AMMICO/notebooks/image_summary.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Image summary and visual question answering"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebooks shows some preliminary work on Image Captioning and Visual question answering with lavis. It is mainly meant to explore its capabilities and to decide on future research directions. We package our code into a `misinformation` package that is imported here:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import misinformation\n",
    "from misinformation import utils as mutils\n",
    "from misinformation import display as mdisplay\n",
    "import misinformation.summary as sm"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Set an image path as input file path."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "images = mutils.find_files(\n",
    "    path=\"../misinformation/test/data/\",\n",
    "    limit=1000,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "mydict = mutils.initialize_dict(images[0:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "mydict"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create captions for images and directly write to csv"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here you can choose between two models: \"base\" or \"large\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "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": null,
   "metadata": {
    "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",
    "    )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "Convert the dictionary of dictionarys into a dictionary with lists:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "outdict = mutils.append_data_to_dict(mydict)\n",
    "df = mutils.dump_df(outdict)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Check the dataframe:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "df.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Write the csv file:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.to_csv(\"./data_out.csv\")"
   ]
  },
  {
   "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": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "mdisplay.explore_analysis(mydict, identify=\"summary\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Generate answers to free-form questions about images written in natural language. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Set the list of questions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "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",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for key in mydict:\n",
    "    mydict[key] = sm.SummaryDetector(mydict[key]).analyse_questions(list_of_questions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "mdisplay.explore_analysis(mydict, identify=\"summary\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Convert the dictionary of dictionarys into a dictionary with lists:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "outdict2 = mutils.append_data_to_dict(mydict)\n",
    "df2 = mutils.dump_df(outdict2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df2.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "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
}