-
Notifications
You must be signed in to change notification settings - Fork 35
/
bicubic_swinunet_bicubic256.yaml
126 lines (122 loc) · 2.73 KB
/
bicubic_swinunet_bicubic256.yaml
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
model:
target: models.unet.UNetModelSwin
ckpt_path: ~
params:
image_size: 64
in_channels: 3
model_channels: 160
out_channels: 3
attention_resolutions: [64,32,16,8]
dropout: 0
channel_mult: [1, 2, 2, 4]
num_res_blocks: [2, 2, 2, 2]
conv_resample: True
dims: 2
use_fp16: False
num_head_channels: 32
use_scale_shift_norm: True
resblock_updown: False
swin_depth: 2
swin_embed_dim: 192
window_size: 8
mlp_ratio: 4
cond_lq: True
lq_size: 64
diffusion:
target: models.script_util.create_gaussian_diffusion
params:
sf: 4
schedule_name: exponential
schedule_kwargs:
power: 0.3
etas_end: 0.99
steps: 15
min_noise_level: 0.04
kappa: 1.0
weighted_mse: False
predict_type: xstart
timestep_respacing: ~
scale_factor: 1.0
normalize_input: True
latent_flag: True
autoencoder:
target: ldm.models.autoencoder.VQModelTorch
ckpt_path: weights/autoencoder/autoencoder_vq_f4.pth
use_fp16: True
params:
embed_dim: 3
n_embed: 8192
ddconfig:
double_z: False
z_channels: 3
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
padding_mode: zeros
data:
train:
type: bicubic
params:
sf: 4
dir_path: ~
txt_file_path: [
'/mnt/lustre/zsyue/disk/data/ImageNet/train/image_path_all.txt',
'/mnt/lustre/zsyue/disk/data/FFHQ/files_txt/ffhq256.txt',
]
mean: 0.5
std: 0.5
hflip: True
rotation: False
resize_back: False
length: ~
need_path: False
im_exts: ['png', 'jpg', 'jpeg', 'JPEG', 'bmp']
recursive: False
use_sharp: False
rescale_gt: True
gt_size: 256
val:
type: bicubic
params:
sf: 4
dir_path: testdata/Bicubicx4/gt
txt_file_path: ~
mean: 0.5
std: 0.5
hflip: False
rotation: False
resize_back: False
length: 32
need_path: False
im_exts: ['png', 'jpg', 'jpeg', 'JPEG', 'bmp']
recursive: False
use_sharp: False
rescale_gt: False
gt_size: 256
matlab_mode: True
train:
lr: 5e-5
batch: [64, 8] # batchsize for training and validation
use_fp16: False
microbatch: 16
seed: 123456
global_seeding: False
prefetch_factor: 4
num_workers: 8
ema_rate: 0.999
iterations: 500000
milestones: [5000, 500000]
weight_decay: 0
save_freq: 10000
val_freq: 10000
log_freq: [1000, 5000, 1] #[training loss, training images, val images]
save_images: True # save the images of tensorboard logging
use_ema_val: True