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

2092 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": "2023-07-03T12:15:15.869373Z",
"iopub.status.busy": "2023-07-03T12:15:15.868830Z",
"iopub.status.idle": "2023-07-03T12:15:15.880408Z",
"shell.execute_reply": "2023-07-03T12:15:15.879864Z"
}
},
"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": "2023-07-03T12:15:15.884713Z",
"iopub.status.busy": "2023-07-03T12:15:15.883580Z",
"iopub.status.idle": "2023-07-03T12:15:27.576198Z",
"shell.execute_reply": "2023-07-03T12:15:27.575450Z"
},
"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": "2023-07-03T12:15:27.580324Z",
"iopub.status.busy": "2023-07-03T12:15:27.579544Z",
"iopub.status.idle": "2023-07-03T12:15:27.584950Z",
"shell.execute_reply": "2023-07-03T12:15:27.584254Z"
},
"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": "2023-07-03T12:15:27.588006Z",
"iopub.status.busy": "2023-07-03T12:15:27.587579Z",
"iopub.status.idle": "2023-07-03T12:15:27.591065Z",
"shell.execute_reply": "2023-07-03T12:15:27.590372Z"
},
"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": "2023-07-03T12:15:27.594466Z",
"iopub.status.busy": "2023-07-03T12:15:27.593922Z",
"iopub.status.idle": "2023-07-03T12:16:40.172662Z",
"shell.execute_reply": "2023-07-03T12:16:40.168499Z"
},
"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%| | 8.01M/2.50G [00:00<00:42, 62.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 24.0M/2.50G [00:00<00:25, 103MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 40.0M/2.50G [00:00<00:22, 120MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 56.0M/2.50G [00:00<00:19, 134MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 72.0M/2.50G [00:00<00:18, 138MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 88.0M/2.50G [00:00<00:18, 143MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▍ | 106M/2.50G [00:00<00:16, 158MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▍ | 125M/2.50G [00:00<00:15, 170MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 6%|▌ | 147M/2.50G [00:01<00:13, 188MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 7%|▋ | 175M/2.50G [00:01<00:11, 219MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 8%|▊ | 196M/2.50G [00:01<00:11, 215MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 9%|▉ | 227M/2.50G [00:01<00:09, 245MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|▉ | 252M/2.50G [00:01<00:09, 253MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 11%|█ | 279M/2.50G [00:01<00:10, 235MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 12%|█▏ | 307M/2.50G [00:01<00:09, 251MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 13%|█▎ | 332M/2.50G [00:01<00:11, 206MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 14%|█▍ | 361M/2.50G [00:01<00:10, 230MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 15%|█▌ | 388M/2.50G [00:02<00:09, 246MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 16%|█▋ | 418M/2.50G [00:02<00:08, 264MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 17%|█▋ | 448M/2.50G [00:02<00:08, 276MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 19%|█▊ | 475M/2.50G [00:02<00:08, 266MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|█▉ | 501M/2.50G [00:02<00:12, 173MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 21%|██ | 528M/2.50G [00:02<00:10, 196MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 21%|██▏ | 551M/2.50G [00:03<00:16, 125MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 22%|██▏ | 576M/2.50G [00:03<00:14, 148MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 23%|██▎ | 600M/2.50G [00:03<00:12, 168MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 24%|██▍ | 621M/2.50G [00:03<00:13, 153MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 25%|██▍ | 639M/2.50G [00:04<00:28, 71.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 25%|██▌ | 653M/2.50G [00:04<00:31, 63.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 26%|██▌ | 664M/2.50G [00:04<00:29, 67.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 679M/2.50G [00:04<00:24, 81.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 691M/2.50G [00:04<00:26, 74.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 28%|██▊ | 712M/2.50G [00:05<00:19, 98.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 28%|██▊ | 725M/2.50G [00:05<00:18, 106MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 29%|██▉ | 738M/2.50G [00:05<00:17, 109MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 30%|██▉ | 765M/2.50G [00:05<00:12, 149MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 31%|███ | 790M/2.50G [00:05<00:10, 176MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 32%|███▏ | 819M/2.50G [00:05<00:08, 210MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 33%|███▎ | 848M/2.50G [00:05<00:07, 235MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 34%|███▍ | 877M/2.50G [00:05<00:07, 253MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 35%|███▌ | 905M/2.50G [00:05<00:06, 266MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 36%|███▋ | 933M/2.50G [00:05<00:06, 272MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 37%|███▋ | 960M/2.50G [00:06<00:06, 278MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 39%|███▊ | 989M/2.50G [00:06<00:05, 286MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 40%|███▉ | 0.99G/2.50G [00:06<00:05, 290MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 41%|████ | 1.02G/2.50G [00:06<00:06, 243MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 42%|████▏ | 1.05G/2.50G [00:06<00:06, 253MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 43%|████▎ | 1.08G/2.50G [00:06<00:05, 266MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 44%|████▍ | 1.10G/2.50G [00:06<00:07, 215MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 45%|████▌ | 1.13G/2.50G [00:06<00:06, 235MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 46%|████▋ | 1.16G/2.50G [00:07<00:05, 253MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 47%|████▋ | 1.18G/2.50G [00:07<00:06, 234MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 48%|████▊ | 1.21G/2.50G [00:07<00:05, 248MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 49%|████▉ | 1.24G/2.50G [00:07<00:05, 260MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 50%|█████ | 1.26G/2.50G [00:07<00:11, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 51%|█████▏ | 1.29G/2.50G [00:08<00:09, 141MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 52%|█████▏ | 1.31G/2.50G [00:08<00:07, 162MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 53%|█████▎ | 1.34G/2.50G [00:08<00:08, 141MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 54%|█████▍ | 1.36G/2.50G [00:08<00:07, 154MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 55%|█████▌ | 1.38G/2.50G [00:09<00:14, 82.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 56%|█████▌ | 1.39G/2.50G [00:09<00:13, 87.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 56%|█████▌ | 1.41G/2.50G [00:09<00:12, 94.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 57%|█████▋ | 1.42G/2.50G [00:09<00:12, 96.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 57%|█████▋ | 1.43G/2.50G [00:09<00:19, 57.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 58%|█████▊ | 1.45G/2.50G [00:10<00:16, 70.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 58%|█████▊ | 1.46G/2.50G [00:10<00:12, 91.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 59%|█████▉ | 1.49G/2.50G [00:10<00:09, 116MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 60%|█████▉ | 1.50G/2.50G [00:10<00:08, 128MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 61%|██████ | 1.53G/2.50G [00:10<00:06, 163MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 62%|██████▏ | 1.55G/2.50G [00:10<00:05, 194MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 63%|██████▎ | 1.58G/2.50G [00:10<00:05, 189MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 64%|██████▍ | 1.60G/2.50G [00:10<00:04, 211MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 65%|██████▍ | 1.63G/2.50G [00:10<00:04, 211MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 66%|██████▌ | 1.65G/2.50G [00:11<00:03, 237MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 67%|██████▋ | 1.68G/2.50G [00:11<00:04, 180MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 68%|██████▊ | 1.70G/2.50G [00:11<00:04, 187MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 69%|██████▊ | 1.72G/2.50G [00:11<00:04, 205MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 70%|██████▉ | 1.75G/2.50G [00:11<00:03, 223MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 71%|███████ | 1.78G/2.50G [00:11<00:03, 247MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 72%|███████▏ | 1.80G/2.50G [00:11<00:02, 259MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 73%|███████▎ | 1.83G/2.50G [00:12<00:08, 83.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 74%|███████▍ | 1.86G/2.50G [00:12<00:06, 108MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 75%|███████▍ | 1.88G/2.50G [00:12<00:05, 123MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▌ | 1.90G/2.50G [00:15<00:23, 27.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▋ | 1.91G/2.50G [00:15<00:19, 32.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 77%|███████▋ | 1.93G/2.50G [00:15<00:16, 37.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 78%|███████▊ | 1.94G/2.50G [00:15<00:12, 47.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 78%|███████▊ | 1.96G/2.50G [00:18<00:32, 18.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 78%|███████▊ | 1.96G/2.50G [00:18<00:27, 21.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 79%|███████▉ | 1.97G/2.50G [00:18<00:23, 24.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 79%|███████▉ | 1.98G/2.50G [00:18<00:19, 29.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|███████▉ | 2.00G/2.50G [00:18<00:13, 41.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|████████ | 2.01G/2.50G [00:18<00:11, 46.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 81%|████████ | 2.02G/2.50G [00:18<00:09, 55.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 81%|████████ | 2.03G/2.50G [00:18<00:07, 68.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 82%|████████▏ | 2.05G/2.50G [00:19<00:05, 92.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 82%|████████▏ | 2.06G/2.50G [00:19<00:04, 108MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 83%|████████▎ | 2.08G/2.50G [00:19<00:03, 132MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 84%|████████▍ | 2.10G/2.50G [00:19<00:02, 153MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 85%|████████▍ | 2.12G/2.50G [00:19<00:02, 157MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 86%|████████▌ | 2.15G/2.50G [00:19<00:02, 191MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 86%|████████▋ | 2.17G/2.50G [00:19<00:01, 187MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 87%|████████▋ | 2.19G/2.50G [00:19<00:01, 199MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 88%|████████▊ | 2.21G/2.50G [00:19<00:01, 198MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 89%|████████▉ | 2.23G/2.50G [00:19<00:01, 206MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|█████████ | 2.25G/2.50G [00:20<00:01, 231MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 91%|█████████ | 2.28G/2.50G [00:20<00:01, 207MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 2.30G/2.50G [00:20<00:01, 193MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 2.31G/2.50G [00:22<00:06, 30.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 93%|█████████▎| 2.33G/2.50G [00:22<00:05, 33.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 93%|█████████▎| 2.34G/2.50G [00:22<00:04, 38.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▍| 2.35G/2.50G [00:22<00:03, 47.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▍| 2.36G/2.50G [00:23<00:02, 54.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 95%|█████████▍| 2.38G/2.50G [00:23<00:02, 64.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 95%|█████████▌| 2.39G/2.50G [00:23<00:01, 79.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▌| 2.41G/2.50G [00:23<00:01, 96.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 97%|█████████▋| 2.43G/2.50G [00:23<00:00, 119MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 98%|█████████▊| 2.45G/2.50G [00:23<00:00, 160MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 99%|█████████▉| 2.47G/2.50G [00:23<00:00, 165MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 99%|█████████▉| 2.49G/2.50G [00:23<00:00, 164MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 2.50G/2.50G [00:23<00:00, 113MB/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",
" 1%| | 8.01M/1.35G [00:00<00:25, 56.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 16.0M/1.35G [00:00<00:21, 68.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 32.0M/1.35G [00:00<00:13, 103MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▎ | 49.2M/1.35G [00:00<00:10, 131MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▍ | 64.0M/1.35G [00:00<00:10, 138MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 6%|▌ | 77.7M/1.35G [00:00<00:09, 140MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 7%|▋ | 96.7M/1.35G [00:00<00:08, 159MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 8%|▊ | 116M/1.35G [00:00<00:07, 174MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|█ | 142M/1.35G [00:00<00:06, 204MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 12%|█▏ | 168M/1.35G [00:01<00:05, 225MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 14%|█▍ | 193M/1.35G [00:01<00:05, 236MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 16%|█▌ | 218M/1.35G [00:01<00:04, 244MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 18%|█▊ | 248M/1.35G [00:01<00:04, 263MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|█▉ | 273M/1.35G [00:01<00:04, 265MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 22%|██▏ | 299M/1.35G [00:01<00:04, 256MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 23%|██▎ | 323M/1.35G [00:01<00:04, 255MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 25%|██▌ | 348M/1.35G [00:01<00:04, 256MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 373M/1.35G [00:01<00:04, 259MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 29%|██▉ | 398M/1.35G [00:01<00:03, 260MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 31%|███ | 424M/1.35G [00:02<00:03, 262MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 33%|███▎ | 449M/1.35G [00:02<00:03, 254MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 34%|███▍ | 473M/1.35G [00:02<00:03, 255MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 36%|███▌ | 498M/1.35G [00:02<00:03, 255MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 38%|███▊ | 522M/1.35G [00:02<00:03, 255MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 40%|███▉ | 547M/1.35G [00:02<00:03, 255MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 41%|████▏ | 571M/1.35G [00:02<00:03, 247MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 43%|████▎ | 595M/1.35G [00:02<00:03, 247MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 45%|████▍ | 620M/1.35G [00:02<00:03, 252MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 47%|████▋ | 644M/1.35G [00:03<00:03, 250MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 49%|████▉ | 673M/1.35G [00:03<00:02, 266MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 51%|█████ | 699M/1.35G [00:03<00:02, 267MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 53%|█████▎ | 724M/1.35G [00:03<00:02, 258MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 54%|█████▍ | 750M/1.35G [00:03<00:02, 261MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 56%|█████▌ | 775M/1.35G [00:03<00:02, 261MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 58%|█████▊ | 800M/1.35G [00:03<00:02, 258MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 60%|█████▉ | 824M/1.35G [00:03<00:02, 257MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 62%|██████▏ | 849M/1.35G [00:03<00:02, 254MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 63%|██████▎ | 873M/1.35G [00:03<00:02, 255MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 65%|██████▌ | 898M/1.35G [00:04<00:01, 257MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 67%|██████▋ | 923M/1.35G [00:04<00:01, 259MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 69%|██████▉ | 948M/1.35G [00:04<00:01, 260MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 71%|███████ | 973M/1.35G [00:04<00:01, 259MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 72%|███████▏ | 998M/1.35G [00:04<00:01, 260MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 74%|███████▍ | 1.00G/1.35G [00:04<00:01, 262MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▌ | 1.02G/1.35G [00:04<00:01, 261MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 78%|███████▊ | 1.05G/1.35G [00:04<00:01, 260MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|███████▉ | 1.07G/1.35G [00:04<00:01, 253MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 81%|████████▏ | 1.10G/1.35G [00:04<00:01, 256MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 83%|████████▎ | 1.12G/1.35G [00:05<00:00, 258MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 85%|████████▌ | 1.15G/1.35G [00:05<00:00, 259MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 87%|████████▋ | 1.17G/1.35G [00:05<00:00, 260MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 89%|████████▊ | 1.19G/1.35G [00:05<00:00, 261MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 91%|█████████ | 1.22G/1.35G [00:05<00:00, 261MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 1.24G/1.35G [00:05<00:00, 263MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▍| 1.27G/1.35G [00:05<00:00, 263MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▌| 1.29G/1.35G [00:05<00:00, 263MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 98%|█████████▊| 1.32G/1.35G [00:05<00:00, 252MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|█████████▉| 1.34G/1.35G [00:05<00:00, 255MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 1.35G/1.35G [00:05<00:00, 242MB/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": "2023-07-03T12:16:40.242070Z",
"iopub.status.busy": "2023-07-03T12:16:40.241013Z",
"iopub.status.idle": "2023-07-03T12:17:22.045870Z",
"shell.execute_reply": "2023-07-03T12:17:22.044528Z"
},
"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": "2023-07-03T12:17:22.116389Z",
"iopub.status.busy": "2023-07-03T12:17:22.115755Z",
"iopub.status.idle": "2023-07-03T12:17:22.201902Z",
"shell.execute_reply": "2023-07-03T12:17:22.201122Z"
},
"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": "2023-07-03T12:17:22.209403Z",
"iopub.status.busy": "2023-07-03T12:17:22.208643Z",
"iopub.status.idle": "2023-07-03T12:17:22.380663Z",
"shell.execute_reply": "2023-07-03T12:17:22.379447Z"
},
"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/102141_2_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/102730_eng.png</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" filename\n",
"0 data/102141_2_eng.png\n",
"1 data/106349S_por.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": "2023-07-03T12:17:22.400724Z",
"iopub.status.busy": "2023-07-03T12:17:22.400347Z",
"iopub.status.idle": "2023-07-03T12:17:22.446268Z",
"shell.execute_reply": "2023-07-03T12:17:22.445457Z"
}
},
"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": "2023-07-03T12:17:22.457026Z",
"iopub.status.busy": "2023-07-03T12:17:22.456349Z",
"iopub.status.idle": "2023-07-03T12:17:22.505670Z",
"shell.execute_reply": "2023-07-03T12:17:22.504858Z"
},
"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": "2023-07-03T12:17:22.513172Z",
"iopub.status.busy": "2023-07-03T12:17:22.512915Z",
"iopub.status.idle": "2023-07-03T12:17:22.516262Z",
"shell.execute_reply": "2023-07-03T12:17:22.515567Z"
}
},
"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": "2023-07-03T12:17:22.522018Z",
"iopub.status.busy": "2023-07-03T12:17:22.521409Z",
"iopub.status.idle": "2023-07-03T12:17:22.564237Z",
"shell.execute_reply": "2023-07-03T12:17:22.563271Z"
}
},
"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": "2023-07-03T12:17:22.572925Z",
"iopub.status.busy": "2023-07-03T12:17:22.572413Z",
"iopub.status.idle": "2023-07-03T12:19:12.624557Z",
"shell.execute_reply": "2023-07-03T12:19:12.621474Z"
}
},
"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": "2023-07-03T12:19:12.655963Z",
"iopub.status.busy": "2023-07-03T12:19:12.655626Z",
"iopub.status.idle": "2023-07-03T12:19:12.673902Z",
"shell.execute_reply": "2023-07-03T12:19:12.672593Z"
}
},
"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": "2023-07-03T12:19:12.679448Z",
"iopub.status.busy": "2023-07-03T12:19:12.678774Z",
"iopub.status.idle": "2023-07-03T12:19:12.727513Z",
"shell.execute_reply": "2023-07-03T12:19:12.726494Z"
}
},
"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/102141_2_eng.png</td>\n",
" <td>1</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/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/102141_2_eng.png 1 \n",
"1 data/106349S_por.png 1 \n",
"2 data/102730_eng.png 2 \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": "2023-07-03T12:19:12.734953Z",
"iopub.status.busy": "2023-07-03T12:19:12.734695Z",
"iopub.status.idle": "2023-07-03T12:19:12.743683Z",
"shell.execute_reply": "2023-07-03T12:19:12.743065Z"
}
},
"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