Hugging Face's logo

osanseviero
/
diffusion_pusht

Robotics
Transformers
Safetensors
Inference Endpoints
Model card Files Community
diffusion_pusht
File size: 2,458 Bytes 
8cc09ae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
device: cuda
use_amp: false
seed: 100000
dataset_repo_id: lerobot/pusht
training:
  offline_steps: 200000
  online_steps: 0
  online_steps_between_rollouts: 1
  online_sampling_ratio: 0.5
  online_env_seed: ???
  eval_freq: 10000
  save_freq: 20000
  log_freq: 250
  save_model: true
  batch_size: 64
  grad_clip_norm: 10
  lr: 0.0001
  lr_scheduler: cosine
  lr_warmup_steps: 500
  adam_betas:
  - 0.95
  - 0.999
  adam_eps: 1.0e-08
  adam_weight_decay: 1.0e-06
  delta_timestamps:
    observation.image:
    - -0.1
    - 0.0
    observation.state:
    - -0.1
    - 0.0
    action:
    - -0.1
    - 0.0
    - 0.1
    - 0.2
    - 0.3
    - 0.4
    - 0.5
    - 0.6
    - 0.7
    - 0.8
    - 0.9
    - 1.0
    - 1.1
    - 1.2
    - 1.3
    - 1.4
  n_end_keyframes_dropped: ${policy.horizon} - ${policy.n_action_steps} - ${policy.n_obs_steps}
    + 1
eval:
  n_episodes: 50
  batch_size: 50
  use_async_envs: false
wandb:
  enable: true
  disable_artifact: true
  project: lerobot
  notes: ''
fps: 10
env:
  name: pusht
  task: PushT-v0
  image_size: 96
  state_dim: 2
  action_dim: 2
  fps: ${fps}
  episode_length: 300
  gym:
    obs_type: pixels_agent_pos
    render_mode: rgb_array
    visualization_width: 384
    visualization_height: 384
override_dataset_stats:
  observation.image:
    mean:
    - - - 0.5
    - - - 0.5
    - - - 0.5
    std:
    - - - 0.5
    - - - 0.5
    - - - 0.5
  observation.state:
    min:
    - 13.456424
    - 32.938293
    max:
    - 496.14618
    - 510.9579
  action:
    min:
    - 12.0
    - 25.0
    max:
    - 511.0
    - 511.0
policy:
  name: diffusion
  n_obs_steps: 2
  horizon: 16
  n_action_steps: 8
  input_shapes:
    observation.image:
    - 3
    - 96
    - 96
    observation.state:
    - ${env.state_dim}
  output_shapes:
    action:
    - ${env.action_dim}
  input_normalization_modes:
    observation.image: mean_std
    observation.state: min_max
  output_normalization_modes:
    action: min_max
  vision_backbone: resnet18
  crop_shape:
  - 84
  - 84
  crop_is_random: true
  pretrained_backbone_weights: null
  use_group_norm: true
  spatial_softmax_num_keypoints: 32
  down_dims:
  - 512
  - 1024
  - 2048
  kernel_size: 5
  n_groups: 8
  diffusion_step_embed_dim: 128
  use_film_scale_modulation: true
  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: 100