68 lines
1.6 KiB
YAML
68 lines
1.6 KiB
YAML
|
model:
|
||
|
|
base_learning_rate: 1.0e-06
|
||
|
|
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
||
|
|
params:
|
||
|
|
linear_start: 0.0015
|
||
|
|
linear_end: 0.0205
|
||
|
|
log_every_t: 100
|
||
|
|
timesteps: 1000
|
||
|
|
loss_type: l1
|
||
|
|
first_stage_key: image
|
||
|
|
cond_stage_key: masked_image
|
||
|
|
image_size: 64
|
||
|
|
channels: 3
|
||
|
|
concat_mode: true
|
||
|
|
monitor: val/loss
|
||
|
|
scheduler_config:
|
||
|
|
target: ldm.lr_scheduler.LambdaWarmUpCosineScheduler
|
||
|
|
params:
|
||
|
|
verbosity_interval: 0
|
||
|
|
warm_up_steps: 1000
|
||
|
|
max_decay_steps: 50000
|
||
|
|
lr_start: 0.001
|
||
|
|
lr_max: 0.1
|
||
|
|
lr_min: 0.0001
|
||
|
|
unet_config:
|
||
|
|
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
||
|
|
params:
|
||
|
|
image_size: 64
|
||
|
|
in_channels: 7
|
||
|
|
out_channels: 3
|
||
|
|
model_channels: 256
|
||
|
|
attention_resolutions:
|
||
|
|
- 8
|
||
|
|
- 4
|
||
|
|
- 2
|
||
|
|
num_res_blocks: 2
|
||
|
|
channel_mult:
|
||
|
|
- 1
|
||
|
|
- 2
|
||
|
|
- 3
|
||
|
|
- 4
|
||
|
|
num_heads: 8
|
||
|
|
resblock_updown: true
|
||
|
|
first_stage_config:
|
||
|
|
target: ldm.models.autoencoder.VQModelInterface
|
||
|
|
params:
|
||
|
|
embed_dim: 3
|
||
|
|
n_embed: 8192
|
||
|
|
monitor: val/rec_loss
|
||
|
|
ddconfig:
|
||
|
|
attn_type: none
|
||
|
|
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
|
||
|
|
lossconfig:
|
||
|
|
target: ldm.modules.losses.contperceptual.DummyLoss
|
||
|
|
cond_stage_config: __is_first_stage__
|