Upload 3 files

config.yaml

@@ -0,0 +1,63 @@
+debug: false
+seed: 42
+
+training:
+  num_train_epochs: 10
+  max_train_steps: null
+  gradient_accumulation_steps: 1
+  only_train_attention_layers: true
+  gradient_checkpointing: true
+  resume_path: 1053553/checkpoint-last
+  use_EMA: true
+
+model:
+  modality: depth
+  pretrained_path: GonzaloMG/marigold-e2e-ft-depth
+  checkpoint_path: null
+  enable_xformers: true
+  unet_positional_encoding: RoPE
+  vae_use_RoPE: true
+  metric_depth: false
+  log_scale: true
+
+data:
+  data_path: /home/pf/pfstaff/data
+  dataset: PanoInfinigen
+  scenes: both
+  batch_size: 1
+  use_data_augmentation: true
+
+optimization:
+  learning_rate: 3e-4
+  lr_exp_warmup_steps: 0.03
+  adam_beta1: 0.9
+  adam_beta2: 0.999
+  adam_weight_decay: 1e-2
+  adam_epsilon: 1e-8
+  clip_grad_norm: true
+  max_grad_norm: 1.0
+
+loss:
+  l1_loss_weight: 1.0
+  grad_loss_weight: 20.0
+  normals_consistency_loss_weight: 0.1
+  invalid_mask_weight: 0.0
+
+validation:
+  run_validation: true
+  run_tiny_validation: true
+  tiny_val_frequency: 200
+
+logging:
+  tracker_project_name: Pager
+  model_save_path: checkpoints/
+  model_save_frequency: 1
+  loss_report_frequency: 1
+  img_report_frequency: 200
+  report_to: wandb
+
+  tensorboard:
+    log_path: logs
+
+  wandb:
+    run_name: 1053554

unet/config.json

@@ -0,0 +1,74 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.30.2",
+  "_name_or_path": "GonzaloMG/marigold-e2e-ft-depth",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 1024,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 8,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 96,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_RoPE": true,
+  "use_linear_projection": true
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2555cac1658c9a2c4909c821fb84d3963cd2e93d12e6acb20fd2eab4c0aa80aa
+size 3463772592