| { | |
| "type": "flow_matching_dit", | |
| "n_obs_steps": 1, | |
| "input_features": { | |
| "observation.images.head_rgb": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 3, | |
| 240, | |
| 424 | |
| ] | |
| }, | |
| "observation.state": { | |
| "type": "STATE", | |
| "shape": [ | |
| 21 | |
| ] | |
| } | |
| }, | |
| "output_features": { | |
| "action": { | |
| "type": "ACTION", | |
| "shape": [ | |
| 18 | |
| ] | |
| } | |
| }, | |
| "device": "cuda", | |
| "use_amp": false, | |
| "push_to_hub": true, | |
| "repo_id": "kelvinzhaozg/flow_matching_dit_t1_stack_cube_isaaclab", | |
| "private": null, | |
| "tags": null, | |
| "license": null, | |
| "pretrained_path": null, | |
| "horizon": 64, | |
| "n_action_steps": 32, | |
| "normalization_mapping": { | |
| "VISUAL": "MEAN_STD", | |
| "STATE": "MIN_MAX", | |
| "ACTION": "MIN_MAX" | |
| }, | |
| "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": true, | |
| "hidden_size": 1536, | |
| "num_layers": 12, | |
| "num_attention_heads": 12, | |
| "attention_dropout": 0.1, | |
| "patch_size": 2, | |
| "use_adaln_zero": true, | |
| "cross_attention_dim": 512, | |
| "add_cross_attention": true, | |
| "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, | |
| "flow_matching_type": "CondOT", | |
| "num_integration_steps": 50, | |
| "fm_time_embed_dim": 256, | |
| "fm_min_period": 0.004, | |
| "fm_max_period": 4.0, | |
| "ode_solver_method": "midpoint" | |
| } |