configs/cifar10_ve_ct_ema.py [49:75]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    model.normalization = "GroupNorm"
    model.nonlinearity = "swish"
    model.nf = 128
    model.ch_mult = (2, 2, 2)
    model.num_res_blocks = 4
    model.attn_resolutions = (16,)
    model.resamp_with_conv = True
    model.conditional = True
    model.fir = True
    model.fir_kernel = [1, 3, 3, 1]
    model.skip_rescale = True
    model.resblock_type = "biggan"
    model.progressive = "none"
    model.progressive_input = "residual"
    model.progressive_combine = "sum"
    model.attention_type = "ddpm"
    model.init_scale = 0.0
    model.fourier_scale = 16
    model.conv_size = 3
    model.rho = 7.0
    model.data_std = 0.5
    model.num_scales = 18
    model.dropout = 0.0

    # optimization
    optim = config.optim
    optim.weight_decay = 0.0
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



configs/cifar10_ve_progressive_distillation.py [47:73]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    model.normalization = "GroupNorm"
    model.nonlinearity = "swish"
    model.nf = 128
    model.ch_mult = (2, 2, 2)
    model.num_res_blocks = 4
    model.attn_resolutions = (16,)
    model.resamp_with_conv = True
    model.conditional = True
    model.fir = True
    model.fir_kernel = [1, 3, 3, 1]
    model.skip_rescale = True
    model.resblock_type = "biggan"
    model.progressive = "none"
    model.progressive_input = "residual"
    model.progressive_combine = "sum"
    model.attention_type = "ddpm"
    model.init_scale = 0.0
    model.fourier_scale = 16
    model.conv_size = 3
    model.rho = 7.0
    model.data_std = 0.5
    model.num_scales = 18
    model.dropout = 0.0

    # optimization
    optim = config.optim
    optim.weight_decay = 0.0
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -