-
Notifications
You must be signed in to change notification settings - Fork 0
/
02-fake_real_dataset.py
65 lines (53 loc) · 2.24 KB
/
02-fake_real_dataset.py
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
import json
import os
from distutils.dir_util import copy_tree
import shutil
import numpy as np
import splitfolders
base_path = '.\\train_sample_videos\\'
dataset_path = '.\\prepared_dataset\\'
print('Creating Directory: ' + dataset_path)
os.makedirs(dataset_path, exist_ok=True)
tmp_fake_path = '.\\tmp_fake_faces'
print('Creating Directory: ' + tmp_fake_path)
os.makedirs(tmp_fake_path, exist_ok=True)
def get_filename_only(file_path):
file_basename = os.path.basename(file_path)
filename_only = file_basename.split('.')[0]
return filename_only
with open(os.path.join(base_path, 'metadata.json')) as metadata_json:
metadata = json.load(metadata_json)
print(len(metadata))
real_path = os.path.join(dataset_path, 'real')
print('Creating Directory: ' + real_path)
os.makedirs(real_path, exist_ok=True)
fake_path = os.path.join(dataset_path, 'fake')
print('Creating Directory: ' + fake_path)
os.makedirs(fake_path, exist_ok=True)
for filename in metadata.keys():
print(filename)
print(metadata[filename]['label'])
tmp_path = os.path.join(os.path.join(base_path, get_filename_only(filename)), 'faces')
print(tmp_path)
if os.path.exists(tmp_path):
if metadata[filename]['label'] == 'REAL':
print('Copying to :' + real_path)
copy_tree(tmp_path, real_path)
elif metadata[filename]['label'] == 'FAKE':
print('Copying to :' + tmp_fake_path)
copy_tree(tmp_path, tmp_fake_path)
else:
print('Ignored..')
all_real_faces = [f for f in os.listdir(real_path) if os.path.isfile(os.path.join(real_path, f))]
print('Total Number of Real faces: ', len(all_real_faces))
all_fake_faces = [f for f in os.listdir(tmp_fake_path) if os.path.isfile(os.path.join(tmp_fake_path, f))]
print('Total Number of Fake faces: ', len(all_fake_faces))
random_faces = np.random.choice(all_fake_faces, len(all_real_faces), replace=True)
for fname in random_faces:
src = os.path.join(tmp_fake_path, fname)
dst = os.path.join(fake_path, fname)
shutil.copyfile(src, dst)
print('Down-sampling Done!')
# Split into Train/ Val/ Test folders
splitfolders.ratio(dataset_path, output='split_dataset', seed=1377, ratio=(.8, .1, .1)) # default values
print('Train/ Val/ Test Split Done!')