:01, 65.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▌| 2.40G/2.50G [00:17<00:02, 46.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 97%|█████████▋| 2.42G/2.50G [00:17<00:01, 67.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 97%|█████████▋| 2.43G/2.50G [00:17<00:01, 65.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 98%|█████████▊| 2.45G/2.50G [00:17<00:00, 85.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 98%|█████████▊| 2.47G/2.50G [00:17<00:00, 105MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 99%|█████████▉| 2.48G/2.50G [00:17<00:00, 80.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|█████████▉| 2.50G/2.50G [00:18<00:00, 104MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 2.50G/2.50G [00:18<00:00, 148MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
}
],
"source": [
"obj = sm.SummaryDetector(mydict)\n",
"summary_model, summary_vis_processors = obj.load_model(model_type=\"base\")\n",
"# summary_model, summary_vis_processors = mutils.load_model(\"large\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:58:19.351111Z",
"iopub.status.busy": "2023-06-14T17:58:19.350697Z",
"iopub.status.idle": "2023-06-14T17:58:53.233661Z",
"shell.execute_reply": "2023-06-14T17:58:53.233035Z"
},
"tags": []
},
"outputs": [],
"source": [
"for key in mydict:\n",
" mydict[key] = sm.SummaryDetector(mydict[key]).analyse_image(\n",
" summary_model=summary_model, summary_vis_processors=summary_vis_processors\n",
" )"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"tags": []
},
"source": [
"Convert the dictionary of dictionarys into a dictionary with lists:"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:58:53.237164Z",
"iopub.status.busy": "2023-06-14T17:58:53.236674Z",
"iopub.status.idle": "2023-06-14T17:58:53.240506Z",
"shell.execute_reply": "2023-06-14T17:58:53.239983Z"
},
"tags": []
},
"outputs": [],
"source": [
"outdict = mutils.append_data_to_dict(mydict)\n",
"df = mutils.dump_df(outdict)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Check the dataframe:"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:58:53.243495Z",
"iopub.status.busy": "2023-06-14T17:58:53.242775Z",
"iopub.status.idle": "2023-06-14T17:58:53.255014Z",
"shell.execute_reply": "2023-06-14T17:58:53.254472Z"
},
"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",
" <th>const_image_summary</th>\n",
" <th>3_non-deterministic summary</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>data/102730_eng.png</td>\n",
" <td>two people in blue coats spray disinfection a van</td>\n",
" <td>[two people with blue robes are spraying water...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>data/106349S_por.png</td>\n",
" <td>a man wearing a face mask while looking at a c...</td>\n",
" <td>[an image of a television screen that has a ma...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>data/102141_2_eng.png</td>\n",
" <td>a collage of images including a corona sign, a...</td>\n",
" <td>[a hand holding an empty tube and another phot...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" filename const_image_summary \\\n",
"0 data/102730_eng.png two people in blue coats spray disinfection a van \n",
"1 data/106349S_por.png a man wearing a face mask while looking at a c... \n",
"2 data/102141_2_eng.png a collage of images including a corona sign, a... \n",
"\n",
" 3_non-deterministic summary \n",
"0 [two people with blue robes are spraying water... \n",
"1 [an image of a television screen that has a ma... \n",
"2 [a hand holding an empty tube and another phot... "
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head(10)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Write the csv file:"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:58:53.257953Z",
"iopub.status.busy": "2023-06-14T17:58:53.257445Z",
"iopub.status.idle": "2023-06-14T17:58:53.262544Z",
"shell.execute_reply": "2023-06-14T17:58:53.262010Z"
}
},
"outputs": [],
"source": [
"df.to_csv(\"data_out.csv\")"
]
},
{
"attachments": {},
"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": 10,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:58:53.265362Z",
"iopub.status.busy": "2023-06-14T17:58:53.264878Z",
"iopub.status.idle": "2023-06-14T17:58:53.311443Z",
"shell.execute_reply": "2023-06-14T17:58:53.310745Z"
},
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Dash is running on http://127.0.0.1:8055/\n",
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:dash.dash:Dash is running on http://127.0.0.1:8055/\n",
"\n"
]
},
{
"data": {
"text/html": [
"\n",
" <iframe\n",
" width=\"100%\"\n",
" height=\"650\"\n",
" src=\"http://127.0.0.1:8055/\"\n",
" frameborder=\"0\"\n",
" allowfullscreen\n",
" \n",
" ></iframe>\n",
" "
],
"text/plain": [
"<IPython.lib.display.IFrame at 0x7fea1c7117f0>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"analysis_explorer = mdisplay.AnalysisExplorer(mydict, identify=\"summary\")\n",
"analysis_explorer.run_server(port=8055)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Generate answers to free-form questions about images written in natural language. "
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Set the list of questions as a list of strings:"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:58:53.314849Z",
"iopub.status.busy": "2023-06-14T17:58:53.314379Z",
"iopub.status.idle": "2023-06-14T17:58:53.317692Z",
"shell.execute_reply": "2023-06-14T17:58:53.317049Z"
}
},
"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",
"]"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Explore the analysis using the interface:"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:58:53.320760Z",
"iopub.status.busy": "2023-06-14T17:58:53.320175Z",
"iopub.status.idle": "2023-06-14T17:58:53.840610Z",
"shell.execute_reply": "2023-06-14T17:58:53.839967Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Dash is running on http://127.0.0.1:8055/\n",
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:dash.dash:Dash is running on http://127.0.0.1:8055/\n",
"\n"
]
},
{
"data": {
"text/html": [
"\n",
" <iframe\n",
" width=\"100%\"\n",
" height=\"650\"\n",
" src=\"http://127.0.0.1:8055/\"\n",
" frameborder=\"0\"\n",
" allowfullscreen\n",
" \n",
" ></iframe>\n",
" "
],
"text/plain": [
"<IPython.lib.display.IFrame at 0x7fea1c96ae50>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"analysis_explorer = mdisplay.AnalysisExplorer(mydict, identify=\"summary\")\n",
"analysis_explorer.run_server(port=8055)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Or directly analyze for further processing\n",
"Instead of inspecting each of the images, you can also directly carry out the analysis and export the result into a csv. This may take a while depending on how many images you have loaded."
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:58:53.844313Z",
"iopub.status.busy": "2023-06-14T17:58:53.843678Z",
"iopub.status.idle": "2023-06-14T17:59:41.700852Z",
"shell.execute_reply": "2023-06-14T17:59:41.700142Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 0%| | 0.00/1.35G [00:00<?, ?B/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 0%| | 4.72M/1.35G [00:00<00:29, 49.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 16.0M/1.35G [00:00<00:17, 80.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 25.2M/1.35G [00:00<00:16, 87.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 40.0M/1.35G [00:00<00:13, 106MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▍ | 55.9M/1.35G [00:00<00:10, 126MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▍ | 68.9M/1.35G [00:00<00:10, 129MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 6%|▌ | 85.7M/1.35G [00:00<00:09, 144MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 7%|▋ | 103M/1.35G [00:00<00:08, 157MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 9%|▊ | 118M/1.35G [00:00<00:08, 149MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|▉ | 134M/1.35G [00:01<00:08, 153MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 11%|█ | 152M/1.35G [00:01<00:08, 143MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 12%|█▏ | 172M/1.35G [00:01<00:07, 161MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 14%|█▍ | 192M/1.35G [00:01<00:07, 176MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 15%|█▌ | 212M/1.35G [00:01<00:06, 185MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 17%|█▋ | 233M/1.35G [00:01<00:06, 193MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 18%|█▊ | 254M/1.35G [00:01<00:05, 201MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|█▉ | 274M/1.35G [00:01<00:05, 206MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 21%|██▏ | 295M/1.35G [00:01<00:05, 210MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 23%|██▎ | 315M/1.35G [00:02<00:05, 209MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 24%|██▍ | 336M/1.35G [00:02<00:05, 211MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 26%|██▌ | 357M/1.35G [00:02<00:05, 214MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 378M/1.35G [00:02<00:04, 214MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 29%|██▉ | 398M/1.35G [00:02<00:04, 215MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 30%|███ | 419M/1.35G [00:02<00:04, 214MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 32%|███▏ | 439M/1.35G [00:02<00:04, 213MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 33%|███▎ | 460M/1.35G [00:02<00:04, 211MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 35%|███▍ | 480M/1.35G [00:02<00:04, 212MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 36%|███▋ | 500M/1.35G [00:02<00:04, 213MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 38%|███▊ | 521M/1.35G [00:03<00:04, 214MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 39%|███▉ | 542M/1.35G [00:03<00:04, 215MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 41%|████ | 562M/1.35G [00:03<00:04, 214MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 42%|████▏ | 583M/1.35G [00:03<00:03, 216MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 44%|████▍ | 604M/1.35G [00:03<00:03, 212MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 45%|████▌ | 624M/1.35G [00:03<00:03, 210MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 47%|████▋ | 644M/1.35G [00:03<00:03, 208MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 48%|████▊ | 664M/1.35G [00:03<00:03, 206MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 50%|████▉ | 684M/1.35G [00:03<00:03, 209MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 51%|█████ | 705M/1.35G [00:03<00:03, 210MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 53%|█████▎ | 725M/1.35G [00:04<00:03, 212MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 54%|█████▍ | 746M/1.35G [00:04<00:03, 210MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 56%|█████▌ | 766M/1.35G [00:04<00:03, 211MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 57%|█████▋ | 786M/1.35G [00:04<00:03, 202MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 58%|█████▊ | 806M/1.35G [00:04<00:02, 203MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 60%|█████▉ | 826M/1.35G [00:04<00:02, 205MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 61%|██████▏ | 845M/1.35G [00:04<00:02, 205MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 63%|██████▎ | 866M/1.35G [00:04<00:02, 210MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 64%|██████▍ | 888M/1.35G [00:04<00:02, 214MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 66%|██████▌ | 909M/1.35G [00:04<00:02, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 67%|██████▋ | 930M/1.35G [00:05<00:02, 218MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 69%|██████▉ | 951M/1.35G [00:05<00:02, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 70%|███████ | 972M/1.35G [00:05<00:01, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 72%|███████▏ | 993M/1.35G [00:05<00:01, 218MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 73%|███████▎ | 0.99G/1.35G [00:05<00:01, 216MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 75%|███████▍ | 1.01G/1.35G [00:05<00:01, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▋ | 1.03G/1.35G [00:05<00:01, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 78%|███████▊ | 1.05G/1.35G [00:05<00:01, 216MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|███████▉ | 1.07G/1.35G [00:05<00:01, 218MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 81%|████████ | 1.09G/1.35G [00:05<00:01, 218MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 83%|████████▎ | 1.11G/1.35G [00:06<00:01, 219MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 84%|████████▍ | 1.13G/1.35G [00:06<00:01, 219MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 86%|████████▌ | 1.15G/1.35G [00:06<00:00, 219MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 87%|████████▋ | 1.17G/1.35G [00:06<00:00, 220MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 89%|████████▊ | 1.19G/1.35G [00:06<00:00, 220MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|█████████ | 1.21G/1.35G [00:06<00:00, 220MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 1.24G/1.35G [00:06<00:00, 216MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 93%|█████████▎| 1.26G/1.35G [00:06<00:00, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 95%|█████████▍| 1.28G/1.35G [00:06<00:00, 216MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▋| 1.30G/1.35G [00:06<00:00, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 98%|█████████▊| 1.32G/1.35G [00:07<00:00, 218MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 99%|█████████▉| 1.34G/1.35G [00:07<00:00, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 1.35G/1.35G [00:07<00:00, 200MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
}
],
"source": [
"for key in mydict:\n",
" mydict[key] = sm.SummaryDetector(mydict[key]).analyse_questions(list_of_questions)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Convert to dataframe and write csv\n",
"These steps are required to convert the dictionary of dictionarys into a dictionary with lists, that can be converted into a pandas dataframe and exported to a csv file."
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:59:41.704626Z",
"iopub.status.busy": "2023-06-14T17:59:41.704257Z",
"iopub.status.idle": "2023-06-14T17:59:41.709177Z",
"shell.execute_reply": "2023-06-14T17:59:41.708628Z"
}
},
"outputs": [],
"source": [
"outdict2 = mutils.append_data_to_dict(mydict)\n",
"df2 = mutils.dump_df(outdict2)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:59:41.711883Z",
"iopub.status.busy": "2023-06-14T17:59:41.711543Z",
"iopub.status.idle": "2023-06-14T17:59:41.720324Z",
"shell.execute_reply": "2023-06-14T17:59:41.719831Z"
}
},
"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",
" <th>const_image_summary</th>\n",
" <th>3_non-deterministic summary</th>\n",
" <th>How many persons on the picture?</th>\n",
" <th>Are there any politicians in the picture?</th>\n",
" <th>Does the picture show something from medicine?</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>data/102730_eng.png</td>\n",
" <td>two people in blue coats spray disinfection a van</td>\n",
" <td>[two people with blue robes are spraying water...</td>\n",
" <td>2</td>\n",
" <td>no</td>\n",
" <td>yes</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>data/106349S_por.png</td>\n",
" <td>a man wearing a face mask while looking at a c...</td>\n",
" <td>[an image of a television screen that has a ma...</td>\n",
" <td>1</td>\n",
" <td>yes</td>\n",
" <td>yes</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>data/102141_2_eng.png</td>\n",
" <td>a collage of images including a corona sign, a...</td>\n",
" <td>[a hand holding an empty tube and another phot...</td>\n",
" <td>1</td>\n",
" <td>no</td>\n",
" <td>yes</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" filename const_image_summary \\\n",
"0 data/102730_eng.png two people in blue coats spray disinfection a van \n",
"1 data/106349S_por.png a man wearing a face mask while looking at a c... \n",
"2 data/102141_2_eng.png a collage of images including a corona sign, a... \n",
"\n",
" 3_non-deterministic summary \\\n",
"0 [two people with blue robes are spraying water... \n",
"1 [an image of a television screen that has a ma... \n",
"2 [a hand holding an empty tube and another phot... \n",
"\n",
" How many persons on the picture? Are there any politicians in the picture? \\\n",
"0 2 no \n",
"1 1 yes \n",
"2 1 no \n",
"\n",
" Does the picture show something from medicine? \n",
"0 yes \n",
"1 yes \n",
"2 yes "
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df2.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T17:59:41.723130Z",
"iopub.status.busy": "2023-06-14T17:59:41.722802Z",
"iopub.status.idle": "2023-06-14T17:59:41.727004Z",
"shell.execute_reply": "2023-06-14T17:59:41.726511Z"
}
},
"outputs": [],
"source": [
"df2.to_csv(\"data_out2.csv\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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