audio-diffusion / ldm_autoencoder_kl.yaml
teticio's picture
log audio to tensorboard
3e8b723
raw
history blame
669 Bytes
model:
base_learning_rate: 4.5e-6
target: ldm.models.autoencoder.AutoencoderKL
params:
monitor: "val/rec_loss"
embed_dim: 3
lossconfig:
target: ldm.modules.losses.LPIPSWithDiscriminator
params:
disc_start: 50001
kl_weight: 0.000001
disc_weight: 0.5
ddconfig:
double_z: True
z_channels: 3
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult: [ 1,2,4 ] # num_down = len(ch_mult)-1
num_res_blocks: 2
attn_resolutions: [ ]
dropout: 0.0
lightning:
trainer:
benchmark: True
accumulate_grad_batches: 24
accelerator: gpu
devices: 1