1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
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
}
|
