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/html/notebooks/Example summary.ipynb

2036 строки
49 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": "2023-07-12T07:43:54.592760Z",
"iopub.status.busy": "2023-07-12T07:43:54.592229Z",
"iopub.status.idle": "2023-07-12T07:43:54.601347Z",
"shell.execute_reply": "2023-07-12T07:43:54.600720Z"
}
},
"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": "2023-07-12T07:43:54.604589Z",
"iopub.status.busy": "2023-07-12T07:43:54.604149Z",
"iopub.status.idle": "2023-07-12T07:44:06.155007Z",
"shell.execute_reply": "2023-07-12T07:44:06.154269Z"
},
"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": "2023-07-12T07:44:06.159395Z",
"iopub.status.busy": "2023-07-12T07:44:06.158548Z",
"iopub.status.idle": "2023-07-12T07:44:06.163957Z",
"shell.execute_reply": "2023-07-12T07:44:06.163315Z"
},
"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": "2023-07-12T07:44:06.167102Z",
"iopub.status.busy": "2023-07-12T07:44:06.166641Z",
"iopub.status.idle": "2023-07-12T07:44:06.170038Z",
"shell.execute_reply": "2023-07-12T07:44:06.169327Z"
},
"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": "2023-07-12T07:44:06.174147Z",
"iopub.status.busy": "2023-07-12T07:44:06.173692Z",
"iopub.status.idle": "2023-07-12T07:45:10.075604Z",
"shell.execute_reply": "2023-07-12T07:45:10.071896Z"
},
"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%| | 6.67M/2.50G [00:00<00:38, 69.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 13.3M/2.50G [00:00<00:41, 65.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 24.0M/2.50G [00:00<00:32, 82.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 40.0M/2.50G [00:00<00:30, 87.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 56.0M/2.50G [00:00<00:25, 103MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 72.0M/2.50G [00:00<00:23, 112MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▎ | 91.1M/2.50G [00:00<00:19, 136MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▍ | 105M/2.50G [00:01<00:23, 109MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▍ | 128M/2.50G [00:01<00:18, 140MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 6%|▌ | 149M/2.50G [00:01<00:15, 161MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 7%|▋ | 174M/2.50G [00:01<00:13, 187MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 8%|▊ | 198M/2.50G [00:01<00:12, 204MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 9%|▊ | 223M/2.50G [00:01<00:11, 222MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|▉ | 248M/2.50G [00:01<00:10, 233MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 11%|█ | 271M/2.50G [00:01<00:10, 219MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 11%|█▏ | 293M/2.50G [00:01<00:10, 223MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 12%|█▏ | 318M/2.50G [00:01<00:10, 234MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 13%|█▎ | 343M/2.50G [00:02<00:09, 241MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 14%|█▍ | 366M/2.50G [00:02<00:10, 227MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 15%|█▌ | 391M/2.50G [00:02<00:09, 238MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 16%|█▋ | 417M/2.50G [00:02<00:09, 248MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 17%|█▋ | 441M/2.50G [00:02<00:09, 233MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 18%|█▊ | 464M/2.50G [00:02<00:09, 235MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 19%|█▉ | 490M/2.50G [00:02<00:08, 244MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|██ | 516M/2.50G [00:02<00:08, 252MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 21%|██ | 540M/2.50G [00:03<00:12, 174MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 22%|██▏ | 560M/2.50G [00:03<00:12, 170MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 23%|██▎ | 578M/2.50G [00:04<00:33, 63.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 24%|██▎ | 604M/2.50G [00:04<00:24, 84.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 24%|██▍ | 624M/2.50G [00:04<00:20, 97.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 25%|██▌ | 650M/2.50G [00:04<00:16, 124MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 26%|██▋ | 675M/2.50G [00:04<00:13, 146MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 697M/2.50G [00:04<00:12, 163MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 28%|██▊ | 723M/2.50G [00:04<00:10, 186MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 29%|██▉ | 748M/2.50G [00:04<00:09, 207MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 30%|███ | 774M/2.50G [00:04<00:08, 221MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 31%|███ | 797M/2.50G [00:05<00:09, 203MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 32%|███▏ | 819M/2.50G [00:05<00:10, 179MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 33%|███▎ | 843M/2.50G [00:05<00:09, 196MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 34%|███▍ | 868M/2.50G [00:05<00:08, 213MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 35%|███▍ | 893M/2.50G [00:05<00:07, 227MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 36%|███▌ | 918M/2.50G [00:05<00:07, 236MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 37%|███▋ | 944M/2.50G [00:05<00:06, 247MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 38%|███▊ | 968M/2.50G [00:05<00:07, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 39%|███▉ | 994M/2.50G [00:05<00:07, 230MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 40%|███▉ | 1.00G/2.50G [00:06<00:06, 241MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 41%|████ | 1.02G/2.50G [00:06<00:06, 246MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 42%|████▏ | 1.04G/2.50G [00:06<00:06, 252MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 43%|████▎ | 1.07G/2.50G [00:06<00:05, 258MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 44%|████▎ | 1.09G/2.50G [00:06<00:05, 260MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 45%|████▍ | 1.12G/2.50G [00:06<00:05, 260MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 46%|████▌ | 1.14G/2.50G [00:06<00:05, 258MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 47%|████▋ | 1.17G/2.50G [00:06<00:05, 259MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 48%|████▊ | 1.19G/2.50G [00:06<00:05, 258MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 49%|████▊ | 1.22G/2.50G [00:07<00:05, 257MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 50%|████▉ | 1.24G/2.50G [00:07<00:06, 224MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 50%|█████ | 1.26G/2.50G [00:07<00:06, 208MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 51%|█████ | 1.28G/2.50G [00:07<00:06, 206MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 52%|█████▏ | 1.31G/2.50G [00:07<00:05, 224MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 53%|█████▎ | 1.33G/2.50G [00:07<00:05, 240MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 54%|█████▍ | 1.36G/2.50G [00:07<00:05, 235MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 55%|█████▌ | 1.38G/2.50G [00:07<00:04, 246MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 56%|█████▌ | 1.41G/2.50G [00:07<00:05, 210MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 57%|█████▋ | 1.43G/2.50G [00:08<00:05, 216MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 58%|█████▊ | 1.45G/2.50G [00:08<00:04, 227MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 59%|█████▉ | 1.47G/2.50G [00:08<00:05, 194MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 60%|█████▉ | 1.50G/2.50G [00:08<00:05, 214MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 61%|██████ | 1.52G/2.50G [00:08<00:05, 198MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 62%|██████▏ | 1.55G/2.50G [00:08<00:04, 216MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 63%|██████▎ | 1.57G/2.50G [00:08<00:06, 148MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 64%|██████▎ | 1.59G/2.50G [00:09<00:05, 172MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 64%|██████▍ | 1.61G/2.50G [00:09<00:05, 190MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 65%|██████▌ | 1.64G/2.50G [00:09<00:04, 209MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 67%|██████▋ | 1.66G/2.50G [00:09<00:04, 225MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 67%|██████▋ | 1.69G/2.50G [00:09<00:03, 234MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 68%|██████▊ | 1.71G/2.50G [00:09<00:03, 236MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 69%|██████▉ | 1.74G/2.50G [00:09<00:03, 244MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 70%|███████ | 1.76G/2.50G [00:10<00:06, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 71%|███████▏ | 1.79G/2.50G [00:10<00:05, 142MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 72%|███████▏ | 1.81G/2.50G [00:10<00:05, 140MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 73%|███████▎ | 1.82G/2.50G [00:10<00:04, 150MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 74%|███████▍ | 1.85G/2.50G [00:10<00:04, 173MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 75%|███████▍ | 1.87G/2.50G [00:10<00:03, 188MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 75%|███████▌ | 1.89G/2.50G [00:10<00:03, 180MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▋ | 1.91G/2.50G [00:10<00:03, 197MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 77%|███████▋ | 1.94G/2.50G [00:11<00:02, 213MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 78%|███████▊ | 1.96G/2.50G [00:11<00:02, 209MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 79%|███████▉ | 1.98G/2.50G [00:11<00:02, 219MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|████████ | 2.00G/2.50G [00:11<00:02, 233MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 81%|████████ | 2.03G/2.50G [00:11<00:02, 239MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 82%|████████▏ | 2.05G/2.50G [00:11<00:01, 248MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 83%|████████▎ | 2.08G/2.50G [00:11<00:01, 254MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 84%|████████▍ | 2.10G/2.50G [00:11<00:01, 256MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 85%|████████▍ | 2.13G/2.50G [00:11<00:01, 250MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 86%|████████▌ | 2.15G/2.50G [00:11<00:01, 253MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 87%|████████▋ | 2.17G/2.50G [00:12<00:01, 253MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 88%|████████▊ | 2.20G/2.50G [00:12<00:01, 252MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 89%|████████▉ | 2.22G/2.50G [00:12<00:01, 253MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|████████▉ | 2.25G/2.50G [00:13<00:06, 44.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|█████████ | 2.26G/2.50G [00:14<00:04, 53.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 91%|█████████ | 2.28G/2.50G [00:14<00:03, 62.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 2.30G/2.50G [00:14<00:02, 75.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 93%|█████████▎| 2.32G/2.50G [00:14<00:02, 95.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 93%|█████████▎| 2.34G/2.50G [00:14<00:01, 115MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▍| 2.36G/2.50G [00:14<00:01, 138MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 95%|█████████▌| 2.38G/2.50G [00:14<00:00, 161MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▌| 2.41G/2.50G [00:14<00:00, 182MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 97%|█████████▋| 2.43G/2.50G [00:14<00:00, 204MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 98%|█████████▊| 2.46G/2.50G [00:15<00:00, 220MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 99%|█████████▉| 2.48G/2.50G [00:15<00:00, 234MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 2.50G/2.50G [00:15<00:00, 177MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 0%| | 0.00/1.35G [00:00<?, ?B/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 0%| | 4.01M/1.35G [00:00<00:42, 33.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 8.01M/1.35G [00:00<01:13, 19.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 16.0M/1.35G [00:00<00:57, 24.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 24.0M/1.35G [00:00<00:45, 31.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 33.7M/1.35G [00:00<00:31, 45.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 46.6M/1.35G [00:01<00:21, 65.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▍ | 56.0M/1.35G [00:01<00:20, 69.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▌ | 72.0M/1.35G [00:01<00:15, 89.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 7%|▋ | 96.0M/1.35G [00:01<00:10, 124MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 9%|▊ | 119M/1.35G [00:01<00:08, 153MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|█ | 140M/1.35G [00:01<00:07, 172MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 12%|█▏ | 163M/1.35G [00:01<00:06, 190MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 13%|█▎ | 184M/1.35G [00:01<00:06, 197MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 15%|█▌ | 208M/1.35G [00:01<00:05, 211MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 17%|█▋ | 228M/1.35G [00:02<00:06, 188MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 18%|█▊ | 248M/1.35G [00:02<00:08, 145MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|█▉ | 273M/1.35G [00:02<00:06, 170MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 21%|██▏ | 295M/1.35G [00:02<00:06, 187MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 23%|██▎ | 321M/1.35G [00:02<00:05, 207MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 25%|██▌ | 347M/1.35G [00:02<00:04, 224MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 371M/1.35G [00:02<00:04, 234MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 29%|██▊ | 395M/1.35G [00:02<00:04, 212MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 30%|███ | 420M/1.35G [00:03<00:04, 225MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 32%|███▏ | 442M/1.35G [00:03<00:04, 229MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 34%|███▎ | 465M/1.35G [00:03<00:04, 222MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 36%|███▌ | 491M/1.35G [00:03<00:03, 237MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 38%|███▊ | 518M/1.35G [00:03<00:03, 250MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 39%|███▉ | 542M/1.35G [00:03<00:03, 238MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 41%|████▏ | 570M/1.35G [00:03<00:03, 252MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 43%|████▎ | 597M/1.35G [00:03<00:03, 261MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 45%|████▌ | 622M/1.35G [00:03<00:03, 251MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 47%|████▋ | 646M/1.35G [00:04<00:03, 219MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 49%|████▊ | 672M/1.35G [00:04<00:03, 231MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 51%|█████ | 698M/1.35G [00:04<00:02, 243MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 52%|█████▏ | 722M/1.35G [00:04<00:02, 241MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 54%|█████▍ | 748M/1.35G [00:04<00:02, 250MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 56%|█████▌ | 772M/1.35G [00:04<00:03, 186MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 58%|█████▊ | 798M/1.35G [00:04<00:02, 206MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 59%|█████▉ | 820M/1.35G [00:04<00:03, 171MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 61%|██████▏ | 847M/1.35G [00:05<00:02, 195MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 63%|██████▎ | 873M/1.35G [00:05<00:02, 216MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 65%|██████▍ | 896M/1.35G [00:05<00:02, 203MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 67%|██████▋ | 921M/1.35G [00:05<00:02, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 69%|██████▊ | 946M/1.35G [00:05<00:01, 230MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 70%|███████ | 969M/1.35G [00:05<00:02, 212MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 72%|███████▏ | 996M/1.35G [00:05<00:01, 229MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 74%|███████▍ | 1.00G/1.35G [00:05<00:01, 244MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▌ | 1.03G/1.35G [00:05<00:01, 255MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 78%|███████▊ | 1.05G/1.35G [00:06<00:01, 261MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|███████▉ | 1.08G/1.35G [00:06<00:01, 266MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 82%|████████▏ | 1.10G/1.35G [00:06<00:01, 230MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 84%|████████▎ | 1.13G/1.35G [00:06<00:01, 133MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 85%|████████▌ | 1.15G/1.35G [00:06<00:01, 158MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 87%|████████▋ | 1.17G/1.35G [00:06<00:01, 152MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 89%|████████▉ | 1.20G/1.35G [00:07<00:00, 177MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|█████████ | 1.22G/1.35G [00:07<00:00, 194MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 1.24G/1.35G [00:07<00:00, 206MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▍| 1.26G/1.35G [00:07<00:00, 216MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▌| 1.29G/1.35G [00:07<00:00, 230MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 97%|█████████▋| 1.31G/1.35G [00:07<00:00, 214MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 99%|█████████▉| 1.33G/1.35G [00:07<00:00, 190MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 1.35G/1.35G [00:07<00:00, 185MB/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": "2023-07-12T07:45:10.158342Z",
"iopub.status.busy": "2023-07-12T07:45:10.156679Z",
"iopub.status.idle": "2023-07-12T07:45:53.671505Z",
"shell.execute_reply": "2023-07-12T07:45:53.670229Z"
},
"tags": []
},
"outputs": [
{
"ename": "TypeError",
"evalue": "analyse_image() got an unexpected keyword argument 'summary_model'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[6], 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_image\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 3\u001b[0m \u001b[43m \u001b[49m\u001b[43msummary_model\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msummary_model\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msummary_vis_processors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msummary_vis_processors\u001b[49m\n\u001b[1;32m 4\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
"\u001b[0;31mTypeError\u001b[0m: analyse_image() got an unexpected keyword argument 'summary_model'"
]
}
],
"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": "2023-07-12T07:45:53.748096Z",
"iopub.status.busy": "2023-07-12T07:45:53.747534Z",
"iopub.status.idle": "2023-07-12T07:45:53.837111Z",
"shell.execute_reply": "2023-07-12T07:45:53.836353Z"
},
"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": "2023-07-12T07:45:53.845508Z",
"iopub.status.busy": "2023-07-12T07:45:53.844879Z",
"iopub.status.idle": "2023-07-12T07:45:54.001215Z",
"shell.execute_reply": "2023-07-12T07:45:54.000313Z"
},
"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/106349S_por.png</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>data/102141_2_eng.png</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" filename\n",
"0 data/102730_eng.png\n",
"1 data/106349S_por.png\n",
"2 data/102141_2_eng.png"
]
},
"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": "2023-07-12T07:45:54.020794Z",
"iopub.status.busy": "2023-07-12T07:45:54.020165Z",
"iopub.status.idle": "2023-07-12T07:45:54.081412Z",
"shell.execute_reply": "2023-07-12T07:45:54.080589Z"
}
},
"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": "2023-07-12T07:45:54.088889Z",
"iopub.status.busy": "2023-07-12T07:45:54.088346Z",
"iopub.status.idle": "2023-07-12T07:45:54.131832Z",
"shell.execute_reply": "2023-07-12T07:45:54.130962Z"
},
"tags": []
},
"outputs": [
{
"ename": "TypeError",
"evalue": "__init__() got an unexpected keyword argument 'identify'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[10], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m analysis_explorer \u001b[38;5;241m=\u001b[39m \u001b[43mmdisplay\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mAnalysisExplorer\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmydict\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43midentify\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msummary\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2\u001b[0m analysis_explorer\u001b[38;5;241m.\u001b[39mrun_server(port\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m8055\u001b[39m)\n",
"\u001b[0;31mTypeError\u001b[0m: __init__() got an unexpected keyword argument 'identify'"
]
}
],
"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": "2023-07-12T07:45:54.140173Z",
"iopub.status.busy": "2023-07-12T07:45:54.139532Z",
"iopub.status.idle": "2023-07-12T07:45:54.143493Z",
"shell.execute_reply": "2023-07-12T07:45:54.142502Z"
}
},
"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": "2023-07-12T07:45:54.173991Z",
"iopub.status.busy": "2023-07-12T07:45:54.173337Z",
"iopub.status.idle": "2023-07-12T07:45:54.214362Z",
"shell.execute_reply": "2023-07-12T07:45:54.213572Z"
}
},
"outputs": [
{
"ename": "TypeError",
"evalue": "__init__() got an unexpected keyword argument 'identify'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[12], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m analysis_explorer \u001b[38;5;241m=\u001b[39m \u001b[43mmdisplay\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mAnalysisExplorer\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmydict\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43midentify\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msummary\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2\u001b[0m analysis_explorer\u001b[38;5;241m.\u001b[39mrun_server(port\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m8055\u001b[39m)\n",
"\u001b[0;31mTypeError\u001b[0m: __init__() got an unexpected keyword argument 'identify'"
]
}
],
"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": "2023-07-12T07:45:54.221600Z",
"iopub.status.busy": "2023-07-12T07:45:54.221111Z",
"iopub.status.idle": "2023-07-12T07:47:37.875116Z",
"shell.execute_reply": "2023-07-12T07:47:37.873132Z"
}
},
"outputs": [],
"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": "2023-07-12T07:47:37.883851Z",
"iopub.status.busy": "2023-07-12T07:47:37.883374Z",
"iopub.status.idle": "2023-07-12T07:47:37.896536Z",
"shell.execute_reply": "2023-07-12T07:47:37.895892Z"
}
},
"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": "2023-07-12T07:47:37.902301Z",
"iopub.status.busy": "2023-07-12T07:47:37.901773Z",
"iopub.status.idle": "2023-07-12T07:47:37.933118Z",
"shell.execute_reply": "2023-07-12T07:47:37.932145Z"
}
},
"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>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>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>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>1</td>\n",
" <td>no</td>\n",
" <td>yes</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" filename How many persons on the picture? \\\n",
"0 data/102730_eng.png 2 \n",
"1 data/106349S_por.png 1 \n",
"2 data/102141_2_eng.png 1 \n",
"\n",
" Are there any politicians in the picture? \\\n",
"0 no \n",
"1 yes \n",
"2 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": "2023-07-12T07:47:37.941355Z",
"iopub.status.busy": "2023-07-12T07:47:37.940780Z",
"iopub.status.idle": "2023-07-12T07:47:37.946924Z",
"shell.execute_reply": "2023-07-12T07:47:37.946177Z"
}
},
"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": "3.9.17"
},
"vscode": {
"interpreter": {
"hash": "f1142466f556ab37fe2d38e2897a16796906208adb09fea90ba58bdf8a56f0ba"
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Ссылка в новой задаче Показать git blame Копировать постоянную ссылку