Hugging Face's logo

kywch
/
act_mimicgen_stack_d0

Robotics
Safetensors
lerobot
act
model_hub_mixin
pytorch_model_hub_mixin
Model card Files Community
act_mimicgen_stack_d0
File size: 2,996 Bytes 
8140ee5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
 
resume: false
device: cuda
use_amp: false
seed: 1000
dataset_repo_id: kywch/mimicgen_stack_d0
video_backend: pyav
training:
  offline_steps: 100000
  num_workers: 4
  batch_size: 64
  eval_freq: 10000
  log_freq: 200
  save_checkpoint: true
  save_freq: 20000
  online_steps: 0
  online_rollout_n_episodes: 1
  online_rollout_batch_size: 1
  online_steps_between_rollouts: 1
  online_sampling_ratio: 0.5
  online_env_seed: null
  online_buffer_capacity: null
  online_buffer_seed_size: 0
  do_online_rollout_async: false
  image_transforms:
    enable: false
    max_num_transforms: 3
    random_order: false
    brightness:
      weight: 1
      min_max:
      - 0.8
      - 1.2
    contrast:
      weight: 1
      min_max:
      - 0.8
      - 1.2
    saturation:
      weight: 1
      min_max:
      - 0.5
      - 1.5
    hue:
      weight: 1
      min_max:
      - -0.05
      - 0.05
    sharpness:
      weight: 1
      min_max:
      - 0.8
      - 1.2
  lr: 5.0e-05
  lr_backbone: 1.0e-05
  weight_decay: 0.0001
  grad_clip_norm: 10
  delta_timestamps:
    action:
    - 0.0
    - 0.05
    - 0.1
    - 0.15
    - 0.2
    - 0.25
    - 0.3
    - 0.35
    - 0.4
    - 0.45
    - 0.5
    - 0.55
    - 0.6
    - 0.65
    - 0.7
    - 0.75
    - 0.8
    - 0.85
    - 0.9
    - 0.95
eval:
  n_episodes: 20
  batch_size: 20
  use_async_envs: true
wandb:
  enable: true
  disable_artifact: true
  project: lerobot
  notes: ''
fps: 20
env:
  name: mimicgen
  task: Stack_D0
  state_dim: 9
  action_dim: 7
  episode_length: 200
  meta: stack_d0_env.json
  image_keys:
  - agentview
  - robot0_eye_in_hand
  state_keys:
  - robot0_eef_pos
  - robot0_eef_quat
  - robot0_gripper_qpos
  use_delta_action: false
  use_highres_image_obs: true
override_dataset_stats:
  observation.images.agentview:
    mean:
    - - - 0.485
    - - - 0.456
    - - - 0.406
    std:
    - - - 0.229
    - - - 0.224
    - - - 0.225
  observation.images.robot0_eye_in_hand:
    mean:
    - - - 0.485
    - - - 0.456
    - - - 0.406
    std:
    - - - 0.229
    - - - 0.224
    - - - 0.225
policy:
  name: act
  n_obs_steps: 1
  chunk_size: 20
  n_action_steps: 20
  input_shapes:
    observation.images.agentview:
    - 3
    - 256
    - 256
    observation.images.robot0_eye_in_hand:
    - 3
    - 256
    - 256
    observation.state:
    - ${env.state_dim}
  output_shapes:
    action:
    - ${env.action_dim}
  input_normalization_modes:
    observation.images.agentview: mean_std
    observation.images.robot0_eye_in_hand: mean_std
    observation.state: mean_std
  output_normalization_modes:
    action: mean_std
  vision_backbone: resnet18
  pretrained_backbone_weights: ResNet18_Weights.IMAGENET1K_V1
  replace_final_stride_with_dilation: false
  pre_norm: false
  dim_model: 512
  n_heads: 8
  dim_feedforward: 3200
  feedforward_activation: relu
  n_encoder_layers: 4
  n_decoder_layers: 1
  use_vae: true
  latent_dim: 32
  n_vae_encoder_layers: 4
  temporal_ensemble_momentum: null
  dropout: 0.1
  kl_weight: 10.0