| { | |
| "type": "hybrid", | |
| "n_obs_steps": 1, | |
| "normalization_mapping": {}, | |
| "input_features": { | |
| "observation.images.top": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 3, | |
| 480, | |
| 640 | |
| ] | |
| }, | |
| "observation.state": { | |
| "type": "STATE", | |
| "shape": [ | |
| 14 | |
| ] | |
| } | |
| }, | |
| "output_features": { | |
| "action": { | |
| "type": "ACTION", | |
| "shape": [ | |
| 14 | |
| ] | |
| } | |
| }, | |
| "device": "cuda", | |
| "use_amp": false, | |
| "act_config": { | |
| "type": "act", | |
| "n_obs_steps": 1, | |
| "normalization_mapping": { | |
| "VISUAL": "MEAN_STD", | |
| "STATE": "MEAN_STD", | |
| "ACTION": "MEAN_STD" | |
| }, | |
| "input_features": { | |
| "observation.state": { | |
| "type": "STATE", | |
| "shape": [ | |
| 14 | |
| ] | |
| }, | |
| "observation.images.top": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 3, | |
| 480, | |
| 640 | |
| ] | |
| } | |
| }, | |
| "output_features": { | |
| "action": { | |
| "type": "ACTION", | |
| "shape": [ | |
| 14 | |
| ] | |
| } | |
| }, | |
| "device": "cuda", | |
| "use_amp": false, | |
| "chunk_size": 16, | |
| "n_action_steps": 16, | |
| "vision_backbone": "resnet18", | |
| "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1", | |
| "replace_final_stride_with_dilation": false, | |
| "pre_norm": false, | |
| "dim_model": 512, | |
| "n_heads": 8, | |
| "dim_feedforward": 3200, | |
| "feedforward_activation": "relu", | |
| "n_encoder_layers": 4, | |
| "n_decoder_layers": 1, | |
| "use_vae": true, | |
| "latent_dim": 32, | |
| "n_vae_encoder_layers": 4, | |
| "temporal_ensemble_coeff": null, | |
| "dropout": 0.1, | |
| "kl_weight": 10.0, | |
| "smoothness_weight": 0.0, | |
| "smoothness_type": "velocity", | |
| "optimizer_lr": 1e-05, | |
| "optimizer_weight_decay": 0.0001, | |
| "optimizer_lr_backbone": 1e-05 | |
| }, | |
| "diffusion_config": { | |
| "type": "diffusion", | |
| "n_obs_steps": 1, | |
| "normalization_mapping": { | |
| "VISUAL": "MEAN_STD", | |
| "STATE": "MEAN_STD", | |
| "ACTION": "MEAN_STD" | |
| }, | |
| "input_features": { | |
| "observation.state": { | |
| "type": "STATE", | |
| "shape": [ | |
| 14 | |
| ] | |
| }, | |
| "observation.images.top": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 3, | |
| 480, | |
| 640 | |
| ] | |
| } | |
| }, | |
| "output_features": { | |
| "action": { | |
| "type": "ACTION", | |
| "shape": [ | |
| 14 | |
| ] | |
| } | |
| }, | |
| "device": "cuda", | |
| "use_amp": false, | |
| "horizon": 16, | |
| "n_action_steps": 1, | |
| "drop_n_last_frames": 7, | |
| "vision_backbone": "resnet18", | |
| "crop_shape": null, | |
| "crop_is_random": true, | |
| "pretrained_backbone_weights": null, | |
| "use_group_norm": true, | |
| "spatial_softmax_num_keypoints": 32, | |
| "use_separate_rgb_encoder_per_camera": false, | |
| "down_dims": [ | |
| 64, | |
| 128, | |
| 256 | |
| ], | |
| "kernel_size": 3, | |
| "n_groups": 8, | |
| "diffusion_step_embed_dim": 128, | |
| "use_film_scale_modulation": true, | |
| "noise_scheduler_type": "DDIM", | |
| "num_train_timesteps": 100, | |
| "beta_schedule": "squaredcos_cap_v2", | |
| "beta_start": 0.0001, | |
| "beta_end": 0.02, | |
| "prediction_type": "epsilon", | |
| "clip_sample": true, | |
| "clip_sample_range": 1.0, | |
| "num_inference_steps": 100, | |
| "do_mask_loss_for_padding": false, | |
| "optimizer_lr": 0.0001, | |
| "optimizer_betas": [ | |
| 0.95, | |
| 0.999 | |
| ], | |
| "optimizer_eps": 1e-08, | |
| "optimizer_weight_decay": 1e-06, | |
| "scheduler_name": "cosine", | |
| "scheduler_warmup_steps": 500 | |
| }, | |
| "act_loss_weight": 1.0, | |
| "diffusion_loss_weight": 0.1, | |
| "num_keyframes_to_refine": 5, | |
| "refinement_window_past": 2, | |
| "refinement_window_future": 5, | |
| "action_blend_alpha": 0.9 | |
| } |