93 lines
2.0 KiB
YAML
93 lines
2.0 KiB
YAML
model:
|
|
base_learning_rate: 5.0e-05
|
|
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
|
params:
|
|
linear_start: 0.0015
|
|
linear_end: 0.0155
|
|
num_timesteps_cond: 1
|
|
log_every_t: 200
|
|
timesteps: 1000
|
|
loss_type: l1
|
|
first_stage_key: image
|
|
cond_stage_key: image
|
|
image_size: 32
|
|
channels: 4
|
|
cond_stage_trainable: false
|
|
concat_mode: false
|
|
scale_by_std: true
|
|
monitor: val/loss_simple_ema
|
|
scheduler_config:
|
|
target: ldm.lr_scheduler.LambdaLinearScheduler
|
|
params:
|
|
warm_up_steps:
|
|
- 10000
|
|
cycle_lengths:
|
|
- 10000000000000
|
|
f_start:
|
|
- 1.0e-06
|
|
f_max:
|
|
- 1.0
|
|
f_min:
|
|
- 1.0
|
|
unet_config:
|
|
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
|
params:
|
|
image_size: 32
|
|
in_channels: 4
|
|
out_channels: 4
|
|
model_channels: 192
|
|
attention_resolutions:
|
|
- 1
|
|
- 2
|
|
- 4
|
|
- 8
|
|
num_res_blocks: 2
|
|
channel_mult:
|
|
- 1
|
|
- 2
|
|
- 2
|
|
- 4
|
|
- 4
|
|
num_heads: 8
|
|
use_scale_shift_norm: true
|
|
resblock_updown: true
|
|
first_stage_config:
|
|
target: ldm.models.autoencoder.AutoencoderKL
|
|
params:
|
|
embed_dim: 4
|
|
monitor: val/rec_loss
|
|
ddconfig:
|
|
double_z: true
|
|
z_channels: 4
|
|
resolution: 256
|
|
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: '__is_unconditional__'
|
|
|
|
data:
|
|
target: main.DataModuleFromConfig
|
|
params:
|
|
batch_size: 96
|
|
num_workers: 5
|
|
wrap: false
|
|
train:
|
|
target: ldm.data.lsun.LSUNChurchesTrain
|
|
params:
|
|
size: 256
|
|
validation:
|
|
target: ldm.data.lsun.LSUNChurchesValidation
|
|
params:
|
|
size: 256
|