Hugging Face's logo

Mimic-Robotics
/
act_odin_red_x_30a_80k

Safetensors
Model card Files
xet
 Community
ac-pate commited on
Commit
6fd277a
·
verified ·
1 Parent(s): aa2eb04

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +87 -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 +80 -0
  6. policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  7. train_config.json +253 -0
config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 15
9
+ ]
10
+ },
11
+ "observation.images.right_wrist": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.images.left_wrist": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 480,
24
+ 640
25
+ ]
26
+ },
27
+ "observation.images.front": {
28
+ "type": "VISUAL",
29
+ "shape": [
30
+ 3,
31
+ 480,
32
+ 640
33
+ ]
34
+ },
35
+ "observation.images.top": {
36
+ "type": "VISUAL",
37
+ "shape": [
38
+ 3,
39
+ 720,
40
+ 1280
41
+ ]
42
+ }
43
+ },
44
+ "output_features": {
45
+ "action": {
46
+ "type": "ACTION",
47
+ "shape": [
48
+ 15
49
+ ]
50
+ }
51
+ },
52
+ "device": "cuda",
53
+ "use_amp": false,
54
+ "use_peft": false,
55
+ "push_to_hub": true,
56
+ "repo_id": "Mimic-Robotics/act_odin_red_x_handover_and_place_tictactoe_v8",
57
+ "private": null,
58
+ "tags": null,
59
+ "license": null,
60
+ "pretrained_path": null,
61
+ "chunk_size": 100,
62
+ "n_action_steps": 30,
63
+ "normalization_mapping": {
64
+ "VISUAL": "MEAN_STD",
65
+ "STATE": "MEAN_STD",
66
+ "ACTION": "MEAN_STD"
67
+ },
68
+ "vision_backbone": "resnet18",
69
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
70
+ "replace_final_stride_with_dilation": false,
71
+ "pre_norm": false,
72
+ "dim_model": 512,
73
+ "n_heads": 8,
74
+ "dim_feedforward": 3200,
75
+ "feedforward_activation": "relu",
76
+ "n_encoder_layers": 4,
77
+ "n_decoder_layers": 1,
78
+ "use_vae": true,
79
+ "latent_dim": 32,
80
+ "n_vae_encoder_layers": 4,
81
+ "temporal_ensemble_coeff": null,
82
+ "dropout": 0.1,
83
+ "kl_weight": 10.0,
84
+ "optimizer_lr": 1e-05,
85
+ "optimizer_weight_decay": 0.0001,
86
+ "optimizer_lr_backbone": 1e-05
87
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e17109fff184eb905650cf081e7c75474b0e5894e50addb9d3a32cb6686307c
3
+ size 206773500
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
+ 15
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:bef68475e643607621867318232998ae155b647a3af98277393e69b0d864cfbf
3
+ size 10376
policy_preprocessor.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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.state": {
27
+ "type": "STATE",
28
+ "shape": [
29
+ 15
30
+ ]
31
+ },
32
+ "observation.images.right_wrist": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 480,
37
+ 640
38
+ ]
39
+ },
40
+ "observation.images.left_wrist": {
41
+ "type": "VISUAL",
42
+ "shape": [
43
+ 3,
44
+ 480,
45
+ 640
46
+ ]
47
+ },
48
+ "observation.images.front": {
49
+ "type": "VISUAL",
50
+ "shape": [
51
+ 3,
52
+ 480,
53
+ 640
54
+ ]
55
+ },
56
+ "observation.images.top": {
57
+ "type": "VISUAL",
58
+ "shape": [
59
+ 3,
60
+ 720,
61
+ 1280
62
+ ]
63
+ },
64
+ "action": {
65
+ "type": "ACTION",
66
+ "shape": [
67
+ 15
68
+ ]
69
+ }
70
+ },
71
+ "norm_map": {
72
+ "VISUAL": "MEAN_STD",
73
+ "STATE": "MEAN_STD",
74
+ "ACTION": "MEAN_STD"
75
+ }
76
+ },
77
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
78
+ }
79
+ ]
80
+ }
policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bef68475e643607621867318232998ae155b647a3af98277393e69b0d864cfbf
3
+ size 10376
train_config.json ADDED
@@ -0,0 +1,253 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": [
4
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v2",
5
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v3",
6
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v4",
7
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v5",
8
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v6",
9
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v8",
10
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v9",
11
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v11",
12
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v12",
13
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v13",
14
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v14",
15
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v15",
16
+ "Mimic-Robotics/mimic_tictactoe_pick_red_x_handover_place_mm_v16",
17
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_topleft_v1",
18
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_topleft_v2",
19
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_toprght_v1",
20
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_toprght_v2",
21
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_toprght_v3",
22
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_toprght_v4",
23
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_bottomleft_v1",
24
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_bottomleft_v2",
25
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_bottomright_v1",
26
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_bottomright_v2",
27
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_topmiddle_v1",
28
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_topMiddle_v3",
29
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_topMiddle_v4",
30
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_middleLeft_v1",
31
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_middleLeft_v2",
32
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_middleLeft_v3",
33
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_middleLeft_v4",
34
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_middleRight_v1",
35
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_middleRight_v2",
36
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_bottom_middle_v1",
37
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_bottom_middle_v2",
38
+ "Mimic-Robotics/mimic_tictactoe_red_x_handover_center_slow_v1"
39
+ ],
40
+ "root": null,
41
+ "episodes": null,
42
+ "image_transforms": {
43
+ "enable": false,
44
+ "max_num_transforms": 3,
45
+ "random_order": false,
46
+ "tfs": {
47
+ "brightness": {
48
+ "weight": 1.0,
49
+ "type": "ColorJitter",
50
+ "kwargs": {
51
+ "brightness": [
52
+ 0.8,
53
+ 1.2
54
+ ]
55
+ }
56
+ },
57
+ "contrast": {
58
+ "weight": 1.0,
59
+ "type": "ColorJitter",
60
+ "kwargs": {
61
+ "contrast": [
62
+ 0.8,
63
+ 1.2
64
+ ]
65
+ }
66
+ },
67
+ "saturation": {
68
+ "weight": 1.0,
69
+ "type": "ColorJitter",
70
+ "kwargs": {
71
+ "saturation": [
72
+ 0.5,
73
+ 1.5
74
+ ]
75
+ }
76
+ },
77
+ "hue": {
78
+ "weight": 1.0,
79
+ "type": "ColorJitter",
80
+ "kwargs": {
81
+ "hue": [
82
+ -0.05,
83
+ 0.05
84
+ ]
85
+ }
86
+ },
87
+ "sharpness": {
88
+ "weight": 1.0,
89
+ "type": "SharpnessJitter",
90
+ "kwargs": {
91
+ "sharpness": [
92
+ 0.5,
93
+ 1.5
94
+ ]
95
+ }
96
+ },
97
+ "affine": {
98
+ "weight": 1.0,
99
+ "type": "RandomAffine",
100
+ "kwargs": {
101
+ "degrees": [
102
+ -5.0,
103
+ 5.0
104
+ ],
105
+ "translate": [
106
+ 0.05,
107
+ 0.05
108
+ ]
109
+ }
110
+ }
111
+ }
112
+ },
113
+ "revision": null,
114
+ "use_imagenet_stats": true,
115
+ "video_backend": "torchcodec",
116
+ "streaming": false
117
+ },
118
+ "env": null,
119
+ "policy": {
120
+ "type": "act",
121
+ "n_obs_steps": 1,
122
+ "input_features": {
123
+ "observation.state": {
124
+ "type": "STATE",
125
+ "shape": [
126
+ 15
127
+ ]
128
+ },
129
+ "observation.images.right_wrist": {
130
+ "type": "VISUAL",
131
+ "shape": [
132
+ 3,
133
+ 480,
134
+ 640
135
+ ]
136
+ },
137
+ "observation.images.left_wrist": {
138
+ "type": "VISUAL",
139
+ "shape": [
140
+ 3,
141
+ 480,
142
+ 640
143
+ ]
144
+ },
145
+ "observation.images.front": {
146
+ "type": "VISUAL",
147
+ "shape": [
148
+ 3,
149
+ 480,
150
+ 640
151
+ ]
152
+ },
153
+ "observation.images.top": {
154
+ "type": "VISUAL",
155
+ "shape": [
156
+ 3,
157
+ 720,
158
+ 1280
159
+ ]
160
+ }
161
+ },
162
+ "output_features": {
163
+ "action": {
164
+ "type": "ACTION",
165
+ "shape": [
166
+ 15
167
+ ]
168
+ }
169
+ },
170
+ "device": "cuda",
171
+ "use_amp": false,
172
+ "use_peft": false,
173
+ "push_to_hub": true,
174
+ "repo_id": "Mimic-Robotics/act_odin_red_x_handover_and_place_tictactoe_v8",
175
+ "private": null,
176
+ "tags": null,
177
+ "license": null,
178
+ "pretrained_path": null,
179
+ "chunk_size": 100,
180
+ "n_action_steps": 30,
181
+ "normalization_mapping": {
182
+ "VISUAL": "MEAN_STD",
183
+ "STATE": "MEAN_STD",
184
+ "ACTION": "MEAN_STD"
185
+ },
186
+ "vision_backbone": "resnet18",
187
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
188
+ "replace_final_stride_with_dilation": false,
189
+ "pre_norm": false,
190
+ "dim_model": 512,
191
+ "n_heads": 8,
192
+ "dim_feedforward": 3200,
193
+ "feedforward_activation": "relu",
194
+ "n_encoder_layers": 4,
195
+ "n_decoder_layers": 1,
196
+ "use_vae": true,
197
+ "latent_dim": 32,
198
+ "n_vae_encoder_layers": 4,
199
+ "temporal_ensemble_coeff": null,
200
+ "dropout": 0.1,
201
+ "kl_weight": 10.0,
202
+ "optimizer_lr": 1e-05,
203
+ "optimizer_weight_decay": 0.0001,
204
+ "optimizer_lr_backbone": 1e-05
205
+ },
206
+ "output_dir": "/home/odin/mimic-lerobot/outputs/train/act_odin_red_x_handover_and_place_tictactoe_v8",
207
+ "job_name": "act_odin_red_x_handover_and_place_tictactoe_v8",
208
+ "resume": false,
209
+ "seed": 1000,
210
+ "num_workers": 12,
211
+ "batch_size": 10,
212
+ "steps": 100000,
213
+ "eval_freq": 20000,
214
+ "log_freq": 200,
215
+ "tolerance_s": 0.0001,
216
+ "save_checkpoint": true,
217
+ "save_freq": 10000,
218
+ "use_policy_training_preset": true,
219
+ "optimizer": {
220
+ "type": "adamw",
221
+ "lr": 1e-05,
222
+ "weight_decay": 0.0001,
223
+ "grad_clip_norm": 10.0,
224
+ "betas": [
225
+ 0.9,
226
+ 0.999
227
+ ],
228
+ "eps": 1e-08
229
+ },
230
+ "scheduler": null,
231
+ "eval": {
232
+ "n_episodes": 50,
233
+ "batch_size": 50,
234
+ "use_async_envs": false
235
+ },
236
+ "wandb": {
237
+ "enable": true,
238
+ "disable_artifact": false,
239
+ "project": "lerobot",
240
+ "entity": null,
241
+ "notes": "Multi-dataset ACT training on red_x_handover_and_place_tictactoe_v8 with Computer odin and Batch 10",
242
+ "run_id": "l5ybc6d8",
243
+ "mode": null
244
+ },
245
+ "peft": null,
246
+ "use_rabc": false,
247
+ "rabc_progress_path": null,
248
+ "rabc_kappa": 0.01,
249
+ "rabc_epsilon": 1e-06,
250
+ "rabc_head_mode": "sparse",
251
+ "rename_map": {},
252
+ "checkpoint_path": null
253
+ }