Spaces:
Runtime error
Runtime error
File size: 7,623 Bytes
bd366ed |
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 |
import argparse
import inspect
from . import gaussian_diffusion as gd
from .respace import SpacedDiffusion, space_timesteps
from .text2im_model import (
SuperResText2ImModel,
Text2ImModel,
)
def model_and_diffusion_defaults(super_res=0):
"""
Defaults for image training.
"""
result= dict(
image_size=64,
num_channels=192,
num_res_blocks=3,
channel_mult="",
num_heads=1,
num_head_channels=64,
num_heads_upsample=-1,
attention_resolutions="32,16,8",
dropout=0.1,
text_ctx=128,
xf_width=512,
xf_layers=16,
xf_heads=8,
xf_final_ln=True,
xf_padding=True,
learn_sigma=True, ##
sigma_small=False, ##
diffusion_steps=1000,
noise_schedule="squaredcos_cap_v2",
timestep_respacing="",
use_kl=False, ##
predict_xstart=False,
rescale_timesteps=True,
rescale_learned_sigmas=True,
use_fp16=False, ##
use_scale_shift_norm=True,
resblock_updown=True,
cache_text_emb=False,
inpaint=False,
super_res=0,
mode = '',
)
if super_res:
result.update(
dict(
image_size=256,
num_res_blocks=2,
noise_schedule="linear",
super_res=super_res,
))
return result
def create_model_and_diffusion(
image_size=64,
num_channels=192,
num_res_blocks=3,
channel_mult="",
num_heads=1,
num_head_channels=64,
num_heads_upsample=-1,
attention_resolutions="32,16,8",
dropout=0.1,
text_ctx=128,
xf_width=512,
xf_layers=16,
xf_heads=8,
xf_final_ln=True,
xf_padding=True,
learn_sigma=False, ##
sigma_small=False, ##
diffusion_steps=1000,
noise_schedule="squaredcos_cap_v2",
timestep_respacing="",
use_kl=False, ##
predict_xstart=False,
rescale_timesteps=True,
rescale_learned_sigmas=True,
use_fp16=False, ##
use_scale_shift_norm=True,
resblock_updown=True,
cache_text_emb=False,
inpaint=False,
super_res=False,
mode = '',
):
model = create_model(
image_size,
num_channels,
num_res_blocks,
learn_sigma=learn_sigma,
channel_mult=channel_mult,
use_fp16=use_fp16,
attention_resolutions=attention_resolutions,
num_heads=num_heads,
num_head_channels=num_head_channels,
num_heads_upsample=num_heads_upsample,
use_scale_shift_norm=use_scale_shift_norm,
dropout=dropout,
text_ctx=text_ctx,
xf_width=xf_width,
xf_layers=xf_layers,
xf_heads=xf_heads,
xf_final_ln=xf_final_ln,
xf_padding=xf_padding,
resblock_updown=resblock_updown,
cache_text_emb=cache_text_emb,
inpaint=inpaint,
super_res=super_res,
mode = mode
)
diffusion = create_gaussian_diffusion(
steps=diffusion_steps,
learn_sigma=learn_sigma,
sigma_small=sigma_small,
noise_schedule=noise_schedule,
use_kl=use_kl,
predict_xstart=predict_xstart,
rescale_timesteps=rescale_timesteps,
rescale_learned_sigmas=rescale_learned_sigmas,
timestep_respacing=timestep_respacing,
)
return model, diffusion
def create_model(
image_size,
num_channels,
num_res_blocks,
learn_sigma,
channel_mult,
use_fp16,
attention_resolutions,
num_heads,
num_head_channels,
num_heads_upsample,
use_scale_shift_norm,
dropout,
text_ctx,
xf_width,
xf_layers,
xf_heads,
xf_final_ln,
xf_padding,
resblock_updown,
cache_text_emb,
inpaint,
super_res,
mode,
):
if channel_mult == "":
if image_size == 256:
channel_mult = (1, 1, 2, 2, 4, 4)
elif image_size == 128:
channel_mult = (1, 1, 2, 3, 4)
elif image_size == 64:
channel_mult = (1, 2, 3, 4)
else:
raise ValueError(f"unsupported image size: {image_size}")
else:
channel_mult = tuple(int(ch_mult) for ch_mult in channel_mult.split(","))
assert 2 ** (len(channel_mult) + 2) == image_size
attention_ds = []
for res in attention_resolutions.split(","):
attention_ds.append(image_size // int(res))
if super_res:
model_cls = SuperResText2ImModel
else:
model_cls = Text2ImModel
n_class = 3
if mode == 'ade20k' or mode == 'coco':
n_class = 3
elif mode == 'depth-normal' :
n_class = 6
elif mode == 'coco-edge' or mode == 'flickr-edge':
n_class = 1
return model_cls(
text_ctx=text_ctx,
xf_width=xf_width,
xf_layers=xf_layers,
xf_heads=xf_heads,
xf_final_ln=xf_final_ln,
model_channels=num_channels,
out_channels=(3 if not learn_sigma else 6),
num_res_blocks=num_res_blocks,
attention_resolutions=tuple(attention_ds),
dropout=dropout,
channel_mult=channel_mult,
use_fp16=use_fp16,
num_heads=num_heads,
num_heads_upsample=num_heads_upsample,
num_head_channels=num_head_channels,
use_scale_shift_norm=use_scale_shift_norm,
resblock_updown=resblock_updown,
in_channels=3,
n_class = n_class,
image_size = image_size,
)
def create_gaussian_diffusion(
*,
steps=1000,
learn_sigma=False,
sigma_small=False,
noise_schedule="linear",
use_kl=False,
predict_xstart=False,
rescale_timesteps=False,
rescale_learned_sigmas=False,
timestep_respacing="",
):
betas = gd.get_named_beta_schedule(noise_schedule, steps)
if use_kl:
loss_type = gd.LossType.RESCALED_KL
elif rescale_learned_sigmas:
loss_type = gd.LossType.RESCALED_MSE
else:
loss_type = gd.LossType.MSE
if not timestep_respacing:
timestep_respacing = [steps]
return SpacedDiffusion(
use_timesteps=space_timesteps(steps, timestep_respacing),
betas=betas,
model_mean_type=(
gd.ModelMeanType.EPSILON if not predict_xstart else gd.ModelMeanType.START_X
),
model_var_type=(
(
gd.ModelVarType.FIXED_LARGE
if not sigma_small
else gd.ModelVarType.FIXED_SMALL
)
if not learn_sigma
else gd.ModelVarType.LEARNED_RANGE
),
loss_type=loss_type,
rescale_timesteps=rescale_timesteps,
)
def add_dict_to_argparser(parser, default_dict):
for k, v in default_dict.items():
v_type = type(v)
if v is None:
v_type = str
elif isinstance(v, bool):
v_type = str2bool
parser.add_argument(f"--{k}", default=v, type=v_type)
def args_to_dict(args, keys=None):
if keys is None:
keys=vars(args)
return {k: getattr(args, k) for k in keys}
def str2bool(v):
"""
https://stackoverflow.com/questions/15008758/parsing-boolean-values-with-argparse
"""
if isinstance(v, bool):
return 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")
|