diff --git a/photocat.ipynb b/photocat.ipynb
new file mode 100644
index 0000000..c37cdf8
--- /dev/null
+++ b/photocat.ipynb
@@ -0,0 +1,133 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Automatic photo categorization\n",
+    "\n",
+    "\n",
+    "Goals:\n",
+    "  - Categorize photos into semantically similar groups.\n",
+    "  - Mark similar photos for removal.\n",
+    "\n",
+    "\n",
+    "## Table of contents\n",
+    " 1. [Features](#features)\n",
+    " 2. [Clustering](#clustering)\n",
+    " 3. [Deduplication](#deduplication)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "%matplotlib inline\n",
+    "\n",
+    "from tqdm import tqdm\n",
+    "#from tqdm.notebook import tqdm\n",
+    "\n",
+    "from toolz import compose\n",
+    "from toolz.curried import map, filter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from photocat import fs, photo, group\n",
+    "\n",
+    "INPUT_DIR = 'data/photos'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<a name=\"features\"></a>\n",
+    "## Features\n",
+    "\n",
+    "Extract features from EXIF data and YOLOv3 output."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def show_photos(photos, n_row, n_col, size=4):\n",
+    "    _, axs = plt.subplots(n_row, n_col, figsize=(n_col*size, n_row*size))\n",
+    "    axs = axs.flatten()\n",
+    "    for p, ax in zip(photos, axs):\n",
+    "        ax.imshow(p.thumbnail)\n",
+    "    plt.show()\n",
+    "\n",
+    "photos = compose(\n",
+    "    list,\n",
+    "    tqdm,\n",
+    "    map(lambda f: photo.Photo(f)),\n",
+    "    fs.list_images\n",
+    ")(INPUT_DIR)\n",
+    "\n",
+    "show_photos(photos[0:24], 6, 4)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<a name=\"clustering\"></a>\n",
+    "## Clustering\n",
+    "\n",
+    "Normalize features and cluster with DBSCAN."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<a name=\"deduplication\"></a>\n",
+    "## Deduplication\n",
+    "\n",
+    "Use eucledian distance between outputs of topmost YOLOv3 layers as a metric for photo similarity."
+   ]
+  },
+  {
+   "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": "3.9.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}