Instructions to use K-vr/bimanual_diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use K-vr/bimanual_diffusion with LeRobot:
- Notebooks
- Google Colab
- Kaggle
File size: 3,321 Bytes
5e23da1 | 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 | {
"type": "diffusion",
"n_obs_steps": 2,
"input_features": {
"observation.state": {
"type": "STATE",
"shape": [
12
]
},
"observation.images.left_cam_left": {
"type": "VISUAL",
"shape": [
3,
480,
640
]
},
"observation.images.left_cam_scene": {
"type": "VISUAL",
"shape": [
3,
480,
640
]
},
"observation.images.right_cam_right": {
"type": "VISUAL",
"shape": [
3,
480,
640
]
},
"observation.images.cam_realsense_rgb": {
"type": "VISUAL",
"shape": [
3,
480,
640
]
},
"observation.depth.cam_realsense": {
"type": "STATE",
"shape": [
480,
640
]
},
"observation.images.cam_realsense_ir_left": {
"type": "VISUAL",
"shape": [
3,
480,
640
]
},
"observation.images.cam_realsense_ir_right": {
"type": "VISUAL",
"shape": [
3,
480,
640
]
},
"observation.camera_intrinsics.realsense": {
"type": "STATE",
"shape": [
5
]
}
},
"output_features": {
"action": {
"type": "ACTION",
"shape": [
12
]
}
},
"device": "cuda",
"use_amp": true,
"use_peft": false,
"push_to_hub": true,
"repo_id": "K-vr/bimanual_diffusion",
"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",
"resize_shape": [
96,
96
],
"crop_ratio": 1.0,
"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": false,
"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
} |