| |
| |
| checkpoint: ./model.pt |
| mixed_precision: bf16 |
| eval_num_inference_steps: 10 |
| data: |
| train: |
| shape_meta: |
| images: |
| - key: cam_high |
| raw_shape: |
| - 3 |
| - 480 |
| - 640 |
| shape: |
| - 3 |
| - 240 |
| - 320 |
| - key: cam_left_wrist |
| raw_shape: |
| - 3 |
| - 480 |
| - 640 |
| shape: |
| - 3 |
| - 240 |
| - 320 |
| - key: cam_right_wrist |
| raw_shape: |
| - 3 |
| - 480 |
| - 640 |
| shape: |
| - 3 |
| - 240 |
| - 320 |
| action: |
| - key: default |
| raw_shape: 14 |
| shape: 14 |
| state: |
| - key: default |
| raw_shape: 14 |
| shape: 14 |
| num_frames: 81 |
| past_obs_size: 48 |
| action_chunk: 32 |
| action_video_freq_ratio: 4 |
| video_size: |
| - 384 |
| - 320 |
| concat_multi_camera: robotwin |
| context_len: 128 |
| processor: |
| _target_: fastwam.datasets.lerobot.processors.fastwam_processor.FastWAMProcessor |
| shape_meta: |
| images: |
| - key: cam_high |
| raw_shape: |
| - 3 |
| - 480 |
| - 640 |
| shape: |
| - 3 |
| - 240 |
| - 320 |
| - key: cam_left_wrist |
| raw_shape: |
| - 3 |
| - 480 |
| - 640 |
| shape: |
| - 3 |
| - 240 |
| - 320 |
| - key: cam_right_wrist |
| raw_shape: |
| - 3 |
| - 480 |
| - 640 |
| shape: |
| - 3 |
| - 240 |
| - 320 |
| action: |
| - key: default |
| raw_shape: 14 |
| shape: 14 |
| state: |
| - key: default |
| raw_shape: 14 |
| shape: 14 |
| num_obs_steps: 81 |
| num_output_cameras: 3 |
| action_output_dim: 14 |
| proprio_output_dim: 14 |
| action_state_transforms: null |
| use_stepwise_action_norm: false |
| norm_default_mode: z-score |
| norm_exception_mode: null |
| action_state_merger: |
| _target_: fastwam.datasets.lerobot.transforms.action_state_merger.ConcatLeftAlign |
| val_transforms: |
| - _target_: fastwam.datasets.lerobot.transforms.image.ToTensor |
| - _target_: torchvision.transforms.Resize |
| size: |
| - 240 |
| - 320 |
| pretrained_norm_stats: ./dataset_stats.json |
| model: |
| _target_: fastwam.runtime.create_arwam |
| model_id: Wan-AI/Wan2.2-TI2V-5B |
| tokenizer_model_id: Wan-AI/Wan2.1-T2V-1.3B |
| tokenizer_max_len: 128 |
| load_text_encoder: false |
| proprio_dim: 14 |
| redirect_common_files: false |
| mot_checkpoint_mixed_attn: true |
| skip_dit_load_from_pretrain: true |
| longlive_video_weights: null |
| action_dit_pretrained_path: null |
| arwam_num_frame_per_block: 1 |
| arwam_local_attn_size: -1 |
| arwam_sink_size: 0 |
| arwam_past_obs_size: 48 |
| arwam_num_imagine_frames: 2 |
| arwam_imagine_sigma: 0.9 |
| arwam_imagine_infer_steps: 4 |
| video_dit_config: |
| has_image_input: false |
| patch_size: |
| - 1 |
| - 2 |
| - 2 |
| in_dim: 48 |
| hidden_dim: 3072 |
| ffn_dim: 14336 |
| freq_dim: 256 |
| text_dim: 4096 |
| out_dim: 48 |
| num_heads: 24 |
| attn_head_dim: 128 |
| num_layers: 30 |
| eps: 1.0e-06 |
| seperated_timestep: true |
| require_clip_embedding: false |
| require_vae_embedding: false |
| fuse_vae_embedding_in_latents: true |
| use_gradient_checkpointing: true |
| video_attention_mask_mode: per_frame_causal |
| action_conditioned: false |
| action_dim: 14 |
| action_group_causal_mask_mode: group_diagonal |
| action_dit_config: |
| action_dim: 14 |
| hidden_dim: 1024 |
| ffn_dim: 4096 |
| num_heads: 24 |
| attn_head_dim: 128 |
| num_layers: 30 |
| text_dim: 4096 |
| freq_dim: 256 |
| eps: 1.0e-06 |
| use_gradient_checkpointing: true |
| video_scheduler: |
| train_shift: 5.0 |
| infer_shift: 5.0 |
| num_train_timesteps: 1000 |
| action_scheduler: |
| train_shift: 5.0 |
| infer_shift: 5.0 |
| num_train_timesteps: 1000 |
| skip_video_dit_load_from_pretrain: true |
| skip_action_dit_load_from_pretrain: true |
|
|
