Instructions to use maximellerbach/folding_lingbot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use maximellerbach/folding_lingbot with LeRobot:
- Notebooks
- Google Colab
- Kaggle
File size: 3,513 Bytes
0dd11e7 3cd18b0 0dd11e7 1e15115 0dd11e7 337c8b3 0dd11e7 1e15115 0dd11e7 1e15115 0dd11e7 1e15115 0dd11e7 1e15115 0dd11e7 1e15115 0dd11e7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 | {
"type": "lingbot_va",
"n_obs_steps": 1,
"input_features": {
"observation.images.cam_high": {
"type": "VISUAL",
"shape": [
3,
256,
256
]
},
"observation.images.cam_left_wrist": {
"type": "VISUAL",
"shape": [
3,
256,
256
]
},
"observation.images.cam_right_wrist": {
"type": "VISUAL",
"shape": [
3,
256,
256
]
}
},
"output_features": {
"action": {
"type": "ACTION",
"shape": [
16
]
}
},
"device": "cuda",
"use_amp": false,
"use_peft": false,
"push_to_hub": true,
"repo_id": "maximellerbach/folding_lingbot",
"private": null,
"tags": null,
"license": null,
"pretrained_path": "/fsx/maxime_ellerbach/robots/runs/folding-tshirt/outputs/train/lingbot_absolute_22372322/checkpoints/last/pretrained_model",
"pretrained_revision": null,
"patch_size": [
1,
2,
2
],
"num_attention_heads": 24,
"attention_head_dim": 128,
"in_channels": 48,
"out_channels": 48,
"action_dim": 30,
"text_dim": 4096,
"freq_dim": 256,
"ffn_dim": 14336,
"num_layers": 30,
"cross_attn_norm": true,
"eps": 1e-06,
"rope_max_seq_len": 1024,
"attn_mode": "flex",
"wan_pretrained_path": "robbyant/lingbot-va-base",
"dtype": "bfloat16",
"text_encoder_device": "cuda",
"obs_cam_keys": [
"observation.images.cam_high",
"observation.images.cam_left_wrist",
"observation.images.cam_right_wrist"
],
"image_hflip": false,
"camera_layout": "width_concat",
"height": 224,
"width": 224,
"action_per_frame": 16,
"frame_chunk_size": 2,
"attn_window": 72,
"num_inference_steps": 25,
"video_exec_step": -1,
"action_num_inference_steps": 50,
"guidance_scale": 5.0,
"action_guidance_scale": 1.0,
"snr_shift": 5.0,
"action_snr_shift": 1.0,
"max_sequence_length": 512,
"used_action_channel_ids": [
21,
22,
23,
24,
25,
26,
27,
29,
14,
15,
16,
17,
18,
19,
20,
28
],
"use_relative_actions": true,
"relative_exclude_joints": [
"gripper"
],
"action_feature_names": [
"right_joint_1.pos",
"right_joint_2.pos",
"right_joint_3.pos",
"right_joint_4.pos",
"right_joint_5.pos",
"right_joint_6.pos",
"right_joint_7.pos",
"right_gripper.pos",
"left_joint_1.pos",
"left_joint_2.pos",
"left_joint_3.pos",
"left_joint_4.pos",
"left_joint_5.pos",
"left_joint_6.pos",
"left_joint_7.pos",
"left_gripper.pos"
],
"save_predicted_video": false,
"normalization_mapping": {
"VISUAL": "IDENTITY",
"STATE": "IDENTITY",
"ACTION": "QUANTILES"
},
"optimizer_lr": 2e-05,
"optimizer_betas": [
0.9,
0.95
],
"optimizer_eps": 1e-08,
"optimizer_weight_decay": 0.0001,
"optimizer_grad_clip_norm": 1.0,
"scheduler_warmup_steps": 1000,
"scheduler_type": "constant_with_warmup",
"action_noisy_cond_prob": 0.2
} |