Spaces:
Sleeping
Sleeping
File size: 5,513 Bytes
7dd9869 |
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 |
import argparse
from . import gaussian_diffusion as gd
from .respace import SpacedDiffusion, space_timesteps
# from .unet import SuperResModel
NUM_CLASSES = 1000
def model_and_diffusion_defaults():
"""
Defaults for image training.
"""
return dict(
image_size=64,
num_channels=128,
num_res_blocks=2,
num_heads=4,
num_heads_upsample=-1,
attention_resolutions="16,8",
dropout=0.0,
learn_sigma=False,
class_cond=False,
diffusion_steps=1000,
noise_schedule="linear",
timestep_respacing="",
use_kl=False,
predict_xstart=False,
rescale_timesteps=True,
rescale_learned_sigmas=True,
use_checkpoint=False,
use_scale_shift_norm=True,
model_arch="trans-unet",
in_channel=8,
out_channel=8,
training_mode="emb",
vocab_size=66,
config_name="QizhiPei/biot5-base-text2mol",
experiment_mode="lm",
logits_mode=1,
)
# def sr_model_and_diffusion_defaults():
# res = model_and_diffusion_defaults()
# res["large_size"] = 256
# res["small_size"] = 64
# arg_names = inspect.getfullargspec(sr_create_model_and_diffusion)[0]
# for k in res.copy().keys():
# if k not in arg_names:
# del res[k]
# return res
# def sr_create_model_and_diffusion(
# large_size,
# small_size,
# class_cond,
# learn_sigma,
# num_channels,
# num_res_blocks,
# num_heads,
# num_heads_upsample,
# attention_resolutions,
# dropout,
# diffusion_steps,
# noise_schedule,
# timestep_respacing,
# use_kl,
# predict_xstart,
# rescale_timesteps,
# rescale_learned_sigmas,
# use_checkpoint,
# use_scale_shift_norm,
# ):
# model = sr_create_model(
# large_size,
# small_size,
# num_channels,
# num_res_blocks,
# learn_sigma=learn_sigma,
# class_cond=class_cond,
# use_checkpoint=use_checkpoint,
# attention_resolutions=attention_resolutions,
# num_heads=num_heads,
# num_heads_upsample=num_heads_upsample,
# use_scale_shift_norm=use_scale_shift_norm,
# dropout=dropout,
# )
# diffusion = create_gaussian_diffusion(
# steps=diffusion_steps,
# learn_sigma=learn_sigma,
# 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 sr_create_model(
# large_size,
# small_size,
# num_channels,
# num_res_blocks,
# learn_sigma,
# class_cond,
# use_checkpoint,
# attention_resolutions,
# num_heads,
# num_heads_upsample,
# use_scale_shift_norm,
# dropout,
# ):
# _ = small_size # hack to prevent unused variable
# if large_size == 256:
# channel_mult = (1, 1, 2, 2, 4, 4)
# elif large_size == 64:
# channel_mult = (1, 2, 3, 4)
# else:
# raise ValueError(f"unsupported large size: {large_size}")
# attention_ds = []
# for res in attention_resolutions.split(","):
# attention_ds.append(large_size // int(res))
# return SuperResModel(
# in_channels=3,
# 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,
# num_classes=(NUM_CLASSES if class_cond else None),
# use_checkpoint=use_checkpoint,
# num_heads=num_heads,
# num_heads_upsample=num_heads_upsample,
# use_scale_shift_norm=use_scale_shift_norm,
# )
def create_gaussian_diffusion(
*,
steps=1000,
learn_sigma=False,
noise_schedule="linear", # sqrt
use_kl=False,
predict_xstart=False, # True
rescale_timesteps=False, # True
rescale_learned_sigmas=False, # True
timestep_respacing="",
model_arch="conv-unet", # transformer
training_mode="emb", # e2e
):
return SpacedDiffusion(
use_timesteps=space_timesteps(2000, [2000]),
betas=gd.get_named_beta_schedule("sqrt", 2000),
model_mean_type=(gd.ModelMeanType.START_X),
model_var_type=(
(gd.ModelVarType.FIXED_LARGE)
if not learn_sigma
else gd.ModelVarType.LEARNED_RANGE
),
loss_type=gd.LossType.E2E_MSE,
rescale_timesteps=True,
model_arch="transformer",
training_mode="e2e",
)
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):
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")
|