46 lines
955 B
YAML
46 lines
955 B
YAML
|
model:
|
||
|
base_learning_rate: 4.5e-06
|
||
|
target: ldm.models.autoencoder.VQModel
|
||
|
params:
|
||
|
embed_dim: 3
|
||
|
n_embed: 8192
|
||
|
monitor: val/rec_loss
|
||
|
|
||
|
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: taming.modules.losses.vqperceptual.VQLPIPSWithDiscriminator
|
||
|
params:
|
||
|
disc_conditional: false
|
||
|
disc_in_channels: 3
|
||
|
disc_start: 0
|
||
|
disc_weight: 0.75
|
||
|
codebook_weight: 1.0
|
||
|
|
||
|
data:
|
||
|
target: main.DataModuleFromConfig
|
||
|
params:
|
||
|
batch_size: 8
|
||
|
num_workers: 16
|
||
|
wrap: true
|
||
|
train:
|
||
|
target: ldm.data.openimages.FullOpenImagesTrain
|
||
|
params:
|
||
|
crop_size: 256
|
||
|
validation:
|
||
|
target: ldm.data.openimages.FullOpenImagesValidation
|
||
|
params:
|
||
|
crop_size: 256
|