Hugging Face's logo

iantc104
/
real_occluded_key_insertion_3arms_static_act

Robotics
Safetensors
lerobot
act
model_hub_mixin
pytorch_model_hub_mixin
Model card Files Community
real_occluded_key_insertion_3arms_static_act
File size: 3,109 Bytes 
210181e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
 
resume: false
device: cuda
use_amp: false
seed: 1000
dataset_repo_id: iantc104/gv_real_occluded_key_insertion
video_backend: pyav
training:
  offline_steps: 15625
  num_workers: 4
  batch_size: 16
  eval_freq: -1
  log_freq: 100
  save_checkpoint: true
  save_freq: 1000
  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: 2.5e-05
  lr_backbone: 1.0e-05
  weight_decay: 0.0001
  grad_clip_norm: 10
  delta_timestamps:
    action:
    - 0.0
    - 0.02
    - 0.04
    - 0.06
    - 0.08
    - 0.1
    - 0.12
    - 0.14
    - 0.16
    - 0.18
    - 0.2
    - 0.22
    - 0.24
    - 0.26
    - 0.28
    - 0.3
    - 0.32
    - 0.34
    - 0.36
    - 0.38
    - 0.4
    - 0.42
    - 0.44
    - 0.46
    - 0.48
    - 0.5
    - 0.52
    - 0.54
    - 0.56
    - 0.58
    - 0.6
    - 0.62
    - 0.64
    - 0.66
    - 0.68
    - 0.7
    - 0.72
    - 0.74
    - 0.76
    - 0.78
    - 0.8
    - 0.82
    - 0.84
    - 0.86
    - 0.88
    - 0.9
    - 0.92
    - 0.94
    - 0.96
    - 0.98
eval:
  n_episodes: 1
  batch_size: 1
  use_async_envs: true
wandb:
  enable: true
  disable_artifact: false
  project: lerobot
  notes: ''
fps: 50
env:
  name: real_world
  task: null
  state_dim: 21
  action_dim: 21
  fps: ${fps}
override_dataset_stats:
  observation.images.overhead_cam:
    mean:
    - - - 0.485
    - - - 0.456
    - - - 0.406
    std:
    - - - 0.229
    - - - 0.224
    - - - 0.225
  observation.images.worms_eye_cam:
    mean:
    - - - 0.485
    - - - 0.456
    - - - 0.406
    std:
    - - - 0.229
    - - - 0.224
    - - - 0.225
policy:
  name: act
  n_obs_steps: 1
  chunk_size: 50
  n_action_steps: 50
  input_shapes:
    observation.images.overhead_cam:
    - 3
    - 480
    - 640
    observation.images.worms_eye_cam:
    - 3
    - 480
    - 640
    observation.state:
    - ${env.state_dim}
  output_shapes:
    action:
    - ${env.action_dim}
  input_normalization_modes:
    observation.images.overhead_cam: mean_std
    observation.images.worms_eye_cam: 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_coeff: null
  dropout: 0.1
  kl_weight: 10.0