change for running in dtk24.04.1

Signed-off-by: lijian <lijian6@sugon.com>

configs/autoencoder/autoencoder_kl_16x16x16.yaml

-model:
-  base_learning_rate: 4.5e-6
-  target: ldm.models.autoencoder.AutoencoderKL
-  params:
-    monitor: "val/rec_loss"
-    embed_dim: 16
-    lossconfig:
-      target: ldm.modules.losses.LPIPSWithDiscriminator
-      params:
-        disc_start: 50001
-        kl_weight: 0.000001
-        disc_weight: 0.5
-
-    ddconfig:
-      double_z: True
-      z_channels: 16
-      resolution: 256
-      in_channels: 3
-      out_ch: 3
-      ch: 128
-      ch_mult: [ 1,1,2,2,4]  # num_down = len(ch_mult)-1
-      num_res_blocks: 2
-      attn_resolutions: [16]
-      dropout: 0.0
-
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/autoencoder/autoencoder_kl_32x32x4.yaml

-model:
-  base_learning_rate: 4.5e-6
-  target: ldm.models.autoencoder.AutoencoderKL
-  params:
-    monitor: "val/rec_loss"
-    embed_dim: 4
-    lossconfig:
-      target: ldm.modules.losses.LPIPSWithDiscriminator
-      params:
-        disc_start: 50001
-        kl_weight: 0.000001
-        disc_weight: 0.5
-
-    ddconfig:
-      double_z: True
-      z_channels: 4
-      resolution: 256
-      in_channels: 3
-      out_ch: 3
-      ch: 128
-      ch_mult: [ 1,2,4,4 ]  # num_down = len(ch_mult)-1
-      num_res_blocks: 2
-      attn_resolutions: [ ]
-      dropout: 0.0
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/autoencoder/autoencoder_kl_64x64x3.yaml

-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
-
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/autoencoder/autoencoder_kl_8x8x64.yaml

-model:
-  base_learning_rate: 4.5e-6
-  target: ldm.models.autoencoder.AutoencoderKL
-  params:
-    monitor: "val/rec_loss"
-    embed_dim: 64
-    lossconfig:
-      target: ldm.modules.losses.LPIPSWithDiscriminator
-      params:
-        disc_start: 50001
-        kl_weight: 0.000001
-        disc_weight: 0.5
-
-    ddconfig:
-      double_z: True
-      z_channels: 64
-      resolution: 256
-      in_channels: 3
-      out_ch: 3
-      ch: 128
-      ch_mult: [ 1,1,2,2,4,4]  # num_down = len(ch_mult)-1
-      num_res_blocks: 2
-      attn_resolutions: [16,8]
-      dropout: 0.0
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/latent-diffusion/celebahq-ldm-vq-4.yaml

-model:
-  base_learning_rate: 2.0e-06
-  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
-    image_size: 64
-    channels: 3
-    monitor: val/loss_simple_ema
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 64
-        in_channels: 3
-        out_channels: 3
-        model_channels: 224
-        attention_resolutions:
-        # note: this isn\t actually the resolution but
-        # the downsampling factor, i.e. this corresnponds to
-        # attention on spatial resolution 8,16,32, as the
-        # spatial reolution of the latents is 64 for f4
-        - 8
-        - 4
-        - 2
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 4
-        num_head_channels: 32
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        embed_dim: 3
-        n_embed: 8192
-        ckpt_path: models/first_stage_models/vq-f4/model.ckpt
-        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: __is_unconditional__
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 48
-    num_workers: 5
-    wrap: false
-    train:
-      target: taming.data.faceshq.CelebAHQTrain
-      params:
-        size: 256
-    validation:
-      target: taming.data.faceshq.CelebAHQValidation
-      params:
-        size: 256
-
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-  trainer:
-    benchmark: True
\ No newline at end of file

configs/latent-diffusion/cin-ldm-vq-f8.yaml

-model:
-  base_learning_rate: 1.0e-06
-  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: 32
-    channels: 4
-    cond_stage_trainable: true
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 32
-        in_channels: 4
-        out_channels: 4
-        model_channels: 256
-        attention_resolutions:
-        #note: this isn\t actually the resolution but
-        # the downsampling factor, i.e. this corresnponds to
-        # attention on spatial resolution 8,16,32, as the
-        # spatial reolution of the latents is 32 for f8
-        - 4
-        - 2
-        - 1
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 4
-        num_head_channels: 32
-        use_spatial_transformer: true
-        transformer_depth: 1
-        context_dim: 512
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        embed_dim: 4
-        n_embed: 16384
-        ckpt_path: configs/first_stage_models/vq-f8/model.yaml
-        ddconfig:
-          double_z: false
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions:
-          - 32
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config:
-      target: ldm.modules.encoders.modules.ClassEmbedder
-      params:
-        embed_dim: 512
-        key: class_label
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 64
-    num_workers: 12
-    wrap: false
-    train:
-      target: ldm.data.imagenet.ImageNetTrain
-      params:
-        config:
-          size: 256
-    validation:
-      target: ldm.data.imagenet.ImageNetValidation
-      params:
-        config:
-          size: 256
-
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-  trainer:
-    benchmark: True
\ No newline at end of file

configs/latent-diffusion/cin256-v2.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