-
Notifications
You must be signed in to change notification settings - Fork 200
/
cfg.py
executable file
·284 lines (276 loc) · 11.3 KB
/
cfg.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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
# -*- coding: utf-8 -*-
# @Date : 2019-07-25
# @Author : Xinyu Gong ([email protected])
# @Link : None
# @Version : 0.0
import argparse
def str2bool(v):
if v.lower() in ('yes', 'true', 't', 'y', '1'):
return True
elif v.lower() in ('no', 'false', 'f', 'n', '0'):
return False
else:
raise argparse.ArgumentTypeError('Boolean value expected.')
def parse_args():
parser = argparse.ArgumentParser()
parser.add_argument('--world-size', default=-1, type=int,
help='number of nodes for distributed training')
parser.add_argument('--rank', default=-1, type=int,
help='node rank for distributed training')
parser.add_argument('--loca_rank', default=-1, type=int,
help='node rank for distributed training')
parser.add_argument('--dist-url', default='tcp://224.66.41.62:23456', type=str,
help='url used to set up distributed training')
parser.add_argument('--dist-backend', default='nccl', type=str,
help='distributed backend')
parser.add_argument('--seed', default=12345, type=int,
help='seed for initializing training. ')
parser.add_argument('--gpu', default=None, type=int,
help='GPU id to use.')
parser.add_argument('--multiprocessing-distributed', action='store_true',
help='Use multi-processing distributed training to launch '
'N processes per node, which has N GPUs. This is the '
'fastest way to use PyTorch for either single node or '
'multi node data parallel training')
parser.add_argument(
'--max_epoch',
type=int,
default=200,
help='number of epochs of training')
parser.add_argument(
'--max_iter',
type=int,
default=None,
help='set the max iteration number')
parser.add_argument(
'-gen_bs',
'--gen_batch_size',
type=int,
default=64,
help='size of the batches')
parser.add_argument(
'-dis_bs',
'--dis_batch_size',
type=int,
default=64,
help='size of the batches')
parser.add_argument(
'--g_lr',
type=float,
default=0.0002,
help='adam: gen learning rate')
parser.add_argument(
'--wd',
type=float,
default=0,
help='adamw: gen weight decay')
parser.add_argument(
'--d_lr',
type=float,
default=0.0002,
help='adam: disc learning rate')
parser.add_argument(
'--ctrl_lr',
type=float,
default=3.5e-4,
help='adam: ctrl learning rate')
parser.add_argument(
'--lr_decay',
action='store_true',
help='learning rate decay or not')
parser.add_argument(
'--beta1',
type=float,
default=0.0,
help='adam: decay of first order momentum of gradient')
parser.add_argument(
'--beta2',
type=float,
default=0.9,
help='adam: decay of first order momentum of gradient')
parser.add_argument(
'--num_workers',
type=int,
default=8,
help='number of cpu threads to use during batch generation')
parser.add_argument(
'--latent_dim',
type=int,
default=128,
help='dimensionality of the latent space')
parser.add_argument(
'--img_size',
type=int,
default=32,
help='size of each image dimension')
parser.add_argument(
'--channels',
type=int,
default=3,
help='number of image channels')
parser.add_argument(
'--n_critic',
type=int,
default=1,
help='number of training steps for discriminator per iter')
parser.add_argument(
'--val_freq',
type=int,
default=20,
help='interval between each validation')
parser.add_argument(
'--print_freq',
type=int,
default=100,
help='interval between each verbose')
parser.add_argument(
'--load_path',
type=str,
help='The reload model path')
parser.add_argument(
'--exp_name',
type=str,
help='The name of exp')
parser.add_argument(
'--d_spectral_norm',
type=str2bool,
default=False,
help='add spectral_norm on discriminator?')
parser.add_argument(
'--g_spectral_norm',
type=str2bool,
default=False,
help='add spectral_norm on generator?')
parser.add_argument(
'--dataset',
type=str,
default='cifar10',
help='dataset type')
parser.add_argument(
'--data_path',
type=str,
default='./data',
help='The path of data set')
parser.add_argument('--init_type', type=str, default='normal',
choices=['normal', 'orth', 'xavier_uniform', 'false'],
help='The init type')
parser.add_argument('--gf_dim', type=int, default=64,
help='The base channel num of gen')
parser.add_argument('--df_dim', type=int, default=64,
help='The base channel num of disc')
parser.add_argument(
'--gen_model',
type=str,
help='path of gen model')
parser.add_argument(
'--dis_model',
type=str,
help='path of dis model')
parser.add_argument(
'--controller',
type=str,
default='controller',
help='path of controller')
parser.add_argument('--eval_batch_size', type=int, default=100)
parser.add_argument('--num_eval_imgs', type=int, default=50000)
parser.add_argument(
'--bottom_width',
type=int,
default=4,
help="the base resolution of the GAN")
parser.add_argument('--random_seed', type=int, default=12345)
# search
parser.add_argument('--shared_epoch', type=int, default=15,
help='the number of epoch to train the shared gan at each search iteration')
parser.add_argument('--grow_step1', type=int, default=25,
help='which iteration to grow the image size from 8 to 16')
parser.add_argument('--grow_step2', type=int, default=55,
help='which iteration to grow the image size from 16 to 32')
parser.add_argument('--max_search_iter', type=int, default=90,
help='max search iterations of this algorithm')
parser.add_argument('--ctrl_step', type=int, default=30,
help='number of steps to train the controller at each search iteration')
parser.add_argument('--ctrl_sample_batch', type=int, default=1,
help='sample size of controller of each step')
parser.add_argument('--hid_size', type=int, default=100,
help='the size of hidden vector')
parser.add_argument('--baseline_decay', type=float, default=0.9,
help='baseline decay rate in RL')
parser.add_argument('--rl_num_eval_img', type=int, default=5000,
help='number of images to be sampled in order to get the reward')
parser.add_argument('--num_candidate', type=int, default=10,
help='number of candidate architectures to be sampled')
parser.add_argument('--topk', type=int, default=5,
help='preserve topk models architectures after each stage' )
parser.add_argument('--entropy_coeff', type=float, default=1e-3,
help='to encourage the exploration')
parser.add_argument('--dynamic_reset_threshold', type=float, default=1e-3,
help='var threshold')
parser.add_argument('--dynamic_reset_window', type=int, default=500,
help='the window size')
parser.add_argument('--arch', nargs='+', type=int,
help='the vector of a discovered architecture')
parser.add_argument('--optimizer', type=str, default="adam",
help='optimizer')
parser.add_argument('--loss', type=str, default="hinge",
help='loss function')
parser.add_argument('--n_classes', type=int, default=0,
help='classes')
parser.add_argument('--phi', type=float, default=1,
help='wgan-gp phi')
parser.add_argument('--grow_steps', nargs='+', type=int,
help='the vector of a discovered architecture')
parser.add_argument('--D_downsample', type=str, default="avg",
help='downsampling type')
parser.add_argument('--fade_in', type=float, default=1,
help='fade in step')
parser.add_argument('--d_depth', type=int, default=7,
help='Discriminator Depth')
parser.add_argument('--g_depth', type=str, default="5,4,2",
help='Generator Depth')
parser.add_argument('--g_norm', type=str, default="ln",
help='Generator Normalization')
parser.add_argument('--d_norm', type=str, default="ln",
help='Discriminator Normalization')
parser.add_argument('--g_act', type=str, default="gelu",
help='Generator activation Layer')
parser.add_argument('--d_act', type=str, default="gelu",
help='Discriminator activation layer')
parser.add_argument('--patch_size', type=int, default=4,
help='Discriminator Depth')
parser.add_argument('--fid_stat', type=str, default="None",
help='Discriminator Depth')
parser.add_argument('--diff_aug', type=str, default="None",
help='differentiable augmentation type')
parser.add_argument('--accumulated_times', type=int, default=1,
help='gradient accumulation')
parser.add_argument('--g_accumulated_times', type=int, default=1,
help='gradient accumulation')
parser.add_argument('--num_landmarks', type=int, default=64,
help='number of landmarks')
parser.add_argument('--d_heads', type=int, default=4,
help='number of heads')
parser.add_argument('--dropout', type=float, default=0.,
help='dropout ratio')
parser.add_argument('--ema', type=float, default=0.995,
help='ema')
parser.add_argument('--ema_warmup', type=float, default=0.,
help='ema warm up')
parser.add_argument('--ema_kimg', type=int, default=500,
help='ema thousand images')
parser.add_argument('--latent_norm',action='store_true',
help='latent vector normalization')
parser.add_argument('--ministd',action='store_true',
help='mini batch std')
parser.add_argument('--g_mlp', type=int, default=4,
help='generator mlp ratio')
parser.add_argument('--d_mlp', type=int, default=4,
help='discriminator mlp ratio')
parser.add_argument('--g_window_size', type=int, default=8,
help='generator mlp ratio')
parser.add_argument('--d_window_size', type=int, default=8,
help='discriminator mlp ratio')
parser.add_argument('--show', action='store_true',
help='show')
opt = parser.parse_args()
return opt