{ "type": "diffusion_dino", "n_obs_steps": 3, "input_features": { "observation.image": { "type": "VISUAL", "shape": [ 3, 224, 224 ] }, "observation.goal": { "type": "VISUAL", "shape": [ 3, 224, 224 ] }, "observation.state": { "type": "STATE", "shape": [ 4 ] } }, "output_features": { "action": { "type": "ACTION", "shape": [ 2 ] } }, "device": "cuda", "use_amp": false, "push_to_hub": true, "repo_id": "ozgraslan/diffusion_dino_pointmaze_v1_4", "private": null, "tags": null, "license": null, "pretrained_path": null, "horizon": 32, "n_action_steps": 25, "use_goal_conditioning": true, "normalization_mapping": { "VISUAL": "MEAN_STD", "STATE": "MEAN_STD", "ACTION": "MEAN_STD" }, "drop_n_last_frames": 5, "vision_backbone": "facebookresearch/dinov2", "crop_shape": [ 224, 224 ], "crop_is_random": true, "pretrained_backbone_weights": "dinov2_vits14", "output_key": "x_norm_patchtokens", "use_group_norm": false, "spatial_softmax_num_keypoints": 32, "use_separate_rgb_encoder_per_camera": false, "down_dims": [ 512, 1024, 2048 ], "kernel_size": 5, "n_groups": 8, "diffusion_step_embed_dim": 128, "use_film_scale_modulation": true, "noise_scheduler_type": "DDPM", "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": 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 }