{ "type": "diffusion", "n_obs_steps": 1, "normalization_mapping": { "VISUAL": "IDENTITY", "STATE": "MIN_MAX", "ACTION": "MIN_MAX" }, "input_features": { "observation.state": { "type": "STATE", "shape": [ 24 ] }, "observation.images.rgb": { "type": "VISUAL", "shape": [ 3, 240, 424 ] }, "observation.images.depth": { "type": "VISUAL", "shape": [ 1, 240, 424 ] } }, "output_features": { "action": { "type": "ACTION", "shape": [ 21 ] } }, "device": "cuda", "use_amp": false, "push_to_hub": true, "repo_id": "kelvinzhaozg/diffusion_digit3a_hardware_box_pickup_rgbd_tiny", "private": null, "tags": null, "license": null, "horizon": 64, "n_action_steps": 32, "per_feature_normalization_overrides": { "observation.images.rgb": "IDENTITY", "observation.images.depth": "MEAN_STD" }, "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, "use_depth_as_channel": true, "use_depth_only": false, "rgbd_pretrained_backbone_weights": "r3m", "norm_rgb": true, "norm_depth": false, "down_dims": [ 128, 256, 512 ], "kernel_size": 5, "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": "sample", "clip_sample": true, "clip_sample_range": 1.0, "num_inference_steps": null, "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 }