1 files changed, 165 insertions, 0 deletions
diff --git a/megapixels/notebooks/datasets/ffhq/prepare_flickr_meta.ipynb b/megapixels/notebooks/datasets/ffhq/prepare_flickr_meta.ipynb
new file mode 100644
index 00000000..3d571aff
--- /dev/null
+++ b/megapixels/notebooks/datasets/ffhq/prepare_flickr_meta.ipynb
@@ -0,0 +1,165 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Download FFHQ Images\n",
+    "\n",
+    "- https://github.com/NVlabs/ffhq-dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%reload_ext autoreload\n",
+    "%autoreload 2\n",
+    "\n",
+    "import os\n",
+    "from os.path import join\n",
+    "from glob import glob\n",
+    "from pathlib import Path\n",
+    "import requests\n",
+    "import json\n",
+    "\n",
+    "from tqdm import tqdm_notebook as tqdm\n",
+    "import pandas as pd\n",
+    "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "import sys\n",
+    "sys.path.append('/work/megapixels_dev/megapixels')\n",
+    "from app.utils import file_utils"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# load JSON\n",
+    "fp_in = '/data_store/datasets/people/ffhq/ffhq-dataset-v1.json'\n",
+    "fp_out = '/data_store/datasets/people/ffhq/research/flickr_api_urls.csv'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(fp_in, 'r') as fp:\n",
+    "  ffhq_items = json.load(fp)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "217c694742e8408d871c3b41183676fb",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(IntProgress(value=0, max=70000), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "results = []\n",
+    "# get photos urls\n",
+    "for idx, ffhq_item in tqdm(ffhq_items.items()):\n",
+    "  url = ffhq_item.get('metadata').get('photo_url')\n",
+    "  photo_id = Path(url).stem\n",
+    "  obj = {'photo_id': photo_id}\n",
+    "  results.append(obj)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'photo_id': '1133484654'}"
+      ]
+     },
+     "execution_count": 34,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "results[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.DataFrame.from_dict(results)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.drop_duplicates(inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_csv(fp_out, index=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "megapixels",
+   "language": "python",
+   "name": "megapixels"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}