{ "dataset": { "repo_id": "the-future-dev/RopeFlatten", "root": null, "episodes": null, "image_transforms": { "enable": false, "max_num_transforms": 3, "random_order": false, "tfs": { "brightness": { "weight": 1.0, "type": "ColorJitter", "kwargs": { "brightness": [ 0.8, 1.2 ] } }, "contrast": { "weight": 1.0, "type": "ColorJitter", "kwargs": { "contrast": [ 0.8, 1.2 ] } }, "saturation": { "weight": 1.0, "type": "ColorJitter", "kwargs": { "saturation": [ 0.5, 1.5 ] } }, "hue": { "weight": 1.0, "type": "ColorJitter", "kwargs": { "hue": [ -0.05, 0.05 ] } }, "sharpness": { "weight": 1.0, "type": "SharpnessJitter", "kwargs": { "sharpness": [ 0.5, 1.5 ] } } } }, "revision": null, "use_imagenet_stats": true, "video_backend": "pyav", "streaming": false }, "env": { "type": "softgym", "task": "RopeFlatten-v0", "fps": 10, "features": { "action": { "type": "ACTION", "shape": [ 8 ] }, "state": { "type": "STATE", "shape": [ 6 ] }, "image": { "type": "VISUAL", "shape": [ 128, 128, 3 ] } }, "features_map": { "action": "action", "state": "observation.state", "image": "observation.image", "environment_state": "observation.environment_state" }, "max_parallel_tasks": 1, "disable_env_checker": true, "episode_length": 300, "obs_type": "pixels_agent_pos", "render_mode": "rgb_array", "observation_height": 128, "observation_width": 128, "visualization_width": 384, "visualization_height": 384, "env_kwargs": {} }, "policy": { "type": "diffusion", "n_obs_steps": 2, "input_features": { "observation.image": { "type": "VISUAL", "shape": [ 3, 128, 128 ] }, "observation.state": { "type": "STATE", "shape": [ 6 ] }, "observation.environment_state": { "type": "ENV", "shape": [ 30 ] } }, "output_features": { "action": { "type": "ACTION", "shape": [ 8 ] } }, "device": "cuda", "use_amp": false, "push_to_hub": true, "repo_id": "the-future-dev/pusht_diffusion_image", "private": null, "tags": null, "license": null, "pretrained_path": null, "horizon": 16, "n_action_steps": 8, "normalization_mapping": { "VISUAL": "MEAN_STD", "STATE": "MIN_MAX", "ACTION": "MIN_MAX" }, "drop_n_last_frames": 7, "vision_backbone": "resnet18", "crop_shape": [ 84, 84 ], "crop_is_random": true, "pretrained_backbone_weights": null, "use_group_norm": true, "spatial_softmax_num_keypoints": 32, "use_separate_rgb_encoder_per_camera": false, "state_encoder": "mlp", "state_encoder_out_dim": 64, "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, "privileged": null, "privileged_dropout_p": 0.0, "add_rgb_prediction_head": false, "priv_encoder_output_shape": 0, "rgb_encoder_checkpoint": null, "pretrained_unet_path": null, "pretrained_state_encoder_path": null }, "output_dir": "outputs/train/ropeflatten_diffusion_image", "job_name": "ropeflatten_diffusion_image", "resume": false, "seed": 100000, "num_workers": 4, "batch_size": 8, "steps": 100, "eval_freq": 0, "log_freq": 200, "save_checkpoint": true, "save_freq": 25000, "use_policy_training_preset": true, "optimizer": { "type": "adam", "lr": 0.0001, "weight_decay": 1e-06, "grad_clip_norm": 10.0, "betas": [ 0.95, 0.999 ], "eps": 1e-08 }, "scheduler": { "type": "diffuser", "num_warmup_steps": 500, "name": "cosine" }, "eval": { "n_episodes": 50, "batch_size": 50, "use_async_envs": false }, "wandb": { "enable": true, "disable_artifact": false, "project": "lerobot-pusht", "entity": null, "notes": null, "run_id": "ed24n4jl", "mode": null } }