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

2068 строки
50 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": "2023-06-27T09:03:47.867208Z",
"iopub.status.busy": "2023-06-27T09:03:47.866989Z",
"iopub.status.idle": "2023-06-27T09:03:47.875293Z",
"shell.execute_reply": "2023-06-27T09:03:47.874718Z"
}
},
"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": "2023-06-27T09:03:47.878143Z",
"iopub.status.busy": "2023-06-27T09:03:47.877647Z",
"iopub.status.idle": "2023-06-27T09:03:58.213427Z",
"shell.execute_reply": "2023-06-27T09:03:58.212816Z"
},
"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": "2023-06-27T09:03:58.216430Z",
"iopub.status.busy": "2023-06-27T09:03:58.215954Z",
"iopub.status.idle": "2023-06-27T09:03:58.219780Z",
"shell.execute_reply": "2023-06-27T09:03:58.219162Z"
},
"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": "2023-06-27T09:03:58.222438Z",
"iopub.status.busy": "2023-06-27T09:03:58.222102Z",
"iopub.status.idle": "2023-06-27T09:03:58.225151Z",
"shell.execute_reply": "2023-06-27T09:03:58.224542Z"
},
"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": "2023-06-27T09:03:58.228652Z",
"iopub.status.busy": "2023-06-27T09:03:58.228311Z",
"iopub.status.idle": "2023-06-27T09:05:07.932578Z",
"shell.execute_reply": "2023-06-27T09:05:07.928904Z"
},
"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%| | 4.01M/2.50G [00:00<01:05, 41.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 15.7M/2.50G [00:00<00:30, 88.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 24.1M/2.50G [00:00<00:36, 72.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 32.0M/2.50G [00:00<00:37, 71.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 44.7M/2.50G [00:00<00:29, 91.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 55.9M/2.50G [00:00<00:26, 99.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 65.6M/2.50G [00:00<00:30, 84.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 80.0M/2.50G [00:00<00:25, 102MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▎ | 90.4M/2.50G [00:01<00:26, 99.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▍ | 109M/2.50G [00:01<00:20, 125MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▍ | 121M/2.50G [00:01<00:23, 110MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▌ | 140M/2.50G [00:01<00:19, 134MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 6%|▌ | 154M/2.50G [00:01<00:19, 132MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 7%|▋ | 171M/2.50G [00:01<00:17, 146MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 8%|▊ | 195M/2.50G [00:01<00:14, 175MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 8%|▊ | 213M/2.50G [00:01<00:14, 171MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 9%|▉ | 238M/2.50G [00:01<00:12, 200MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|█ | 263M/2.50G [00:02<00:11, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 11%|█ | 288M/2.50G [00:02<00:11, 210MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 12%|█▏ | 316M/2.50G [00:02<00:10, 233MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 13%|█▎ | 344M/2.50G [00:02<00:09, 250MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 15%|█▍ | 374M/2.50G [00:02<00:08, 268MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 16%|█▌ | 400M/2.50G [00:02<00:08, 263MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 17%|█▋ | 425M/2.50G [00:02<00:10, 215MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 17%|█▋ | 448M/2.50G [00:02<00:10, 220MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 18%|█▊ | 470M/2.50G [00:02<00:10, 208MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 19%|█▉ | 491M/2.50G [00:03<00:16, 129MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|█▉ | 507M/2.50G [00:03<00:15, 135MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 21%|██ | 530M/2.50G [00:03<00:13, 157MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 22%|██▏ | 558M/2.50G [00:03<00:11, 189MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 23%|██▎ | 579M/2.50G [00:03<00:12, 164MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 24%|██▍ | 611M/2.50G [00:03<00:10, 201MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 25%|██▍ | 639M/2.50G [00:04<00:08, 226MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 26%|██▌ | 664M/2.50G [00:04<00:11, 169MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 689M/2.50G [00:04<00:10, 189MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 28%|██▊ | 710M/2.50G [00:04<00:09, 197MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 29%|██▊ | 735M/2.50G [00:04<00:09, 211MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 30%|██▉ | 757M/2.50G [00:04<00:09, 190MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 30%|███ | 777M/2.50G [00:04<00:09, 196MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 31%|███▏ | 802M/2.50G [00:04<00:08, 212MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 32%|███▏ | 830M/2.50G [00:05<00:07, 236MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 33%|███▎ | 854M/2.50G [00:05<00:09, 191MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 34%|███▍ | 880M/2.50G [00:05<00:17, 104MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 35%|███▌ | 908M/2.50G [00:05<00:13, 132MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 36%|███▌ | 928M/2.50G [00:05<00:12, 137MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 37%|███▋ | 956M/2.50G [00:06<00:10, 167MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 38%|███▊ | 985M/2.50G [00:06<00:08, 196MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 40%|███▉ | 0.99G/2.50G [00:06<00:07, 222MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 41%|████ | 1.01G/2.50G [00:06<00:07, 209MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 42%|████▏ | 1.04G/2.50G [00:06<00:06, 228MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 43%|████▎ | 1.07G/2.50G [00:06<00:08, 192MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 44%|████▎ | 1.09G/2.50G [00:06<00:07, 207MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 44%|████▍ | 1.11G/2.50G [00:07<00:11, 128MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 45%|████▌ | 1.14G/2.50G [00:07<00:09, 158MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 47%|████▋ | 1.17G/2.50G [00:07<00:07, 188MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 48%|████▊ | 1.19G/2.50G [00:07<00:06, 210MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 49%|████▊ | 1.22G/2.50G [00:07<00:06, 213MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 50%|████▉ | 1.25G/2.50G [00:07<00:05, 236MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 51%|█████ | 1.27G/2.50G [00:07<00:05, 250MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 52%|█████▏ | 1.30G/2.50G [00:07<00:04, 265MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 53%|█████▎ | 1.33G/2.50G [00:07<00:04, 267MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 54%|█████▍ | 1.36G/2.50G [00:08<00:04, 274MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 55%|█████▌ | 1.38G/2.50G [00:08<00:05, 241MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 56%|█████▌ | 1.41G/2.50G [00:08<00:05, 223MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 57%|█████▋ | 1.43G/2.50G [00:08<00:04, 241MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 58%|█████▊ | 1.46G/2.50G [00:08<00:05, 224MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 59%|█████▉ | 1.49G/2.50G [00:08<00:04, 244MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 60%|██████ | 1.51G/2.50G [00:09<00:06, 154MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 61%|██████ | 1.53G/2.50G [00:09<00:06, 173MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 62%|██████▏ | 1.56G/2.50G [00:09<00:05, 199MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 63%|██████▎ | 1.58G/2.50G [00:09<00:04, 204MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 64%|██████▍ | 1.61G/2.50G [00:09<00:04, 229MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 66%|██████▌ | 1.64G/2.50G [00:09<00:03, 245MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 67%|██████▋ | 1.67G/2.50G [00:09<00:03, 254MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 68%|██████▊ | 1.69G/2.50G [00:09<00:03, 266MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 69%|██████▊ | 1.72G/2.50G [00:09<00:03, 267MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 70%|██████▉ | 1.75G/2.50G [00:10<00:04, 201MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 71%|███████ | 1.77G/2.50G [00:10<00:03, 219MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 72%|███████▏ | 1.80G/2.50G [00:10<00:03, 232MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 73%|███████▎ | 1.82G/2.50G [00:10<00:03, 235MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 74%|███████▍ | 1.85G/2.50G [00:10<00:02, 254MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 75%|███████▍ | 1.88G/2.50G [00:10<00:02, 268MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▌ | 1.90G/2.50G [00:11<00:06, 97.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 77%|███████▋ | 1.92G/2.50G [00:11<00:05, 111MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 78%|███████▊ | 1.95G/2.50G [00:11<00:04, 141MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 79%|███████▉ | 1.98G/2.50G [00:11<00:03, 166MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|███████▉ | 2.00G/2.50G [00:11<00:02, 190MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 81%|████████ | 2.03G/2.50G [00:12<00:04, 106MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 82%|████████▏ | 2.05G/2.50G [00:12<00:04, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 83%|████████▎ | 2.07G/2.50G [00:12<00:03, 145MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 84%|████████▎ | 2.09G/2.50G [00:12<00:02, 155MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 84%|████████▍ | 2.11G/2.50G [00:14<00:13, 31.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 85%|████████▍ | 2.13G/2.50G [00:14<00:11, 36.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 85%|████████▌ | 2.14G/2.50G [00:14<00:09, 42.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 86%|████████▌ | 2.15G/2.50G [00:15<00:08, 47.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 86%|████████▋ | 2.16G/2.50G [00:15<00:06, 55.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 87%|████████▋ | 2.17G/2.50G [00:15<00:06, 58.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 87%|████████▋ | 2.18G/2.50G [00:15<00:05, 65.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 88%|████████▊ | 2.20G/2.50G [00:15<00:04, 81.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 88%|████████▊ | 2.21G/2.50G [00:15<00:03, 96.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 89%|████████▉ | 2.22G/2.50G [00:17<00:13, 22.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 89%|████████▉ | 2.23G/2.50G [00:17<00:13, 20.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 89%|████████▉ | 2.24G/2.50G [00:18<00:12, 23.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|████████▉ | 2.24G/2.50G [00:18<00:10, 26.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|████████▉ | 2.25G/2.50G [00:18<00:08, 30.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|█████████ | 2.26G/2.50G [00:18<00:07, 36.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|█████████ | 2.27G/2.50G [00:18<00:06, 40.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 91%|█████████ | 2.27G/2.50G [00:18<00:05, 47.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 91%|█████████ | 2.28G/2.50G [00:18<00:05, 44.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 2.29G/2.50G [00:19<00:04, 56.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 2.30G/2.50G [00:19<00:04, 48.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 2.30G/2.50G [00:19<00:05, 41.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 2.31G/2.50G [00:19<00:03, 54.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 93%|█████████▎| 2.32G/2.50G [00:19<00:03, 60.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 93%|█████████▎| 2.33G/2.50G [00:19<00:02, 70.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▎| 2.34G/2.50G [00:19<00:02, 72.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▍| 2.35G/2.50G [00:20<00:02, 74.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▍| 2.36G/2.50G [00:20<00:01, 87.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 95%|█████████▌| 2.38G/2.50G [00:20<00:01, 113MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▌| 2.39G/2.50G [00:20<00:01, 85.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▌| 2.40G/2.50G [00:20<00:01, 85.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▋| 2.41G/2.50G [00:20<00:00, 98.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 97%|█████████▋| 2.43G/2.50G [00:20<00:00, 89.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 98%|█████████▊| 2.45G/2.50G [00:21<00:00, 106MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 98%|█████████▊| 2.46G/2.50G [00:21<00:00, 85.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 99%|█████████▉| 2.47G/2.50G [00:21<00:00, 103MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 99%|█████████▉| 2.48G/2.50G [00:22<00:00, 29.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|█████████▉| 2.49G/2.50G [00:22<00:00, 32.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|█████████▉| 2.50G/2.50G [00:22<00:00, 41.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 2.50G/2.50G [00:22<00:00, 118MB/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<00:38, 37.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 16.0M/1.35G [00:00<00:19, 72.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 35.7M/1.35G [00:00<00:11, 126MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▍ | 56.0M/1.35G [00:00<00:09, 153MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▌ | 75.6M/1.35G [00:00<00:07, 171MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 7%|▋ | 92.4M/1.35G [00:00<00:08, 164MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 9%|▉ | 122M/1.35G [00:00<00:06, 208MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 11%|█ | 149M/1.35G [00:00<00:05, 233MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 13%|█▎ | 182M/1.35G [00:00<00:04, 266MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 15%|█▌ | 208M/1.35G [00:01<00:04, 269MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 17%|█▋ | 238M/1.35G [00:01<00:04, 283MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|█▉ | 273M/1.35G [00:01<00:03, 308MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 22%|██▏ | 303M/1.35G [00:01<00:04, 278MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 24%|██▍ | 335M/1.35G [00:01<00:03, 293MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 367M/1.35G [00:01<00:03, 306MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 29%|██▉ | 402M/1.35G [00:01<00:03, 325MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 32%|███▏ | 437M/1.35G [00:01<00:02, 337MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 34%|███▍ | 473M/1.35G [00:01<00:02, 347MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 37%|███▋ | 507M/1.35G [00:02<00:02, 352MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 39%|███▉ | 541M/1.35G [00:02<00:04, 207MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 41%|████▏ | 570M/1.35G [00:02<00:03, 226MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 44%|████▍ | 605M/1.35G [00:02<00:03, 257MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 46%|████▌ | 635M/1.35G [00:02<00:03, 239MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 48%|████▊ | 661M/1.35G [00:02<00:03, 202MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 50%|█████ | 692M/1.35G [00:02<00:03, 228MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 53%|█████▎ | 725M/1.35G [00:03<00:02, 257MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 55%|█████▍ | 753M/1.35G [00:03<00:03, 179MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 57%|█████▋ | 786M/1.35G [00:03<00:02, 211MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 59%|█████▉ | 819M/1.35G [00:03<00:02, 240MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 61%|██████▏ | 846M/1.35G [00:03<00:02, 226MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 64%|██████▍ | 882M/1.35G [00:03<00:02, 259MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 66%|██████▌ | 910M/1.35G [00:04<00:02, 212MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 68%|██████▊ | 939M/1.35G [00:04<00:01, 234MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 70%|███████ | 967M/1.35G [00:04<00:02, 173MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 73%|███████▎ | 0.98G/1.35G [00:04<00:01, 211MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 75%|███████▌ | 1.01G/1.35G [00:04<00:01, 247MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 78%|███████▊ | 1.04G/1.35G [00:04<00:01, 215MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 79%|███████▉ | 1.07G/1.35G [00:04<00:01, 216MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 81%|████████ | 1.09G/1.35G [00:05<00:01, 223MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 83%|████████▎ | 1.12G/1.35G [00:05<00:01, 170MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 86%|████████▌ | 1.15G/1.35G [00:05<00:01, 207MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 88%|████████▊ | 1.19G/1.35G [00:05<00:00, 242MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 91%|█████████ | 1.22G/1.35G [00:05<00:00, 270MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 93%|█████████▎| 1.25G/1.35G [00:05<00:00, 293MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▌| 1.29G/1.35G [00:05<00:00, 314MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 98%|█████████▊| 1.32G/1.35G [00:05<00:00, 267MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 1.35G/1.35G [00:06<00:00, 221MB/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": "2023-06-27T09:05:07.941454Z",
"iopub.status.busy": "2023-06-27T09:05:07.940339Z",
"iopub.status.idle": "2023-06-27T09:05:49.783091Z",
"shell.execute_reply": "2023-06-27T09:05:49.781170Z"
},
"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": "2023-06-27T09:05:49.846542Z",
"iopub.status.busy": "2023-06-27T09:05:49.845037Z",
"iopub.status.idle": "2023-06-27T09:05:49.929066Z",
"shell.execute_reply": "2023-06-27T09:05:49.928420Z"
},
"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": "2023-06-27T09:05:49.935760Z",
"iopub.status.busy": "2023-06-27T09:05:49.935520Z",
"iopub.status.idle": "2023-06-27T09:05:50.071123Z",
"shell.execute_reply": "2023-06-27T09:05:50.070326Z"
},
"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/106349S_por.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/102730_eng.png</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" filename\n",
"0 data/106349S_por.png\n",
"1 data/102141_2_eng.png\n",
"2 data/102730_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": "2023-06-27T09:05:50.085192Z",
"iopub.status.busy": "2023-06-27T09:05:50.084726Z",
"iopub.status.idle": "2023-06-27T09:05:50.131221Z",
"shell.execute_reply": "2023-06-27T09:05:50.130584Z"
}
},
"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": "2023-06-27T09:05:50.136495Z",
"iopub.status.busy": "2023-06-27T09:05:50.136136Z",
"iopub.status.idle": "2023-06-27T09:05:50.168474Z",
"shell.execute_reply": "2023-06-27T09:05:50.167780Z"
},
"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": "2023-06-27T09:05:50.175012Z",
"iopub.status.busy": "2023-06-27T09:05:50.174534Z",
"iopub.status.idle": "2023-06-27T09:05:50.178293Z",
"shell.execute_reply": "2023-06-27T09:05:50.177589Z"
}
},
"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": "2023-06-27T09:05:50.183463Z",
"iopub.status.busy": "2023-06-27T09:05:50.182925Z",
"iopub.status.idle": "2023-06-27T09:05:50.212836Z",
"shell.execute_reply": "2023-06-27T09:05:50.212044Z"
}
},
"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": "2023-06-27T09:05:50.217587Z",
"iopub.status.busy": "2023-06-27T09:05:50.217229Z",
"iopub.status.idle": "2023-06-27T09:07:33.102446Z",
"shell.execute_reply": "2023-06-27T09:07:33.100338Z"
}
},
"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": "2023-06-27T09:07:33.184466Z",
"iopub.status.busy": "2023-06-27T09:07:33.183900Z",
"iopub.status.idle": "2023-06-27T09:07:33.194912Z",
"shell.execute_reply": "2023-06-27T09:07:33.194204Z"
}
},
"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": "2023-06-27T09:07:33.199785Z",
"iopub.status.busy": "2023-06-27T09:07:33.199557Z",
"iopub.status.idle": "2023-06-27T09:07:33.216692Z",
"shell.execute_reply": "2023-06-27T09:07:33.216036Z"
}
},
"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/106349S_por.png</td>\n",
" <td>1</td>\n",
" <td>yes</td>\n",
" <td>yes</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>data/102141_2_eng.png</td>\n",
" <td>1</td>\n",
" <td>no</td>\n",
" <td>yes</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>data/102730_eng.png</td>\n",
" <td>2</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/106349S_por.png 1 \n",
"1 data/102141_2_eng.png 1 \n",
"2 data/102730_eng.png 2 \n",
"\n",
" Are there any politicians in the picture? \\\n",
"0 yes \n",
"1 no \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": "2023-06-27T09:07:33.222046Z",
"iopub.status.busy": "2023-06-27T09:07:33.221438Z",
"iopub.status.idle": "2023-06-27T09:07:33.228304Z",
"shell.execute_reply": "2023-06-27T09:07:33.226867Z"
}
},
"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