Hugging Face's logo

LeTau
/
act_aloha_transfer_cube

Robotics
LeRobot
Safetensors
imitation-learning
aloha
act
Model card Files
xet
Community
LeTau commited on
Commit
2b66beb
·
verified ·
1 Parent(s): ea58ee5

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +62 -0
  2. model.safetensors +3 -0
  3. policy_postprocessor.json +32 -0
  4. policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. policy_preprocessor.json +56 -0
  6. policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  7. train_config.json +230 -0
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.images.top": {
6
+ "type": "VISUAL",
7
+ "shape": [
8
+ 3,
9
+ 480,
10
+ 640
11
+ ]
12
+ },
13
+ "observation.state": {
14
+ "type": "STATE",
15
+ "shape": [
16
+ 14
17
+ ]
18
+ }
19
+ },
20
+ "output_features": {
21
+ "action": {
22
+ "type": "ACTION",
23
+ "shape": [
24
+ 14
25
+ ]
26
+ }
27
+ },
28
+ "device": "cuda",
29
+ "use_amp": false,
30
+ "push_to_hub": false,
31
+ "repo_id": null,
32
+ "private": null,
33
+ "tags": null,
34
+ "license": null,
35
+ "pretrained_path": null,
36
+ "chunk_size": 100,
37
+ "n_action_steps": 100,
38
+ "normalization_mapping": {
39
+ "VISUAL": "MEAN_STD",
40
+ "STATE": "MEAN_STD",
41
+ "ACTION": "MEAN_STD"
42
+ },
43
+ "vision_backbone": "resnet18",
44
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
45
+ "replace_final_stride_with_dilation": false,
46
+ "pre_norm": false,
47
+ "dim_model": 512,
48
+ "n_heads": 8,
49
+ "dim_feedforward": 3200,
50
+ "feedforward_activation": "relu",
51
+ "n_encoder_layers": 4,
52
+ "n_decoder_layers": 1,
53
+ "use_vae": true,
54
+ "latent_dim": 32,
55
+ "n_vae_encoder_layers": 4,
56
+ "temporal_ensemble_coeff": null,
57
+ "dropout": 0.1,
58
+ "kl_weight": 10.0,
59
+ "optimizer_lr": 1e-05,
60
+ "optimizer_weight_decay": 0.0001,
61
+ "optimizer_lr_backbone": 1e-05
62
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a190eb3f47c8daa51395893af49f9df55977d777575789c1599deea6115551fa
3
+ size 206765304
policy_postprocessor.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_postprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "unnormalizer_processor",
6
+ "config": {
7
+ "eps": 1e-08,
8
+ "features": {
9
+ "action": {
10
+ "type": "ACTION",
11
+ "shape": [
12
+ 14
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "MEAN_STD",
18
+ "STATE": "MEAN_STD",
19
+ "ACTION": "MEAN_STD"
20
+ }
21
+ },
22
+ "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
23
+ },
24
+ {
25
+ "registry_name": "device_processor",
26
+ "config": {
27
+ "device": "cpu",
28
+ "float_dtype": null
29
+ }
30
+ }
31
+ ]
32
+ }
policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beaee74d7bda0ebc6995384e3a02b76ce6cea54bc1af6bb1cb55854c79549303
3
+ size 3892
policy_preprocessor.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {}
8
+ }
9
+ },
10
+ {
11
+ "registry_name": "to_batch_processor",
12
+ "config": {}
13
+ },
14
+ {
15
+ "registry_name": "device_processor",
16
+ "config": {
17
+ "device": "cuda",
18
+ "float_dtype": null
19
+ }
20
+ },
21
+ {
22
+ "registry_name": "normalizer_processor",
23
+ "config": {
24
+ "eps": 1e-08,
25
+ "features": {
26
+ "observation.images.top": {
27
+ "type": "VISUAL",
28
+ "shape": [
29
+ 3,
30
+ 480,
31
+ 640
32
+ ]
33
+ },
34
+ "observation.state": {
35
+ "type": "STATE",
36
+ "shape": [
37
+ 14
38
+ ]
39
+ },
40
+ "action": {
41
+ "type": "ACTION",
42
+ "shape": [
43
+ 14
44
+ ]
45
+ }
46
+ },
47
+ "norm_map": {
48
+ "VISUAL": "MEAN_STD",
49
+ "STATE": "MEAN_STD",
50
+ "ACTION": "MEAN_STD"
51
+ }
52
+ },
53
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
54
+ }
55
+ ]
56
+ }
policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beaee74d7bda0ebc6995384e3a02b76ce6cea54bc1af6bb1cb55854c79549303
3
+ size 3892
train_config.json ADDED
@@ -0,0 +1,230 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "lerobot/aloha_sim_transfer_cube_human_image",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": false,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "tfs": {
11
+ "brightness": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "brightness": [
16
+ 0.8,
17
+ 1.2
18
+ ]
19
+ }
20
+ },
21
+ "contrast": {
22
+ "weight": 1.0,
23
+ "type": "ColorJitter",
24
+ "kwargs": {
25
+ "contrast": [
26
+ 0.8,
27
+ 1.2
28
+ ]
29
+ }
30
+ },
31
+ "saturation": {
32
+ "weight": 1.0,
33
+ "type": "ColorJitter",
34
+ "kwargs": {
35
+ "saturation": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "hue": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "hue": [
46
+ -0.05,
47
+ 0.05
48
+ ]
49
+ }
50
+ },
51
+ "sharpness": {
52
+ "weight": 1.0,
53
+ "type": "SharpnessJitter",
54
+ "kwargs": {
55
+ "sharpness": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ },
61
+ "affine": {
62
+ "weight": 1.0,
63
+ "type": "RandomAffine",
64
+ "kwargs": {
65
+ "degrees": [
66
+ -5.0,
67
+ 5.0
68
+ ],
69
+ "translate": [
70
+ 0.05,
71
+ 0.05
72
+ ]
73
+ }
74
+ }
75
+ }
76
+ },
77
+ "revision": null,
78
+ "use_imagenet_stats": true,
79
+ "video_backend": "torchcodec",
80
+ "streaming": false
81
+ },
82
+ "env": {
83
+ "type": "aloha",
84
+ "task": "AlohaTransferCube-v0",
85
+ "fps": 50,
86
+ "features": {
87
+ "action": {
88
+ "type": "ACTION",
89
+ "shape": [
90
+ 14
91
+ ]
92
+ },
93
+ "agent_pos": {
94
+ "type": "STATE",
95
+ "shape": [
96
+ 14
97
+ ]
98
+ },
99
+ "pixels/top": {
100
+ "type": "VISUAL",
101
+ "shape": [
102
+ 480,
103
+ 640,
104
+ 3
105
+ ]
106
+ }
107
+ },
108
+ "features_map": {
109
+ "action": "action",
110
+ "agent_pos": "observation.state",
111
+ "top": "observation.image.top",
112
+ "pixels/top": "observation.images.top"
113
+ },
114
+ "max_parallel_tasks": 1,
115
+ "disable_env_checker": true,
116
+ "episode_length": 400,
117
+ "obs_type": "pixels_agent_pos",
118
+ "observation_height": 480,
119
+ "observation_width": 640,
120
+ "render_mode": "rgb_array"
121
+ },
122
+ "policy": {
123
+ "type": "act",
124
+ "n_obs_steps": 1,
125
+ "input_features": {
126
+ "observation.images.top": {
127
+ "type": "VISUAL",
128
+ "shape": [
129
+ 3,
130
+ 480,
131
+ 640
132
+ ]
133
+ },
134
+ "observation.state": {
135
+ "type": "STATE",
136
+ "shape": [
137
+ 14
138
+ ]
139
+ }
140
+ },
141
+ "output_features": {
142
+ "action": {
143
+ "type": "ACTION",
144
+ "shape": [
145
+ 14
146
+ ]
147
+ }
148
+ },
149
+ "device": "cuda",
150
+ "use_amp": false,
151
+ "push_to_hub": false,
152
+ "repo_id": null,
153
+ "private": null,
154
+ "tags": null,
155
+ "license": null,
156
+ "pretrained_path": null,
157
+ "chunk_size": 100,
158
+ "n_action_steps": 100,
159
+ "normalization_mapping": {
160
+ "VISUAL": "MEAN_STD",
161
+ "STATE": "MEAN_STD",
162
+ "ACTION": "MEAN_STD"
163
+ },
164
+ "vision_backbone": "resnet18",
165
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
166
+ "replace_final_stride_with_dilation": false,
167
+ "pre_norm": false,
168
+ "dim_model": 512,
169
+ "n_heads": 8,
170
+ "dim_feedforward": 3200,
171
+ "feedforward_activation": "relu",
172
+ "n_encoder_layers": 4,
173
+ "n_decoder_layers": 1,
174
+ "use_vae": true,
175
+ "latent_dim": 32,
176
+ "n_vae_encoder_layers": 4,
177
+ "temporal_ensemble_coeff": null,
178
+ "dropout": 0.1,
179
+ "kl_weight": 10.0,
180
+ "optimizer_lr": 1e-05,
181
+ "optimizer_weight_decay": 0.0001,
182
+ "optimizer_lr_backbone": 1e-05
183
+ },
184
+ "output_dir": "outputs/act_aloha_cube_best",
185
+ "job_name": "aloha_act",
186
+ "resume": false,
187
+ "seed": 1000,
188
+ "num_workers": 4,
189
+ "batch_size": 32,
190
+ "steps": 60000,
191
+ "eval_freq": 5000,
192
+ "log_freq": 200,
193
+ "tolerance_s": 0.0001,
194
+ "save_checkpoint": true,
195
+ "save_freq": 20000,
196
+ "use_policy_training_preset": true,
197
+ "optimizer": {
198
+ "type": "adamw",
199
+ "lr": 1e-05,
200
+ "weight_decay": 0.0001,
201
+ "grad_clip_norm": 10.0,
202
+ "betas": [
203
+ 0.9,
204
+ 0.999
205
+ ],
206
+ "eps": 1e-08
207
+ },
208
+ "scheduler": null,
209
+ "eval": {
210
+ "n_episodes": 50,
211
+ "batch_size": 50,
212
+ "use_async_envs": false
213
+ },
214
+ "wandb": {
215
+ "enable": false,
216
+ "disable_artifact": false,
217
+ "project": "lerobot",
218
+ "entity": null,
219
+ "notes": null,
220
+ "run_id": null,
221
+ "mode": null
222
+ },
223
+ "use_rabc": false,
224
+ "rabc_progress_path": null,
225
+ "rabc_kappa": 0.01,
226
+ "rabc_epsilon": 1e-06,
227
+ "rabc_head_mode": "sparse",
228
+ "rename_map": {},
229
+ "checkpoint_path": null
230
+ }