Instructions to use lambdavi/resnet_object__so101 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use lambdavi/resnet_object__so101 with LeRobot:
- Notebooks
- Google Colab
- Kaggle
| { | |
| "dataset": { | |
| "repo_id": "lambdavi/so101_pick", | |
| "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 | |
| ] | |
| } | |
| }, | |
| "affine": { | |
| "weight": 1.0, | |
| "type": "RandomAffine", | |
| "kwargs": { | |
| "degrees": [ | |
| -5.0, | |
| 5.0 | |
| ], | |
| "translate": [ | |
| 0.05, | |
| 0.05 | |
| ] | |
| } | |
| } | |
| } | |
| }, | |
| "revision": null, | |
| "use_imagenet_stats": true, | |
| "video_backend": "pyav", | |
| "return_uint8": false, | |
| "streaming": false | |
| }, | |
| "env": { | |
| "type": "so101_nexus", | |
| "task": "MuJoCoPickLift-v1", | |
| "fps": 30, | |
| "features": { | |
| "action": { | |
| "type": "ACTION", | |
| "shape": [ | |
| 6 | |
| ] | |
| }, | |
| "agent_pos": { | |
| "type": "STATE", | |
| "shape": [ | |
| 6 | |
| ] | |
| }, | |
| "pixels_overhead": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 480, | |
| 640, | |
| 3 | |
| ] | |
| }, | |
| "pixels_wrist": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 480, | |
| 640, | |
| 3 | |
| ] | |
| } | |
| }, | |
| "features_map": { | |
| "action": "action", | |
| "agent_pos": "observation.state", | |
| "pixels_overhead": "observation.images.overhead", | |
| "pixels_wrist": "observation.images.wrist" | |
| }, | |
| "max_parallel_tasks": 1, | |
| "disable_env_checker": true, | |
| "wrist_size": [ | |
| 640, | |
| 480 | |
| ], | |
| "overhead_size": [ | |
| 640, | |
| 480 | |
| ], | |
| "camera_keys": [ | |
| "overhead_camera", | |
| "wrist_camera" | |
| ], | |
| "control_mode": "pd_joint_pos", | |
| "render_mode": "rgb_array", | |
| "max_episode_steps": 400 | |
| }, | |
| "policy": { | |
| "type": "gap_policy", | |
| "n_obs_steps": 2, | |
| "input_features": { | |
| "observation.state": { | |
| "type": "STATE", | |
| "shape": [ | |
| 6 | |
| ] | |
| }, | |
| "observation.images.wrist": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 3, | |
| 480, | |
| 640 | |
| ] | |
| }, | |
| "observation.images.overhead": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 3, | |
| 480, | |
| 640 | |
| ] | |
| } | |
| }, | |
| "output_features": { | |
| "action": { | |
| "type": "ACTION", | |
| "shape": [ | |
| 6 | |
| ] | |
| } | |
| }, | |
| "device": "cuda", | |
| "use_amp": false, | |
| "use_peft": false, | |
| "push_to_hub": true, | |
| "repo_id": "lambdavi/resnet_object__so101", | |
| "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, | |
| "use_gap_vision_encoder": true, | |
| "vision_model": "lerobot_resnet18", | |
| "fusion_mode": "late", | |
| "separate_camera_weights": true, | |
| "fuse_cameras_strategy": "cat", | |
| "visual_feature_dim_per_camera": 128, | |
| "freeze_backbone": false, | |
| "pretrained_encoder": true, | |
| "pretrain_model": null, | |
| "vit_normalize_input": true, | |
| "vit_upsample_first": true, | |
| "vision_backbone": "resnet18", | |
| "resize_shape": null, | |
| "crop_ratio": 1.0, | |
| "crop_shape": null, | |
| "crop_is_random": true, | |
| "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1", | |
| "use_group_norm": false, | |
| "use_spatial_softmax": true, | |
| "spatial_softmax_strategy": "afa_object_v2", | |
| "spatial_softmax_num_keypoints": 16, | |
| "spatial_softmax_temperature": 1.0, | |
| "target_map_size": [ | |
| 32, | |
| 32 | |
| ], | |
| "use_post_adapter": false, | |
| "use_transformer": false, | |
| "transformer_num_heads": 4, | |
| "transformer_hidden_dim": 128, | |
| "transformer_num_layers": 1, | |
| "afa_num_heads": 12, | |
| "afa_object_latent_dim": 8, | |
| "afa_object_top_k_ratio": 1.0, | |
| "afa_use_2d_positional_priors": false, | |
| "post_adapter_last_act": false, | |
| "post_adapter_layer_norm": false, | |
| "use_separate_rgb_encoder_per_camera": true, | |
| "down_dims": [ | |
| 128, | |
| 256, | |
| 512 | |
| ], | |
| "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, | |
| "compile_model": false, | |
| "compile_mode": "reduce-overhead", | |
| "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 | |
| }, | |
| "reward_model": null, | |
| "output_dir": "outputs/train/gap_dino_so101_1782073006", | |
| "job_name": "gap_dino_so101_1782073006", | |
| "resume": false, | |
| "seed": 1000, | |
| "cudnn_deterministic": false, | |
| "num_workers": 1, | |
| "batch_size": 16, | |
| "prefetch_factor": 4, | |
| "persistent_workers": true, | |
| "steps": 10000, | |
| "eval_freq": 1000, | |
| "log_freq": 200, | |
| "tolerance_s": 0.0001, | |
| "save_checkpoint": true, | |
| "save_freq": 5000, | |
| "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": 10, | |
| "batch_size": 1, | |
| "use_async_envs": true | |
| }, | |
| "wandb": { | |
| "enable": true, | |
| "disable_artifact": false, | |
| "project": "legap", | |
| "entity": null, | |
| "notes": null, | |
| "run_id": "vnidczc8", | |
| "mode": null, | |
| "add_tags": true | |
| }, | |
| "peft": null, | |
| "sample_weighting": null, | |
| "rename_map": {}, | |
| "checkpoint_path": null | |
| } |