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

2439 строки
56 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": "2023-06-14T20:28:13.008765Z",
"iopub.status.busy": "2023-06-14T20:28:13.008147Z",
"iopub.status.idle": "2023-06-14T20:28:13.016452Z",
"shell.execute_reply": "2023-06-14T20:28:13.015879Z"
}
},
"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": "2023-06-14T20:28:13.019331Z",
"iopub.status.busy": "2023-06-14T20:28:13.018724Z",
"iopub.status.idle": "2023-06-14T20:28:23.338700Z",
"shell.execute_reply": "2023-06-14T20:28:23.338058Z"
},
"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": "2023-06-14T20:28:23.342476Z",
"iopub.status.busy": "2023-06-14T20:28:23.341628Z",
"iopub.status.idle": "2023-06-14T20:28:23.346656Z",
"shell.execute_reply": "2023-06-14T20:28:23.346101Z"
},
"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": "2023-06-14T20:28:23.349297Z",
"iopub.status.busy": "2023-06-14T20:28:23.348946Z",
"iopub.status.idle": "2023-06-14T20:28:23.352024Z",
"shell.execute_reply": "2023-06-14T20:28:23.351407Z"
},
"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": "2023-06-14T20:28:23.355482Z",
"iopub.status.busy": "2023-06-14T20:28:23.354887Z",
"iopub.status.idle": "2023-06-14T20:28:51.454799Z",
"shell.execute_reply": "2023-06-14T20:28:51.454044Z"
},
"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<01:26, 31.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 0%| | 8.01M/2.50G [00:00<01:39, 26.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 16.0M/2.50G [00:00<00:58, 45.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 24.1M/2.50G [00:00<00:45, 58.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%|▏ | 32.1M/2.50G [00:00<00:39, 66.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 40.0M/2.50G [00:00<00:38, 68.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 48.0M/2.50G [00:00<00:38, 68.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 56.0M/2.50G [00:00<00:37, 70.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 64.0M/2.50G [00:01<00:35, 73.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 72.7M/2.50G [00:01<00:33, 78.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 82.9M/2.50G [00:01<00:29, 86.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▎ | 95.5M/2.50G [00:01<00:25, 100MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▍ | 105M/2.50G [00:01<00:29, 88.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▍ | 117M/2.50G [00:01<00:26, 98.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▌ | 130M/2.50G [00:01<00:23, 110MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 6%|▌ | 144M/2.50G [00:01<00:21, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 6%|▌ | 160M/2.50G [00:01<00:19, 128MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 7%|▋ | 179M/2.50G [00:02<00:16, 150MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 8%|▊ | 194M/2.50G [00:02<00:16, 147MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 8%|▊ | 212M/2.50G [00:02<00:15, 159MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 9%|▉ | 230M/2.50G [00:02<00:14, 166MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|▉ | 246M/2.50G [00:02<00:15, 156MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|█ | 261M/2.50G [00:02<00:17, 140MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 11%|█ | 277M/2.50G [00:02<00:16, 149MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 12%|█▏ | 296M/2.50G [00:02<00:14, 163MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 12%|█▏ | 315M/2.50G [00:02<00:13, 171MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 13%|█▎ | 336M/2.50G [00:03<00:12, 184MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 14%|█▍ | 358M/2.50G [00:03<00:11, 196MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 15%|█▍ | 377M/2.50G [00:03<00:12, 184MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 15%|█▌ | 395M/2.50G [00:03<00:12, 186MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 16%|█▌ | 416M/2.50G [00:03<00:11, 194MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 17%|█▋ | 438M/2.50G [00:03<00:10, 204MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 18%|█▊ | 458M/2.50G [00:03<00:10, 202MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 19%|█▊ | 479M/2.50G [00:03<00:10, 207MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|█▉ | 502M/2.50G [00:03<00:09, 220MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|██ | 524M/2.50G [00:04<00:11, 179MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 21%|██▏ | 549M/2.50G [00:04<00:10, 203MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 22%|██▏ | 573M/2.50G [00:04<00:09, 214MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 23%|██▎ | 598M/2.50G [00:04<00:09, 229MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 24%|██▍ | 621M/2.50G [00:04<00:08, 230MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 25%|██▌ | 643M/2.50G [00:04<00:10, 196MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 26%|██▌ | 663M/2.50G [00:04<00:12, 163MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 688M/2.50G [00:04<00:12, 161MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 28%|██▊ | 715M/2.50G [00:05<00:10, 188MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 29%|██▊ | 734M/2.50G [00:05<00:10, 177MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 30%|██▉ | 758M/2.50G [00:05<00:09, 194MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 30%|███ | 777M/2.50G [00:05<00:10, 185MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 31%|███ | 796M/2.50G [00:05<00:12, 145MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 32%|███▏ | 816M/2.50G [00:05<00:12, 146MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 32%|███▏ | 832M/2.50G [00:05<00:12, 151MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 33%|███▎ | 854M/2.50G [00:05<00:10, 171MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 34%|███▍ | 872M/2.50G [00:06<00:14, 122MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 35%|███▍ | 889M/2.50G [00:06<00:13, 132MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 36%|███▌ | 913M/2.50G [00:06<00:10, 160MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 36%|███▋ | 931M/2.50G [00:06<00:11, 153MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 37%|███▋ | 954M/2.50G [00:06<00:09, 175MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 38%|███▊ | 973M/2.50G [00:06<00:09, 176MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 39%|███▊ | 991M/2.50G [00:06<00:09, 181MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 39%|███▉ | 0.99G/2.50G [00:07<00:10, 154MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 40%|████ | 1.00G/2.50G [00:07<00:11, 140MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 41%|████ | 1.02G/2.50G [00:07<00:09, 165MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 42%|████▏ | 1.04G/2.50G [00:07<00:11, 139MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 42%|████▏ | 1.06G/2.50G [00:07<00:09, 162MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 43%|████▎ | 1.09G/2.50G [00:07<00:08, 182MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 44%|████▍ | 1.11G/2.50G [00:07<00:07, 201MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 45%|████▌ | 1.13G/2.50G [00:07<00:08, 168MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 46%|████▌ | 1.15G/2.50G [00:08<00:08, 174MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 47%|████▋ | 1.17G/2.50G [00:08<00:07, 187MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 48%|████▊ | 1.20G/2.50G [00:08<00:06, 216MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 49%|████▉ | 1.22G/2.50G [00:08<00:06, 217MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 50%|████▉ | 1.24G/2.50G [00:08<00:07, 191MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 50%|█████ | 1.26G/2.50G [00:08<00:06, 193MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 51%|█████ | 1.28G/2.50G [00:08<00:06, 197MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 52%|█████▏ | 1.31G/2.50G [00:08<00:05, 230MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 53%|█████▎ | 1.33G/2.50G [00:08<00:05, 233MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 54%|█████▍ | 1.36G/2.50G [00:09<00:05, 235MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 55%|█████▌ | 1.38G/2.50G [00:09<00:05, 238MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 56%|█████▌ | 1.40G/2.50G [00:09<00:04, 246MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 57%|█████▋ | 1.43G/2.50G [00:09<00:05, 197MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 58%|█████▊ | 1.45G/2.50G [00:09<00:06, 184MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 59%|█████▊ | 1.46G/2.50G [00:09<00:06, 178MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 59%|█████▉ | 1.48G/2.50G [00:09<00:06, 165MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 60%|█████▉ | 1.50G/2.50G [00:09<00:06, 157MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 61%|██████ | 1.52G/2.50G [00:10<00:06, 166MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 62%|██████▏ | 1.54G/2.50G [00:10<00:05, 196MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 62%|██████▏ | 1.56G/2.50G [00:10<00:04, 207MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 63%|██████▎ | 1.59G/2.50G [00:10<00:04, 224MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 64%|██████▍ | 1.61G/2.50G [00:10<00:04, 216MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 65%|██████▌ | 1.64G/2.50G [00:10<00:04, 230MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 66%|██████▋ | 1.66G/2.50G [00:10<00:03, 242MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 67%|██████▋ | 1.68G/2.50G [00:10<00:03, 246MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 68%|██████▊ | 1.71G/2.50G [00:10<00:03, 244MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 69%|██████▉ | 1.73G/2.50G [00:10<00:03, 247MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 70%|███████ | 1.75G/2.50G [00:11<00:03, 233MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 71%|███████ | 1.78G/2.50G [00:11<00:03, 231MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 72%|███████▏ | 1.80G/2.50G [00:11<00:03, 239MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 73%|███████▎ | 1.82G/2.50G [00:11<00:03, 211MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 74%|███████▎ | 1.84G/2.50G [00:11<00:03, 203MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 75%|███████▍ | 1.87G/2.50G [00:11<00:03, 221MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▌ | 1.89G/2.50G [00:11<00:02, 233MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▋ | 1.92G/2.50G [00:11<00:02, 233MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 77%|███████▋ | 1.94G/2.50G [00:11<00:02, 240MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 78%|███████▊ | 1.96G/2.50G [00:12<00:02, 238MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 79%|███████▉ | 1.98G/2.50G [00:12<00:02, 241MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|████████ | 2.01G/2.50G [00:12<00:02, 240MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 81%|████████ | 2.03G/2.50G [00:12<00:02, 242MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 82%|████████▏ | 2.05G/2.50G [00:12<00:01, 247MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 83%|████████▎ | 2.08G/2.50G [00:12<00:01, 255MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 84%|████████▍ | 2.10G/2.50G [00:12<00:01, 243MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 85%|████████▍ | 2.13G/2.50G [00:12<00:01, 244MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 86%|████████▌ | 2.15G/2.50G [00:12<00:01, 243MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 87%|████████▋ | 2.17G/2.50G [00:12<00:01, 236MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 88%|████████▊ | 2.19G/2.50G [00:13<00:01, 237MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 89%|████████▊ | 2.22G/2.50G [00:13<00:01, 240MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 89%|████████▉ | 2.24G/2.50G [00:13<00:01, 235MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|█████████ | 2.27G/2.50G [00:13<00:01, 246MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 91%|█████████▏| 2.29G/2.50G [00:14<00:03, 74.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 2.31G/2.50G [00:14<00:02, 89.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 93%|█████████▎| 2.33G/2.50G [00:14<00:01, 100MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▍| 2.35G/2.50G [00:14<00:01, 99.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 95%|█████████▍| 2.38G/2.50G [00:14<00:01, 125MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▌| 2.40G/2.50G [00:14<00:00, 139MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▋| 2.41G/2.50G [00:16<00:01, 50.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 97%|█████████▋| 2.44G/2.50G [00:16<00:01, 66.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 98%|█████████▊| 2.45G/2.50G [00:16<00:00, 69.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 99%|█████████▉| 2.48G/2.50G [00:16<00:00, 92.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|█████████▉| 2.49G/2.50G [00:16<00:00, 104MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 2.50G/2.50G [00:16<00:00, 160MB/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": "2023-06-14T20:28:51.458548Z",
"iopub.status.busy": "2023-06-14T20:28:51.458143Z",
"iopub.status.idle": "2023-06-14T20:29:24.517911Z",
"shell.execute_reply": "2023-06-14T20:29:24.517300Z"
},
"tags": []
},
"outputs": [],
"source": [
"for key in mydict:\n",
" mydict[key] = sm.SummaryDetector(mydict[key]).analyse_image(\n",
" summary_model=summary_model, summary_vis_processors=summary_vis_processors\n",
" )"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"tags": []
},
"source": [
"Convert the dictionary of dictionarys into a dictionary with lists:"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T20:29:24.521415Z",
"iopub.status.busy": "2023-06-14T20:29:24.521166Z",
"iopub.status.idle": "2023-06-14T20:29:24.525876Z",
"shell.execute_reply": "2023-06-14T20:29:24.525288Z"
},
"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": "2023-06-14T20:29:24.528923Z",
"iopub.status.busy": "2023-06-14T20:29:24.528703Z",
"iopub.status.idle": "2023-06-14T20:29:24.542275Z",
"shell.execute_reply": "2023-06-14T20:29:24.541721Z"
},
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>filename</th>\n",
" <th>const_image_summary</th>\n",
" <th>3_non-deterministic summary</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>data/102730_eng.png</td>\n",
" <td>two people in blue coats spray disinfection a van</td>\n",
" <td>[two doctors in blue coats spray disinfection ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>data/106349S_por.png</td>\n",
" <td>a man wearing a face mask while looking at a c...</td>\n",
" <td>[a person wearing a mask while talking on the ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>data/102141_2_eng.png</td>\n",
" <td>a collage of images including a corona sign, a...</td>\n",
" <td>[a picture collage with a person in chemical s...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" filename const_image_summary \\\n",
"0 data/102730_eng.png two people in blue coats spray disinfection a van \n",
"1 data/106349S_por.png a man wearing a face mask while looking at a c... \n",
"2 data/102141_2_eng.png a collage of images including a corona sign, a... \n",
"\n",
" 3_non-deterministic summary \n",
"0 [two doctors in blue coats spray disinfection ... \n",
"1 [a person wearing a mask while talking on the ... \n",
"2 [a picture collage with a person in chemical s... "
]
},
"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": "2023-06-14T20:29:24.545433Z",
"iopub.status.busy": "2023-06-14T20:29:24.545206Z",
"iopub.status.idle": "2023-06-14T20:29:24.550655Z",
"shell.execute_reply": "2023-06-14T20:29:24.550144Z"
}
},
"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": "2023-06-14T20:29:24.553400Z",
"iopub.status.busy": "2023-06-14T20:29:24.552869Z",
"iopub.status.idle": "2023-06-14T20:29:24.599646Z",
"shell.execute_reply": "2023-06-14T20:29:24.598996Z"
},
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Dash is running on http://127.0.0.1:8055/\n",
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:dash.dash:Dash is running on http://127.0.0.1:8055/\n",
"\n"
]
},
{
"data": {
"text/html": [
"\n",
" <iframe\n",
" width=\"100%\"\n",
" height=\"650\"\n",
" src=\"http://127.0.0.1:8055/\"\n",
" frameborder=\"0\"\n",
" allowfullscreen\n",
" \n",
" ></iframe>\n",
" "
],
"text/plain": [
"<IPython.lib.display.IFrame at 0x7f815a6741c0>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"analysis_explorer = mdisplay.AnalysisExplorer(mydict, identify=\"summary\")\n",
"analysis_explorer.run_server(port=8055)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Generate answers to free-form questions about images written in natural language. "
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Set the list of questions as a list of strings:"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T20:29:24.603193Z",
"iopub.status.busy": "2023-06-14T20:29:24.602588Z",
"iopub.status.idle": "2023-06-14T20:29:24.606468Z",
"shell.execute_reply": "2023-06-14T20:29:24.605921Z"
}
},
"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": "2023-06-14T20:29:24.609150Z",
"iopub.status.busy": "2023-06-14T20:29:24.608727Z",
"iopub.status.idle": "2023-06-14T20:29:25.127457Z",
"shell.execute_reply": "2023-06-14T20:29:25.126820Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Dash is running on http://127.0.0.1:8055/\n",
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:dash.dash:Dash is running on http://127.0.0.1:8055/\n",
"\n"
]
},
{
"data": {
"text/html": [
"\n",
" <iframe\n",
" width=\"100%\"\n",
" height=\"650\"\n",
" src=\"http://127.0.0.1:8055/\"\n",
" frameborder=\"0\"\n",
" allowfullscreen\n",
" \n",
" ></iframe>\n",
" "
],
"text/plain": [
"<IPython.lib.display.IFrame at 0x7f815a62f5b0>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"analysis_explorer = mdisplay.AnalysisExplorer(mydict, identify=\"summary\")\n",
"analysis_explorer.run_server(port=8055)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Or directly analyze for further processing\n",
"Instead of inspecting each of the images, you can also directly carry out the analysis and export the result into a csv. This may take a while depending on how many images you have loaded."
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T20:29:25.131491Z",
"iopub.status.busy": "2023-06-14T20:29:25.130163Z",
"iopub.status.idle": "2023-06-14T20:30:17.019725Z",
"shell.execute_reply": "2023-06-14T20:30:17.019011Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 0%| | 0.00/1.35G [00:00<?, ?B/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 0%| | 4.01M/1.35G [00:00<00:46, 31.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 13.7M/1.35G [00:00<00:21, 67.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%|▏ | 20.7M/1.35G [00:00<00:22, 63.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 27.0M/1.35G [00:00<00:23, 60.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 38.4M/1.35G [00:00<00:17, 79.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▍ | 53.3M/1.35G [00:00<00:13, 104MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▍ | 64.0M/1.35G [00:00<00:16, 83.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▌ | 72.8M/1.35G [00:01<00:19, 69.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 6%|▌ | 80.2M/1.35G [00:01<00:20, 67.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 6%|▋ | 88.0M/1.35G [00:01<00:23, 56.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 7%|▋ | 96.0M/1.35G [00:01<00:23, 56.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 8%|▊ | 104M/1.35G [00:01<00:22, 60.6MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 8%|▊ | 113M/1.35G [00:01<00:19, 68.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 9%|▉ | 126M/1.35G [00:01<00:15, 84.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|▉ | 134M/1.35G [00:02<00:18, 72.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|█ | 142M/1.35G [00:02<00:18, 71.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 11%|█ | 149M/1.35G [00:02<00:35, 35.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 12%|█▏ | 160M/1.35G [00:02<00:29, 43.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 12%|█▏ | 168M/1.35G [00:02<00:25, 49.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 13%|█▎ | 176M/1.35G [00:03<00:23, 54.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 14%|█▍ | 192M/1.35G [00:03<00:18, 66.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 15%|█▌ | 208M/1.35G [00:03<00:18, 67.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 16%|█▌ | 220M/1.35G [00:03<00:15, 77.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 17%|█▋ | 229M/1.35G [00:03<00:14, 81.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 17%|█▋ | 240M/1.35G [00:03<00:13, 89.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 18%|█▊ | 249M/1.35G [00:03<00:15, 78.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 19%|█▊ | 258M/1.35G [00:04<00:17, 65.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|█▉ | 274M/1.35G [00:04<00:13, 88.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 21%|██ | 288M/1.35G [00:04<00:13, 86.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 22%|██▏ | 297M/1.35G [00:04<00:18, 61.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 23%|██▎ | 312M/1.35G [00:04<00:15, 71.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 23%|██▎ | 320M/1.35G [00:04<00:15, 71.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 25%|██▍ | 338M/1.35G [00:05<00:11, 96.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 26%|██▌ | 352M/1.35G [00:05<00:10, 99.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 376M/1.35G [00:05<00:07, 135MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 28%|██▊ | 391M/1.35G [00:05<00:08, 124MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 29%|██▉ | 406M/1.35G [00:05<00:07, 133MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 31%|███ | 427M/1.35G [00:05<00:06, 155MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 32%|███▏ | 447M/1.35G [00:05<00:05, 170MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 34%|███▎ | 464M/1.35G [00:06<00:08, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 35%|███▌ | 488M/1.35G [00:06<00:06, 141MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 37%|███▋ | 511M/1.35G [00:06<00:05, 162MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 38%|███▊ | 529M/1.35G [00:06<00:06, 139MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 40%|███▉ | 545M/1.35G [00:06<00:06, 128MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 41%|████ | 563M/1.35G [00:06<00:06, 141MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 42%|████▏ | 583M/1.35G [00:06<00:05, 158MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 43%|████▎ | 600M/1.35G [00:06<00:05, 161MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 45%|████▍ | 617M/1.35G [00:07<00:04, 167MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 46%|████▌ | 635M/1.35G [00:07<00:04, 171MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 48%|████▊ | 656M/1.35G [00:07<00:04, 187MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 49%|████▉ | 677M/1.35G [00:07<00:03, 194MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 51%|█████ | 700M/1.35G [00:07<00:03, 209MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 52%|█████▏ | 720M/1.35G [00:07<00:03, 205MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 54%|█████▍ | 744M/1.35G [00:07<00:03, 214MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 56%|█████▌ | 767M/1.35G [00:07<00:02, 220MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 57%|█████▋ | 788M/1.35G [00:07<00:02, 216MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 59%|█████▊ | 808M/1.35G [00:08<00:03, 155MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 60%|██████ | 831M/1.35G [00:08<00:03, 175MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 62%|██████▏ | 850M/1.35G [00:08<00:05, 104MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 63%|██████▎ | 871M/1.35G [00:08<00:04, 124MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 65%|██████▍ | 890M/1.35G [00:08<00:03, 138MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 66%|██████▌ | 907M/1.35G [00:08<00:03, 135MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 67%|██████▋ | 928M/1.35G [00:09<00:03, 121MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 68%|██████▊ | 942M/1.35G [00:09<00:04, 106MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 70%|██████▉ | 963M/1.35G [00:09<00:03, 128MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 71%|███████ | 977M/1.35G [00:09<00:03, 128MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 72%|███████▏ | 995M/1.35G [00:09<00:02, 142MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 73%|███████▎ | 0.99G/1.35G [00:09<00:02, 149MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 75%|███████▍ | 1.01G/1.35G [00:09<00:02, 161MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▌ | 1.02G/1.35G [00:09<00:02, 160MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 77%|███████▋ | 1.04G/1.35G [00:10<00:02, 162MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 79%|███████▊ | 1.06G/1.35G [00:10<00:01, 175MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|████████ | 1.08G/1.35G [00:10<00:01, 201MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 82%|████████▏ | 1.10G/1.35G [00:10<00:01, 147MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 83%|████████▎ | 1.12G/1.35G [00:10<00:01, 168MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 85%|████████▍ | 1.14G/1.35G [00:10<00:01, 181MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 87%|████████▋ | 1.17G/1.35G [00:10<00:00, 200MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 88%|████████▊ | 1.19G/1.35G [00:10<00:00, 192MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|████████▉ | 1.21G/1.35G [00:11<00:00, 193MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 91%|█████████▏| 1.23G/1.35G [00:11<00:00, 205MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 93%|█████████▎| 1.25G/1.35G [00:11<00:00, 202MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▍| 1.27G/1.35G [00:11<00:00, 129MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▌| 1.29G/1.35G [00:11<00:00, 144MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 97%|█████████▋| 1.30G/1.35G [00:11<00:00, 153MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 99%|█████████▊| 1.33G/1.35G [00:11<00:00, 178MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|█████████▉| 1.35G/1.35G [00:11<00:00, 162MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 1.35G/1.35G [00:11<00:00, 121MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
}
],
"source": [
"for key in mydict:\n",
" mydict[key] = sm.SummaryDetector(mydict[key]).analyse_questions(list_of_questions)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Convert to dataframe and write csv\n",
"These steps are required to convert the dictionary of dictionarys into a dictionary with lists, that can be converted into a pandas dataframe and exported to a csv file."
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T20:30:17.024400Z",
"iopub.status.busy": "2023-06-14T20:30:17.024029Z",
"iopub.status.idle": "2023-06-14T20:30:17.028358Z",
"shell.execute_reply": "2023-06-14T20:30:17.027854Z"
}
},
"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": "2023-06-14T20:30:17.031956Z",
"iopub.status.busy": "2023-06-14T20:30:17.031625Z",
"iopub.status.idle": "2023-06-14T20:30:17.040721Z",
"shell.execute_reply": "2023-06-14T20:30:17.040232Z"
}
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>filename</th>\n",
" <th>const_image_summary</th>\n",
" <th>3_non-deterministic summary</th>\n",
" <th>How many persons on the picture?</th>\n",
" <th>Are there any politicians in the picture?</th>\n",
" <th>Does the picture show something from medicine?</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>data/102730_eng.png</td>\n",
" <td>two people in blue coats spray disinfection a van</td>\n",
" <td>[two doctors in blue coats spray disinfection ...</td>\n",
" <td>2</td>\n",
" <td>no</td>\n",
" <td>yes</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>data/106349S_por.png</td>\n",
" <td>a man wearing a face mask while looking at a c...</td>\n",
" <td>[a person wearing a mask while talking on the ...</td>\n",
" <td>1</td>\n",
" <td>yes</td>\n",
" <td>yes</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>data/102141_2_eng.png</td>\n",
" <td>a collage of images including a corona sign, a...</td>\n",
" <td>[a picture collage with a person in chemical s...</td>\n",
" <td>1</td>\n",
" <td>no</td>\n",
" <td>yes</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" filename const_image_summary \\\n",
"0 data/102730_eng.png two people in blue coats spray disinfection a van \n",
"1 data/106349S_por.png a man wearing a face mask while looking at a c... \n",
"2 data/102141_2_eng.png a collage of images including a corona sign, a... \n",
"\n",
" 3_non-deterministic summary \\\n",
"0 [two doctors in blue coats spray disinfection ... \n",
"1 [a person wearing a mask while talking on the ... \n",
"2 [a picture collage with a person in chemical s... \n",
"\n",
" How many persons on the picture? Are there any politicians in the picture? \\\n",
"0 2 no \n",
"1 1 yes \n",
"2 1 no \n",
"\n",
" Does the picture show something from medicine? \n",
"0 yes \n",
"1 yes \n",
"2 yes "
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df2.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"execution": {
"iopub.execute_input": "2023-06-14T20:30:17.043735Z",
"iopub.status.busy": "2023-06-14T20:30:17.043400Z",
"iopub.status.idle": "2023-06-14T20:30:17.047732Z",
"shell.execute_reply": "2023-06-14T20:30:17.047214Z"
}
},
"outputs": [],
"source": [
"df2.to_csv(\"data_out2.csv\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.16"
},
"vscode": {
"interpreter": {
"hash": "f1142466f556ab37fe2d38e2897a16796906208adb09fea90ba58bdf8a56f0ba"
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Ссылка в новой задаче Показать git blame Копировать постоянную ссылку