forked from ml5js/training-styletransfer
-
Notifications
You must be signed in to change notification settings - Fork 8
/
style.py
179 lines (151 loc) · 6.65 KB
/
style.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
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
166
167
168
169
170
171
172
173
174
175
176
177
178
179
from __future__ import print_function
import sys, os, pdb
sys.path.insert(0, 'src')
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
import numpy as np, scipy.misc
from optimize import optimize
from argparse import ArgumentParser
from utils import save_img, get_img, exists, list_files
import evaluate
from dump_checkpoints import dump_checkpoints
CONTENT_WEIGHT = 7.5e0
STYLE_WEIGHT = 1e2
TV_WEIGHT = 2e2
LEARNING_RATE = 1e-3
NUM_EPOCHS = 2
CHECKPOINT_DIR = 'checkpoints'
CHECKPOINT_ITERATIONS = 2000
VGG_PATH = 'data/imagenet-vgg-verydeep-19.mat'
TRAIN_PATH = 'data/train2014'
MODEL_PATH = 'models'
BATCH_SIZE = 4
DEVICE = '/gpu:0'
FRAC_GPU = 1
def build_parser():
parser = ArgumentParser()
parser.add_argument('--model-dir', type=str,
dest='model_dir', help='dir to save ml5 models in',
metavar='MODELS_DIR', default=MODEL_PATH)
parser.add_argument('--checkpoint-dir', type=str,
dest='checkpoint_dir', help='dir to save checkpoint in',
metavar='CHECKPOINT_DIR', required=True)
parser.add_argument('--style', type=str,
dest='style', help='style image path',
metavar='STYLE', required=True)
parser.add_argument('--train-path', type=str,
dest='train_path', help='path to training images folder',
metavar='TRAIN_PATH', default=TRAIN_PATH)
parser.add_argument('--test', type=str,
dest='test', help='test image path',
metavar='TEST', default=False)
parser.add_argument('--test-dir', type=str,
dest='test_dir', help='test image save dir',
metavar='TEST_DIR', default=False)
parser.add_argument('--slow', dest='slow', action='store_true',
help='gatys\' approach (for debugging, not supported)',
default=False)
parser.add_argument('--epochs', type=int,
dest='epochs', help='num epochs',
metavar='EPOCHS', default=NUM_EPOCHS)
parser.add_argument('--batch-size', type=int,
dest='batch_size', help='batch size',
metavar='BATCH_SIZE', default=BATCH_SIZE)
parser.add_argument('--checkpoint-iterations', type=int,
dest='checkpoint_iterations', help='checkpoint frequency',
metavar='CHECKPOINT_ITERATIONS',
default=CHECKPOINT_ITERATIONS)
parser.add_argument('--vgg-path', type=str,
dest='vgg_path',
help='path to VGG19 network (default %(default)s)',
metavar='VGG_PATH', default=VGG_PATH)
parser.add_argument('--content-weight', type=float,
dest='content_weight',
help='content weight (default %(default)s)',
metavar='CONTENT_WEIGHT', default=CONTENT_WEIGHT)
parser.add_argument('--style-weight', type=float,
dest='style_weight',
help='style weight (default %(default)s)',
metavar='STYLE_WEIGHT', default=STYLE_WEIGHT)
parser.add_argument('--tv-weight', type=float,
dest='tv_weight',
help='total variation regularization weight (default %(default)s)',
metavar='TV_WEIGHT', default=TV_WEIGHT)
parser.add_argument('--learning-rate', type=float,
dest='learning_rate',
help='learning rate (default %(default)s)',
metavar='LEARNING_RATE', default=LEARNING_RATE)
return parser
def check_opts(opts):
exists(opts.checkpoint_dir, "checkpoint dir not found!")
exists(opts.style, "style path not found!")
exists(opts.train_path, "train path not found!")
if opts.test or opts.test_dir:
exists(opts.test, "test img not found!")
exists(opts.test_dir, "test directory not found!")
exists(opts.vgg_path, "vgg network data not found!")
assert opts.epochs > 0
assert opts.batch_size > 0
assert opts.checkpoint_iterations > 0
assert os.path.exists(opts.vgg_path)
assert opts.content_weight >= 0
assert opts.style_weight >= 0
assert opts.tv_weight >= 0
assert opts.learning_rate >= 0
def _get_files(img_dir):
files = list_files(img_dir)
return [os.path.join(img_dir,x) for x in files]
def main():
print('ml5.js Style Transfer Training!')
print('Note: This traning will take a couple of hours.')
parser = build_parser()
options = parser.parse_args()
check_opts(options)
style_target = get_img(options.style)
if not options.slow:
content_targets = _get_files(options.train_path)
elif options.test:
content_targets = [options.test]
kwargs = {
"slow":options.slow,
"epochs":options.epochs,
"print_iterations":options.checkpoint_iterations,
"batch_size":options.batch_size,
"save_path":os.path.join(options.checkpoint_dir,'fns.ckpt'),
"learning_rate":options.learning_rate,
}
if options.slow:
if options.epochs < 10:
kwargs['epochs'] = 1000
if options.learning_rate < 1:
kwargs['learning_rate'] = 1e1
args = [
content_targets,
style_target,
options.content_weight,
options.style_weight,
options.tv_weight,
options.vgg_path
]
print('Training is starting!...')
for preds, losses, i, epoch in optimize(*args, **kwargs):
style_loss, content_loss, tv_loss, loss = losses
print('Epoch %d, Iteration: %d, Loss: %s' % (epoch, i, loss))
to_print = (style_loss, content_loss, tv_loss)
print('style: %s, content:%s, tv: %s' % to_print)
if options.test:
assert options.test_dir != False
preds_path = '%s/%s_%s.png' % (options.test_dir,epoch,i)
if not options.slow:
ckpt_dir = os.path.dirname(options.checkpoint_dir)
evaluate.ffwd_to_img(options.test,preds_path,
options.checkpoint_dir)
else:
save_img(preds_path, img)
ckpt_dir = options.checkpoint_dir
cmd_text = 'python evaluate.py --checkpoint %s ...' % ckpt_dir
print("Training complete. For evaluation:\n `%s`" % cmd_text)
print('Converting model to ml5js')
dump_checkpoints(kwargs['save_path'], options.model_dir)
print('Done! Checkpoint saved. Visit https://ml5js.org/docs/StyleTransfer for more information')
if __name__ == '__main__':
main()