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

3599 строки
80 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": "2023-05-26T09:34:20.124150Z",
"iopub.status.busy": "2023-05-26T09:34:20.123919Z",
"iopub.status.idle": "2023-05-26T09:34:20.132420Z",
"shell.execute_reply": "2023-05-26T09:34:20.131778Z"
}
},
"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": "2023-05-26T09:34:20.135371Z",
"iopub.status.busy": "2023-05-26T09:34:20.134938Z",
"iopub.status.idle": "2023-05-26T09:34:31.164137Z",
"shell.execute_reply": "2023-05-26T09:34:31.163398Z"
},
"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": "2023-05-26T09:34:31.168295Z",
"iopub.status.busy": "2023-05-26T09:34:31.167332Z",
"iopub.status.idle": "2023-05-26T09:34:31.171678Z",
"shell.execute_reply": "2023-05-26T09:34:31.170972Z"
},
"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": "2023-05-26T09:34:31.174681Z",
"iopub.status.busy": "2023-05-26T09:34:31.174079Z",
"iopub.status.idle": "2023-05-26T09:34:31.177445Z",
"shell.execute_reply": "2023-05-26T09:34:31.176797Z"
},
"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": "2023-05-26T09:34:31.180851Z",
"iopub.status.busy": "2023-05-26T09:34:31.180314Z",
"iopub.status.idle": "2023-05-26T09:35:08.210237Z",
"shell.execute_reply": "2023-05-26T09:35:08.209403Z"
},
"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%| | 208k/2.50G [00:00<21:21, 2.10MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 0%| | 2.72M/2.50G [00:00<02:44, 16.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 0%| | 12.2M/2.50G [00:00<00:53, 50.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 21.2M/2.50G [00:00<00:41, 64.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 31.6M/2.50G [00:00<00:33, 80.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 40.8M/2.50G [00:00<00:30, 85.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 49.0M/2.50G [00:00<00:31, 84.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 58.5M/2.50G [00:00<00:29, 88.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 67.1M/2.50G [00:00<00:29, 89.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 76.1M/2.50G [00:01<00:28, 90.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 85.9M/2.50G [00:01<00:27, 94.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▎ | 95.1M/2.50G [00:01<00:27, 95.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▍ | 106M/2.50G [00:01<00:25, 101MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▍ | 117M/2.50G [00:01<00:24, 106MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▌ | 128M/2.50G [00:01<00:23, 108MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▌ | 139M/2.50G [00:01<00:23, 110MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 6%|▌ | 150M/2.50G [00:01<00:22, 112MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 6%|▋ | 162M/2.50G [00:01<00:22, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 7%|▋ | 172M/2.50G [00:01<00:22, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 7%|▋ | 183M/2.50G [00:02<00:21, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 8%|▊ | 195M/2.50G [00:02<00:21, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 8%|▊ | 206M/2.50G [00:02<00:21, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 8%|▊ | 217M/2.50G [00:02<00:21, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 9%|▉ | 228M/2.50G [00:02<00:21, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 9%|▉ | 239M/2.50G [00:02<00:21, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|▉ | 251M/2.50G [00:02<00:20, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|█ | 262M/2.50G [00:02<00:20, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 11%|█ | 273M/2.50G [00:02<00:20, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 11%|█ | 285M/2.50G [00:02<00:20, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 12%|█▏ | 296M/2.50G [00:03<00:20, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 12%|█▏ | 307M/2.50G [00:03<00:20, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 12%|█▏ | 319M/2.50G [00:03<00:19, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 13%|█▎ | 330M/2.50G [00:03<00:19, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 13%|█▎ | 341M/2.50G [00:03<00:19, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 14%|█▎ | 352M/2.50G [00:03<00:19, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 14%|█▍ | 363M/2.50G [00:03<00:19, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 15%|█▍ | 375M/2.50G [00:03<00:19, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 15%|█▌ | 386M/2.50G [00:04<00:28, 79.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 15%|█▌ | 395M/2.50G [00:04<00:26, 84.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 16%|█▌ | 406M/2.50G [00:04<00:24, 91.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 16%|█▋ | 418M/2.50G [00:04<00:22, 98.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 17%|█▋ | 429M/2.50G [00:04<00:21, 104MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 17%|█▋ | 440M/2.50G [00:04<00:20, 107MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 18%|█▊ | 451M/2.50G [00:04<00:20, 110MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 18%|█▊ | 463M/2.50G [00:04<00:19, 113MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 18%|█▊ | 474M/2.50G [00:04<00:19, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 19%|█▉ | 485M/2.50G [00:04<00:18, 115MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 19%|█▉ | 496M/2.50G [00:05<00:18, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|█▉ | 507M/2.50G [00:05<00:18, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|██ | 519M/2.50G [00:05<00:18, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 21%|██ | 530M/2.50G [00:05<00:18, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 21%|██ | 541M/2.50G [00:05<00:18, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 22%|██▏ | 552M/2.50G [00:05<00:18, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 22%|██▏ | 563M/2.50G [00:05<00:17, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 22%|██▏ | 575M/2.50G [00:05<00:17, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 23%|██▎ | 586M/2.50G [00:05<00:17, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 23%|██▎ | 597M/2.50G [00:05<00:17, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 24%|██▎ | 608M/2.50G [00:06<00:17, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 24%|██▍ | 620M/2.50G [00:06<00:17, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 25%|██▍ | 631M/2.50G [00:06<00:17, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 25%|██▌ | 642M/2.50G [00:06<00:17, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 25%|██▌ | 653M/2.50G [00:06<00:17, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 26%|██▌ | 664M/2.50G [00:06<00:17, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 26%|██▋ | 676M/2.50G [00:06<00:17, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 687M/2.50G [00:07<00:46, 42.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 698M/2.50G [00:07<00:37, 52.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 28%|██▊ | 707M/2.50G [00:07<00:35, 55.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 28%|██▊ | 718M/2.50G [00:07<00:29, 66.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 28%|██▊ | 729M/2.50G [00:07<00:25, 76.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 29%|██▉ | 739M/2.50G [00:08<00:34, 55.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 29%|██▉ | 749M/2.50G [00:08<00:30, 63.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 30%|██▉ | 760M/2.50G [00:08<00:25, 74.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 30%|███ | 771M/2.50G [00:08<00:22, 83.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 31%|███ | 782M/2.50G [00:08<00:20, 91.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 31%|███ | 792M/2.50G [00:08<00:24, 76.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 31%|███▏ | 804M/2.50G [00:08<00:21, 85.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 32%|███▏ | 815M/2.50G [00:08<00:19, 93.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 32%|███▏ | 826M/2.50G [00:08<00:18, 99.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 33%|███▎ | 837M/2.50G [00:09<00:17, 105MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 33%|███▎ | 848M/2.50G [00:09<00:16, 106MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 34%|███▎ | 860M/2.50G [00:09<00:16, 111MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 34%|███▍ | 871M/2.50G [00:09<00:15, 112MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 34%|███▍ | 882M/2.50G [00:09<00:15, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 35%|███▍ | 893M/2.50G [00:09<00:15, 115MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 35%|███▌ | 905M/2.50G [00:09<00:15, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 36%|███▌ | 916M/2.50G [00:09<00:14, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 36%|███▌ | 927M/2.50G [00:09<00:14, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 37%|███▋ | 938M/2.50G [00:09<00:14, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 37%|███▋ | 949M/2.50G [00:10<00:14, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 37%|███▋ | 960M/2.50G [00:10<00:14, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 38%|███▊ | 972M/2.50G [00:10<00:14, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 38%|███▊ | 983M/2.50G [00:10<00:14, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 39%|███▉ | 994M/2.50G [00:10<00:14, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 39%|███▉ | 0.98G/2.50G [00:10<00:13, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 40%|███▉ | 0.99G/2.50G [00:10<00:13, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 40%|████ | 1.00G/2.50G [00:10<00:13, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 41%|████ | 1.02G/2.50G [00:10<00:13, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 41%|████ | 1.03G/2.50G [00:10<00:13, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 41%|████▏ | 1.04G/2.50G [00:11<00:13, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 42%|████▏ | 1.05G/2.50G [00:11<00:13, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 42%|████▏ | 1.06G/2.50G [00:11<00:13, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 43%|████▎ | 1.07G/2.50G [00:11<00:13, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 43%|████▎ | 1.08G/2.50G [00:11<00:13, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 44%|████▎ | 1.09G/2.50G [00:11<00:12, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 44%|████▍ | 1.10G/2.50G [00:11<00:12, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 45%|████▍ | 1.11G/2.50G [00:11<00:12, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 45%|████▍ | 1.13G/2.50G [00:11<00:12, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 45%|████▌ | 1.14G/2.50G [00:11<00:12, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 46%|████▌ | 1.15G/2.50G [00:12<00:12, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 46%|████▋ | 1.16G/2.50G [00:12<00:12, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 47%|████▋ | 1.17G/2.50G [00:12<00:12, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 47%|████▋ | 1.18G/2.50G [00:12<00:12, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 48%|████▊ | 1.19G/2.50G [00:12<00:12, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 48%|████▊ | 1.20G/2.50G [00:12<00:12, 112MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 48%|████▊ | 1.21G/2.50G [00:12<00:12, 113MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 49%|████▉ | 1.22G/2.50G [00:12<00:12, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 49%|████▉ | 1.24G/2.50G [00:12<00:11, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 50%|████▉ | 1.25G/2.50G [00:13<00:11, 115MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 50%|█████ | 1.26G/2.50G [00:13<00:11, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 51%|█████ | 1.27G/2.50G [00:13<00:11, 115MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 51%|█████ | 1.28G/2.50G [00:13<00:11, 115MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 52%|█████▏ | 1.29G/2.50G [00:13<00:17, 75.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 52%|█████▏ | 1.30G/2.50G [00:13<00:15, 84.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 52%|█████▏ | 1.31G/2.50G [00:13<00:13, 91.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 53%|█████▎ | 1.32G/2.50G [00:13<00:15, 84.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 53%|█████▎ | 1.33G/2.50G [00:14<00:13, 93.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 54%|█████▎ | 1.34G/2.50G [00:14<00:22, 54.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 54%|█████▍ | 1.35G/2.50G [00:14<00:19, 63.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 54%|█████▍ | 1.36G/2.50G [00:14<00:16, 73.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 55%|█████▍ | 1.37G/2.50G [00:14<00:14, 83.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 55%|█████▌ | 1.38G/2.50G [00:14<00:13, 91.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 56%|█████▌ | 1.39G/2.50G [00:15<00:16, 73.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 56%|█████▌ | 1.41G/2.50G [00:15<00:13, 85.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 57%|█████▋ | 1.42G/2.50G [00:15<00:12, 92.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 57%|█████▋ | 1.43G/2.50G [00:15<00:11, 97.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 57%|█████▋ | 1.44G/2.50G [00:15<00:19, 58.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 58%|█████▊ | 1.45G/2.50G [00:15<00:17, 66.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 58%|█████▊ | 1.46G/2.50G [00:15<00:15, 74.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 59%|█████▊ | 1.47G/2.50G [00:16<00:13, 84.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 59%|█████▉ | 1.48G/2.50G [00:16<00:11, 92.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 59%|█████▉ | 1.49G/2.50G [00:16<00:11, 98.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 60%|█████▉ | 1.50G/2.50G [00:16<00:10, 104MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 60%|██████ | 1.51G/2.50G [00:16<00:09, 108MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 61%|██████ | 1.52G/2.50G [00:16<00:09, 109MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 61%|██████ | 1.53G/2.50G [00:16<00:09, 111MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 62%|██████▏ | 1.54G/2.50G [00:16<00:09, 112MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 62%|██████▏ | 1.55G/2.50G [00:16<00:08, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 63%|██████▎ | 1.57G/2.50G [00:16<00:08, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 63%|██████▎ | 1.58G/2.50G [00:17<00:08, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 63%|██████▎ | 1.59G/2.50G [00:17<00:08, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 64%|██████▍ | 1.60G/2.50G [00:17<00:08, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 64%|██████▍ | 1.61G/2.50G [00:17<00:08, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 65%|██████▍ | 1.62G/2.50G [00:17<00:08, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 65%|██████▌ | 1.63G/2.50G [00:17<00:08, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 66%|██████▌ | 1.64G/2.50G [00:17<00:08, 115MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 66%|██████▌ | 1.65G/2.50G [00:17<00:07, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 66%|██████▋ | 1.66G/2.50G [00:17<00:07, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 67%|██████▋ | 1.67G/2.50G [00:17<00:07, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 67%|██████▋ | 1.69G/2.50G [00:18<00:07, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 68%|██████▊ | 1.70G/2.50G [00:18<00:07, 115MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 68%|██████▊ | 1.71G/2.50G [00:18<00:07, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 69%|██████▊ | 1.72G/2.50G [00:18<00:07, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 69%|██████▉ | 1.73G/2.50G [00:18<00:07, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 70%|██████▉ | 1.74G/2.50G [00:18<00:06, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 70%|██████▉ | 1.75G/2.50G [00:18<00:06, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 70%|███████ | 1.76G/2.50G [00:18<00:06, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 71%|███████ | 1.77G/2.50G [00:18<00:06, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 71%|███████▏ | 1.78G/2.50G [00:18<00:06, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 72%|███████▏ | 1.79G/2.50G [00:19<00:06, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 72%|███████▏ | 1.81G/2.50G [00:19<00:06, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 73%|███████▎ | 1.82G/2.50G [00:19<00:06, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 73%|███████▎ | 1.83G/2.50G [00:19<00:06, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 73%|███████▎ | 1.84G/2.50G [00:19<00:06, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 74%|███████▍ | 1.85G/2.50G [00:19<00:06, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 74%|███████▍ | 1.86G/2.50G [00:19<00:05, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 75%|███████▍ | 1.87G/2.50G [00:19<00:05, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 75%|███████▌ | 1.88G/2.50G [00:19<00:05, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▌ | 1.89G/2.50G [00:19<00:05, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▌ | 1.90G/2.50G [00:20<00:05, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▋ | 1.92G/2.50G [00:20<00:05, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 77%|███████▋ | 1.93G/2.50G [00:20<00:10, 59.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 77%|███████▋ | 1.94G/2.50G [00:20<00:08, 69.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 78%|███████▊ | 1.95G/2.50G [00:20<00:07, 79.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 78%|███████▊ | 1.96G/2.50G [00:20<00:06, 84.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 79%|███████▊ | 1.97G/2.50G [00:21<00:09, 62.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 79%|███████▉ | 1.98G/2.50G [00:21<00:08, 63.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 79%|███████▉ | 1.98G/2.50G [00:21<00:08, 68.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|███████▉ | 1.99G/2.50G [00:21<00:07, 75.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|███████▉ | 2.00G/2.50G [00:21<00:06, 83.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|████████ | 2.01G/2.50G [00:21<00:08, 60.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 81%|████████ | 2.02G/2.50G [00:21<00:07, 71.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 81%|████████ | 2.03G/2.50G [00:22<00:06, 81.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 82%|████████▏ | 2.04G/2.50G [00:22<00:05, 89.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 82%|████████▏ | 2.05G/2.50G [00:22<00:07, 60.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 82%|████████▏ | 2.06G/2.50G [00:22<00:06, 68.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 83%|████████▎ | 2.07G/2.50G [00:22<00:05, 78.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 83%|████████▎ | 2.08G/2.50G [00:22<00:05, 87.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 84%|████████▎ | 2.09G/2.50G [00:22<00:04, 95.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 84%|████████▍ | 2.11G/2.50G [00:22<00:04, 101MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 85%|████████▍ | 2.12G/2.50G [00:23<00:03, 105MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 85%|████████▍ | 2.13G/2.50G [00:23<00:03, 108MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 85%|████████▌ | 2.14G/2.50G [00:23<00:03, 111MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 86%|████████▌ | 2.15G/2.50G [00:23<00:03, 113MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 86%|████████▋ | 2.16G/2.50G [00:23<00:03, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 87%|████████▋ | 2.17G/2.50G [00:23<00:03, 115MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 87%|████████▋ | 2.18G/2.50G [00:23<00:02, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 88%|████████▊ | 2.19G/2.50G [00:23<00:02, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 88%|████████▊ | 2.20G/2.50G [00:23<00:02, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 88%|████████▊ | 2.22G/2.50G [00:23<00:02, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 89%|████████▉ | 2.23G/2.50G [00:24<00:02, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 89%|████████▉ | 2.24G/2.50G [00:24<00:02, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|████████▉ | 2.25G/2.50G [00:24<00:02, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|█████████ | 2.26G/2.50G [00:24<00:02, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 91%|█████████ | 2.27G/2.50G [00:24<00:02, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 91%|█████████ | 2.28G/2.50G [00:24<00:02, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 2.29G/2.50G [00:24<00:01, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 2.30G/2.50G [00:24<00:01, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 2.31G/2.50G [00:24<00:01, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 93%|█████████▎| 2.32G/2.50G [00:24<00:01, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 93%|█████████▎| 2.34G/2.50G [00:25<00:01, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▎| 2.35G/2.50G [00:25<00:01, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▍| 2.36G/2.50G [00:25<00:01, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 95%|█████████▍| 2.37G/2.50G [00:25<00:01, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 95%|█████████▌| 2.38G/2.50G [00:25<00:01, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▌| 2.39G/2.50G [00:25<00:01, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▌| 2.40G/2.50G [00:25<00:00, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▋| 2.41G/2.50G [00:25<00:00, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 97%|█████████▋| 2.42G/2.50G [00:25<00:00, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 97%|█████████▋| 2.43G/2.50G [00:25<00:00, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 98%|█████████▊| 2.45G/2.50G [00:26<00:00, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 98%|█████████▊| 2.46G/2.50G [00:26<00:00, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 99%|█████████▊| 2.47G/2.50G [00:26<00:00, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 99%|█████████▉| 2.48G/2.50G [00:26<00:00, 116MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 99%|█████████▉| 2.49G/2.50G [00:26<00:00, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|█████████▉| 2.50G/2.50G [00:26<00:00, 109MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 2.50G/2.50G [00:26<00:00, 101MB/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": "2023-05-26T09:35:08.214704Z",
"iopub.status.busy": "2023-05-26T09:35:08.214273Z",
"iopub.status.idle": "2023-05-26T09:35:41.235078Z",
"shell.execute_reply": "2023-05-26T09:35:41.234360Z"
},
"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": "2023-05-26T09:35:41.238872Z",
"iopub.status.busy": "2023-05-26T09:35:41.238162Z",
"iopub.status.idle": "2023-05-26T09:35:41.242202Z",
"shell.execute_reply": "2023-05-26T09:35:41.241687Z"
},
"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": "2023-05-26T09:35:41.245065Z",
"iopub.status.busy": "2023-05-26T09:35:41.244505Z",
"iopub.status.idle": "2023-05-26T09:35:41.256710Z",
"shell.execute_reply": "2023-05-26T09:35:41.256049Z"
},
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>filename</th>\n",
" <th>const_image_summary</th>\n",
" <th>3_non-deterministic summary</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>data/102730_eng.png</td>\n",
" <td>two people in blue coats spray disinfection a van</td>\n",
" <td>[two people in blue robes spraying geranis, tw...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>data/102141_2_eng.png</td>\n",
" <td>a collage of images including a corona sign, a...</td>\n",
" <td>[the corona vaccine is being released from cor...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</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 man in a white shirt is on a news desk, a m...</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/102141_2_eng.png a collage of images including a corona sign, a... \n",
"2 data/106349S_por.png a man wearing a face mask while looking at a c... \n",
"\n",
" 3_non-deterministic summary \n",
"0 [two people in blue robes spraying geranis, tw... \n",
"1 [the corona vaccine is being released from cor... \n",
"2 [a man in a white shirt is on a news desk, a m... "
]
},
"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": "2023-05-26T09:35:41.259680Z",
"iopub.status.busy": "2023-05-26T09:35:41.259247Z",
"iopub.status.idle": "2023-05-26T09:35:41.264127Z",
"shell.execute_reply": "2023-05-26T09:35:41.263539Z"
}
},
"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": "2023-05-26T09:35:41.266914Z",
"iopub.status.busy": "2023-05-26T09:35:41.266476Z",
"iopub.status.idle": "2023-05-26T09:35:41.292442Z",
"shell.execute_reply": "2023-05-26T09:35:41.291849Z"
},
"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 0x7fb1519bd730>"
]
},
"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": "2023-05-26T09:35:41.295577Z",
"iopub.status.busy": "2023-05-26T09:35:41.295144Z",
"iopub.status.idle": "2023-05-26T09:35:41.298652Z",
"shell.execute_reply": "2023-05-26T09:35:41.297666Z"
}
},
"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": "2023-05-26T09:35:41.301756Z",
"iopub.status.busy": "2023-05-26T09:35:41.301328Z",
"iopub.status.idle": "2023-05-26T09:35:41.824478Z",
"shell.execute_reply": "2023-05-26T09:35:41.823781Z"
}
},
"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 0x7fb14c512790>"
]
},
"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": "2023-05-26T09:35:41.828140Z",
"iopub.status.busy": "2023-05-26T09:35:41.827666Z",
"iopub.status.idle": "2023-05-26T09:36:39.251261Z",
"shell.execute_reply": "2023-05-26T09:36:39.250458Z"
}
},
"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%| | 288k/1.35G [00:00<08:15, 2.92MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 0%| | 5.23M/1.35G [00:00<00:45, 31.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 10.7M/1.35G [00:00<00:33, 43.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 16.1M/1.35G [00:00<00:29, 48.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 20.8M/1.35G [00:00<00:30, 47.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 2%|▏ | 27.2M/1.35G [00:00<00:26, 53.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 35.5M/1.35G [00:00<00:28, 50.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 3%|▎ | 42.3M/1.35G [00:00<00:26, 53.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▎ | 51.2M/1.35G [00:01<00:21, 64.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 4%|▍ | 57.6M/1.35G [00:01<00:22, 62.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▍ | 64.0M/1.35G [00:01<00:26, 52.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 5%|▌ | 72.0M/1.35G [00:01<00:28, 48.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 6%|▌ | 80.0M/1.35G [00:01<00:29, 46.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 6%|▋ | 88.0M/1.35G [00:01<00:29, 46.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 7%|▋ | 97.2M/1.35G [00:01<00:23, 56.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 8%|▊ | 106M/1.35G [00:02<00:21, 63.3MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 8%|▊ | 116M/1.35G [00:02<00:17, 74.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 9%|▉ | 124M/1.35G [00:02<00:17, 73.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|▉ | 131M/1.35G [00:02<00:18, 72.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|█ | 143M/1.35G [00:02<00:15, 85.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 11%|█▏ | 155M/1.35G [00:02<00:13, 98.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 12%|█▏ | 168M/1.35G [00:02<00:11, 107MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 13%|█▎ | 180M/1.35G [00:02<00:11, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 14%|█▍ | 192M/1.35G [00:02<00:11, 112MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 15%|█▍ | 203M/1.35G [00:03<00:11, 108MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 15%|█▌ | 213M/1.35G [00:03<00:12, 99.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 16%|█▌ | 224M/1.35G [00:03<00:17, 69.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 17%|█▋ | 232M/1.35G [00:03<00:24, 49.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 18%|█▊ | 245M/1.35G [00:03<00:18, 63.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 18%|█▊ | 253M/1.35G [00:04<00:18, 64.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 19%|█▉ | 265M/1.35G [00:04<00:14, 78.0MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|██ | 278M/1.35G [00:04<00:12, 90.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 21%|██ | 288M/1.35G [00:04<00:18, 60.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 22%|██▏ | 301M/1.35G [00:04<00:15, 73.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 22%|██▏ | 310M/1.35G [00:04<00:19, 58.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 23%|██▎ | 318M/1.35G [00:05<00:19, 57.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 24%|██▍ | 329M/1.35G [00:05<00:16, 68.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 25%|██▍ | 341M/1.35G [00:05<00:13, 80.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 26%|██▌ | 354M/1.35G [00:05<00:11, 92.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 367M/1.35G [00:05<00:10, 103MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 379M/1.35G [00:05<00:09, 110MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 28%|██▊ | 390M/1.35G [00:05<00:09, 106MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 29%|██▉ | 403M/1.35G [00:05<00:09, 112MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 30%|███ | 415M/1.35G [00:05<00:08, 118MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 31%|███ | 428M/1.35G [00:05<00:08, 121MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 32%|███▏ | 440M/1.35G [00:06<00:07, 124MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 33%|███▎ | 453M/1.35G [00:06<00:07, 126MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 34%|███▍ | 466M/1.35G [00:06<00:07, 128MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 35%|███▍ | 478M/1.35G [00:06<00:07, 129MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 36%|███▌ | 490M/1.35G [00:06<00:08, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 36%|███▋ | 502M/1.35G [00:06<00:07, 115MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 37%|███▋ | 514M/1.35G [00:06<00:08, 106MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 38%|███▊ | 526M/1.35G [00:06<00:08, 111MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 39%|███▉ | 538M/1.35G [00:06<00:07, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 40%|███▉ | 551M/1.35G [00:07<00:07, 121MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 41%|████ | 563M/1.35G [00:07<00:06, 123MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 42%|████▏ | 576M/1.35G [00:07<00:06, 126MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 43%|████▎ | 589M/1.35G [00:07<00:06, 128MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 44%|████▎ | 601M/1.35G [00:07<00:07, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 44%|████▍ | 612M/1.35G [00:07<00:08, 91.2MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 45%|████▌ | 624M/1.35G [00:07<00:10, 72.5MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 46%|████▌ | 636M/1.35G [00:08<00:09, 82.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 47%|████▋ | 645M/1.35G [00:08<00:09, 77.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 47%|████▋ | 655M/1.35G [00:08<00:09, 81.9MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 48%|████▊ | 667M/1.35G [00:08<00:07, 94.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 49%|████▉ | 680M/1.35G [00:08<00:07, 103MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 50%|█████ | 690M/1.35G [00:08<00:07, 93.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 51%|█████ | 703M/1.35G [00:08<00:06, 103MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 52%|█████▏ | 715M/1.35G [00:08<00:06, 111MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 53%|█████▎ | 728M/1.35G [00:08<00:05, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 54%|█████▎ | 741M/1.35G [00:09<00:05, 121MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 55%|█████▍ | 753M/1.35G [00:09<00:05, 124MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 56%|█████▌ | 766M/1.35G [00:09<00:05, 126MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 56%|█████▋ | 778M/1.35G [00:09<00:04, 127MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 57%|█████▋ | 790M/1.35G [00:09<00:04, 128MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 58%|█████▊ | 803M/1.35G [00:09<00:05, 120MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 59%|█████▉ | 815M/1.35G [00:09<00:04, 123MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 60%|██████ | 828M/1.35G [00:09<00:04, 126MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 61%|██████ | 840M/1.35G [00:09<00:05, 99.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 62%|██████▏ | 850M/1.35G [00:10<00:06, 85.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 62%|██████▏ | 859M/1.35G [00:10<00:08, 63.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 63%|██████▎ | 872M/1.35G [00:10<00:06, 77.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 64%|██████▍ | 885M/1.35G [00:10<00:05, 89.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 65%|██████▌ | 897M/1.35G [00:10<00:05, 99.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 66%|██████▌ | 910M/1.35G [00:10<00:04, 108MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 67%|██████▋ | 921M/1.35G [00:11<00:07, 66.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 68%|██████▊ | 933M/1.35G [00:11<00:06, 76.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 69%|██████▊ | 945M/1.35G [00:11<00:05, 86.4MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 69%|██████▉ | 957M/1.35G [00:11<00:04, 96.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 70%|███████ | 970M/1.35G [00:11<00:04, 105MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 71%|███████ | 981M/1.35G [00:11<00:05, 72.3MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 72%|███████▏ | 994M/1.35G [00:11<00:04, 83.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 73%|███████▎ | 0.98G/1.35G [00:12<00:04, 94.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 74%|███████▍ | 1.00G/1.35G [00:12<00:03, 104MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 75%|███████▍ | 1.01G/1.35G [00:12<00:03, 112MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 76%|███████▌ | 1.02G/1.35G [00:12<00:03, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 77%|███████▋ | 1.03G/1.35G [00:12<00:02, 117MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 78%|███████▊ | 1.04G/1.35G [00:12<00:02, 121MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 78%|███████▊ | 1.06G/1.35G [00:12<00:02, 124MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 79%|███████▉ | 1.07G/1.35G [00:12<00:02, 127MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|████████ | 1.08G/1.35G [00:12<00:02, 128MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 81%|████████ | 1.09G/1.35G [00:12<00:02, 129MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 82%|████████▏ | 1.11G/1.35G [00:13<00:02, 122MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 83%|████████▎ | 1.12G/1.35G [00:13<00:01, 125MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 84%|████████▍ | 1.13G/1.35G [00:13<00:01, 126MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 85%|████████▍ | 1.14G/1.35G [00:13<00:01, 127MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 86%|████████▌ | 1.15G/1.35G [00:13<00:01, 129MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 87%|████████▋ | 1.17G/1.35G [00:13<00:01, 128MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 87%|████████▋ | 1.18G/1.35G [00:13<00:01, 129MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 88%|████████▊ | 1.19G/1.35G [00:13<00:01, 130MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 89%|████████▉ | 1.20G/1.35G [00:13<00:01, 131MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|█████████ | 1.22G/1.35G [00:14<00:01, 126MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 91%|█████████ | 1.23G/1.35G [00:14<00:01, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 92%|█████████▏| 1.24G/1.35G [00:14<00:00, 119MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 93%|█████████▎| 1.25G/1.35G [00:14<00:01, 85.8MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▎| 1.26G/1.35G [00:14<00:00, 95.7MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 94%|█████████▍| 1.27G/1.35G [00:14<00:01, 79.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 95%|█████████▌| 1.29G/1.35G [00:14<00:00, 90.6MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▋| 1.30G/1.35G [00:14<00:00, 98.1MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 97%|█████████▋| 1.31G/1.35G [00:15<00:00, 101MB/s] "
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 98%|█████████▊| 1.32G/1.35G [00:15<00:00, 107MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 99%|█████████▉| 1.33G/1.35G [00:15<00:00, 114MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|█████████▉| 1.34G/1.35G [00:15<00:00, 119MB/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 1.35G/1.35G [00:15<00:00, 93.7MB/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": "2023-05-26T09:36:39.255865Z",
"iopub.status.busy": "2023-05-26T09:36:39.255097Z",
"iopub.status.idle": "2023-05-26T09:36:39.260950Z",
"shell.execute_reply": "2023-05-26T09:36:39.260274Z"
}
},
"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": "2023-05-26T09:36:39.264624Z",
"iopub.status.busy": "2023-05-26T09:36:39.264087Z",
"iopub.status.idle": "2023-05-26T09:36:39.274051Z",
"shell.execute_reply": "2023-05-26T09:36:39.273379Z"
}
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>filename</th>\n",
" <th>const_image_summary</th>\n",
" <th>3_non-deterministic summary</th>\n",
" <th>How many persons on the picture?</th>\n",
" <th>Are there any politicians in the picture?</th>\n",
" <th>Does the picture show something from medicine?</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>data/102730_eng.png</td>\n",
" <td>two people in blue coats spray disinfection a van</td>\n",
" <td>[two people in blue robes spraying geranis, tw...</td>\n",
" <td>2</td>\n",
" <td>no</td>\n",
" <td>yes</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>data/102141_2_eng.png</td>\n",
" <td>a collage of images including a corona sign, a...</td>\n",
" <td>[the corona vaccine is being released from cor...</td>\n",
" <td>1</td>\n",
" <td>no</td>\n",
" <td>yes</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</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 man in a white shirt is on a news desk, a m...</td>\n",
" <td>1</td>\n",
" <td>yes</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/102141_2_eng.png a collage of images including a corona sign, a... \n",
"2 data/106349S_por.png a man wearing a face mask while looking at a c... \n",
"\n",
" 3_non-deterministic summary \n",
"0 [two people in blue robes spraying geranis, tw... \\\n",
"1 [the corona vaccine is being released from cor... \n",
"2 [a man in a white shirt is on a news desk, a m... \n",
"\n",
" How many persons on the picture? Are there any politicians in the picture? \n",
"0 2 no \\\n",
"1 1 no \n",
"2 1 yes \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": "2023-05-26T09:36:39.277136Z",
"iopub.status.busy": "2023-05-26T09:36:39.276608Z",
"iopub.status.idle": "2023-05-26T09:36:39.281540Z",
"shell.execute_reply": "2023-05-26T09:36:39.280961Z"
}
},
"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