-
Notifications
You must be signed in to change notification settings - Fork 121
/
v2-finetune_text_T_512.yaml
247 lines (223 loc) · 6.82 KB
/
v2-finetune_text_T_512.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
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
sf: 4
model:
base_learning_rate: 5.0e-05
target: ldm.models.diffusion.ddpm.LatentDiffusionSRTextWT
params:
# parameterization: "v"
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: image
cond_stage_key: caption
image_size: 512
channels: 4
cond_stage_trainable: False # Note: different from the one we trained before
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False
# for training only
# ckpt_path: /mnt/lustre/jywang/code/stable_diffmodels/v2-1_512-ema-pruned.ckpt
unfrozen_diff: False
random_size: False
time_replace: 1000
use_usm: True
#P2 weighting, we do not use in final version
p2_gamma: ~
p2_k: ~
# ignore_keys: []
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModelDualcondV2
params:
image_size: 32 # unused
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_head_channels: 64
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: 1
context_dim: 1024
use_checkpoint: False
legacy: False
semb_channels: 256
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
# for training only
# ckpt_path: /mnt/lustre/jywang/code/stable_diffmodels/v2-1_512-ema-pruned.ckpt
embed_dim: 4
monitor: val/rec_loss
ddconfig:
double_z: true
z_channels: 4
resolution: 512
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"
structcond_stage_config:
target: ldm.modules.diffusionmodules.openaimodel.EncoderUNetModelWT
params:
image_size: 96
in_channels: 4
model_channels: 256
out_channels: 256
num_res_blocks: 2
attention_resolutions: [ 4, 2, 1 ]
dropout: 0
channel_mult: [ 1, 1, 2, 2 ]
conv_resample: True
dims: 2
use_checkpoint: False
use_fp16: False
num_heads: 4
num_head_channels: -1
num_heads_upsample: -1
use_scale_shift_norm: False
resblock_updown: False
use_new_attention_order: False
degradation:
# the first degradation process
resize_prob: [0.2, 0.7, 0.1] # up, down, keep
resize_range: [0.3, 1.5]
gaussian_noise_prob: 0.5
noise_range: [1, 15]
poisson_scale_range: [0.05, 2.0]
gray_noise_prob: 0.4
jpeg_range: [60, 95]
# the second degradation process
second_blur_prob: 0.5
resize_prob2: [0.3, 0.4, 0.3] # up, down, keep
resize_range2: [0.6, 1.2]
gaussian_noise_prob2: 0.5
noise_range2: [1, 12]
poisson_scale_range2: [0.05, 1.0]
gray_noise_prob2: 0.4
jpeg_range2: [60, 100]
gt_size: 512
no_degradation_prob: 0.01
data:
target: main.DataModuleFromConfig
params:
batch_size: 6
num_workers: 6
wrap: false
train:
target: basicsr.data.realesrgan_dataset.RealESRGANDataset
params:
queue_size: 180
gt_path: ['/mnt/lustre/share/jywang/dataset/DIV8K/train_HR/', '/mnt/lustre/share/jywang/dataset/df2k_ost/GT/']
face_gt_path: '/mnt/lustre/share/jywang/dataset/FFHQ/1024/'
num_face: 10000
crop_size: 512
io_backend:
type: disk
blur_kernel_size: 21
kernel_list: ['iso', 'aniso', 'generalized_iso', 'generalized_aniso', 'plateau_iso', 'plateau_aniso']
kernel_prob: [0.45, 0.25, 0.12, 0.03, 0.12, 0.03]
sinc_prob: 0.1
blur_sigma: [0.2, 1.5]
betag_range: [0.5, 2.0]
betap_range: [1, 1.5]
blur_kernel_size2: 11
kernel_list2: ['iso', 'aniso', 'generalized_iso', 'generalized_aniso', 'plateau_iso', 'plateau_aniso']
kernel_prob2: [0.45, 0.25, 0.12, 0.03, 0.12, 0.03]
sinc_prob2: 0.1
blur_sigma2: [0.2, 1.0]
betag_range2: [0.5, 2.0]
betap_range2: [1, 1.5]
final_sinc_prob: 0.8
gt_size: 512
use_hflip: True
use_rot: False
validation:
target: basicsr.data.realesrgan_dataset.RealESRGANDataset
params:
gt_path: /mnt/lustre/share/jywang/dataset/ImageSR/DIV2K/DIV2K_train_HR/
crop_size: 512
io_backend:
type: disk
blur_kernel_size: 21
kernel_list: ['iso', 'aniso', 'generalized_iso', 'generalized_aniso', 'plateau_iso', 'plateau_aniso']
kernel_prob: [0.45, 0.25, 0.12, 0.03, 0.12, 0.03]
sinc_prob: 0.1
blur_sigma: [0.2, 1.5]
betag_range: [0.5, 2.0]
betap_range: [1, 1.5]
blur_kernel_size2: 11
kernel_list2: ['iso', 'aniso', 'generalized_iso', 'generalized_aniso', 'plateau_iso', 'plateau_aniso']
kernel_prob2: [0.45, 0.25, 0.12, 0.03, 0.12, 0.03]
sinc_prob2: 0.1
blur_sigma2: [0.2, 1.0]
betag_range2: [0.5, 2.0]
betap_range2: [1, 1.5]
final_sinc_prob: 0.8
gt_size: 512
use_hflip: True
use_rot: False
test_data:
target: main.DataModuleFromConfig
params:
batch_size: 1
num_workers: 6
wrap: false
test:
target: basicsr.data.realesrgan_dataset.RealESRGANDataset
params:
gt_path: /mnt/lustre/share/jywang/dataset/ImageSR/DIV2K/DIV2K_train_HR/
crop_size: 512
io_backend:
type: disk
blur_kernel_size: 21
kernel_list: ['iso', 'aniso', 'generalized_iso', 'generalized_aniso', 'plateau_iso', 'plateau_aniso']
kernel_prob: [0.45, 0.25, 0.12, 0.03, 0.12, 0.03]
sinc_prob: 0.1
blur_sigma: [0.2, 1.5]
betag_range: [0.5, 2.0]
betap_range: [1, 1.5]
blur_kernel_size2: 11
kernel_list2: ['iso', 'aniso', 'generalized_iso', 'generalized_aniso', 'plateau_iso', 'plateau_aniso']
kernel_prob2: [0.45, 0.25, 0.12, 0.03, 0.12, 0.03]
sinc_prob2: 0.1
blur_sigma2: [0.2, 1.0]
betag_range2: [0.5, 2.0]
betap_range2: [1, 1.5]
final_sinc_prob: 0.8
gt_size: 512
use_hflip: True
use_rot: False
lightning:
modelcheckpoint:
params:
every_n_train_steps: 1500
callbacks:
image_logger:
target: main.ImageLogger
params:
batch_frequency: 1500
max_images: 4
increase_log_steps: False
trainer:
benchmark: True
max_steps: 800000
accumulate_grad_batches: 4