69 lines
1.5 KiB
YAML
69 lines
1.5 KiB
YAML
model:
|
|
base_learning_rate: 0.0001
|
|
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
|
params:
|
|
linear_start: 0.0015
|
|
linear_end: 0.0195
|
|
num_timesteps_cond: 1
|
|
log_every_t: 200
|
|
timesteps: 1000
|
|
first_stage_key: image
|
|
cond_stage_key: class_label
|
|
image_size: 64
|
|
channels: 3
|
|
cond_stage_trainable: true
|
|
conditioning_key: crossattn
|
|
monitor: val/loss
|
|
use_ema: False
|
|
|
|
unet_config:
|
|
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
|
params:
|
|
image_size: 64
|
|
in_channels: 3
|
|
out_channels: 3
|
|
model_channels: 192
|
|
attention_resolutions:
|
|
- 8
|
|
- 4
|
|
- 2
|
|
num_res_blocks: 2
|
|
channel_mult:
|
|
- 1
|
|
- 2
|
|
- 3
|
|
- 5
|
|
num_heads: 1
|
|
use_spatial_transformer: true
|
|
transformer_depth: 1
|
|
context_dim: 512
|
|
|
|
first_stage_config:
|
|
target: ldm.models.autoencoder.VQModelInterface
|
|
params:
|
|
embed_dim: 3
|
|
n_embed: 8192
|
|
ddconfig:
|
|
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: torch.nn.Identity
|
|
|
|
cond_stage_config:
|
|
target: ldm.modules.encoders.modules.ClassEmbedder
|
|
params:
|
|
n_classes: 1001
|
|
embed_dim: 512
|
|
key: class_label
|