Hugging Face's logo

Lemon-03
/
ACT_PushT_test

Robotics
LeRobot
Safetensors
act
pusht
imitation-learning
baseline
Model card Files
xet
Community
Lemon-03 commited on
Commit
47c9190
·
verified ·
1 Parent(s): f35712d

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 +226 -0
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.image": {
6
+ "type": "VISUAL",
7
+ "shape": [
8
+ 3,
9
+ 96,
10
+ 96
11
+ ]
12
+ },
13
+ "observation.state": {
14
+ "type": "STATE",
15
+ "shape": [
16
+ 2
17
+ ]
18
+ }
19
+ },
20
+ "output_features": {
21
+ "action": {
22
+ "type": "ACTION",
23
+ "shape": [
24
+ 2
25
+ ]
26
+ }
27
+ },
28
+ "device": "cuda",
29
+ "use_amp": true,
30
+ "push_to_hub": true,
31
+ "repo_id": "Lemon-03/pusht_ACT_PushT_test",
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": 0,
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": 2e-05,
60
+ "optimizer_weight_decay": 0.0002,
61
+ "optimizer_lr_backbone": 2e-05
62
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbae9793d2ee7b67012b28852b310307c224c0b1eaadd6cc330482e5eba040e8
3
+ size 206666936
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
+ 2
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:bc174a7436ff5075efebe7be7cece5e5d8430658cc9b5314fb8a652eab912d96
3
+ size 4204
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.image": {
27
+ "type": "VISUAL",
28
+ "shape": [
29
+ 3,
30
+ 96,
31
+ 96
32
+ ]
33
+ },
34
+ "observation.state": {
35
+ "type": "STATE",
36
+ "shape": [
37
+ 2
38
+ ]
39
+ },
40
+ "action": {
41
+ "type": "ACTION",
42
+ "shape": [
43
+ 2
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:bc174a7436ff5075efebe7be7cece5e5d8430658cc9b5314fb8a652eab912d96
3
+ size 4204
train_config.json ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "lerobot/pusht",
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": "pusht",
84
+ "task": "PushT-v0",
85
+ "fps": 10,
86
+ "features": {
87
+ "action": {
88
+ "type": "ACTION",
89
+ "shape": [
90
+ 2
91
+ ]
92
+ },
93
+ "agent_pos": {
94
+ "type": "STATE",
95
+ "shape": [
96
+ 2
97
+ ]
98
+ },
99
+ "pixels": {
100
+ "type": "VISUAL",
101
+ "shape": [
102
+ 384,
103
+ 384,
104
+ 3
105
+ ]
106
+ }
107
+ },
108
+ "features_map": {
109
+ "action": "action",
110
+ "agent_pos": "observation.state",
111
+ "environment_state": "observation.environment_state",
112
+ "pixels": "observation.image"
113
+ },
114
+ "max_parallel_tasks": 1,
115
+ "disable_env_checker": true,
116
+ "episode_length": 300,
117
+ "obs_type": "pixels_agent_pos",
118
+ "render_mode": "rgb_array",
119
+ "visualization_width": 384,
120
+ "visualization_height": 384,
121
+ "observation_height": 384,
122
+ "observation_width": 384
123
+ },
124
+ "policy": {
125
+ "type": "act",
126
+ "n_obs_steps": 1,
127
+ "input_features": {
128
+ "observation.image": {
129
+ "type": "VISUAL",
130
+ "shape": [
131
+ 3,
132
+ 96,
133
+ 96
134
+ ]
135
+ },
136
+ "observation.state": {
137
+ "type": "STATE",
138
+ "shape": [
139
+ 2
140
+ ]
141
+ }
142
+ },
143
+ "output_features": {
144
+ "action": {
145
+ "type": "ACTION",
146
+ "shape": [
147
+ 2
148
+ ]
149
+ }
150
+ },
151
+ "device": "cuda",
152
+ "use_amp": true,
153
+ "push_to_hub": true,
154
+ "repo_id": "Lemon-03/pusht_ACT_PushT_test",
155
+ "private": null,
156
+ "tags": null,
157
+ "license": null,
158
+ "pretrained_path": null,
159
+ "chunk_size": 100,
160
+ "n_action_steps": 100,
161
+ "normalization_mapping": {
162
+ "VISUAL": "MEAN_STD",
163
+ "STATE": "MEAN_STD",
164
+ "ACTION": "MEAN_STD"
165
+ },
166
+ "vision_backbone": "resnet18",
167
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
168
+ "replace_final_stride_with_dilation": 0,
169
+ "pre_norm": false,
170
+ "dim_model": 512,
171
+ "n_heads": 8,
172
+ "dim_feedforward": 3200,
173
+ "feedforward_activation": "relu",
174
+ "n_encoder_layers": 4,
175
+ "n_decoder_layers": 1,
176
+ "use_vae": true,
177
+ "latent_dim": 32,
178
+ "n_vae_encoder_layers": 4,
179
+ "temporal_ensemble_coeff": null,
180
+ "dropout": 0.1,
181
+ "kl_weight": 10.0,
182
+ "optimizer_lr": 2e-05,
183
+ "optimizer_weight_decay": 0.0002,
184
+ "optimizer_lr_backbone": 2e-05
185
+ },
186
+ "output_dir": "outputs/train/2025-12-02/00-28-32_pusht_ACT_PushT",
187
+ "job_name": "pusht_ACT_PushT",
188
+ "resume": false,
189
+ "seed": 100000,
190
+ "num_workers": 4,
191
+ "batch_size": 64,
192
+ "steps": 200000,
193
+ "eval_freq": 10000,
194
+ "log_freq": 250,
195
+ "save_checkpoint": true,
196
+ "save_freq": 50000,
197
+ "use_policy_training_preset": true,
198
+ "optimizer": {
199
+ "type": "adamw",
200
+ "lr": 2e-05,
201
+ "weight_decay": 0.0002,
202
+ "grad_clip_norm": 10.0,
203
+ "betas": [
204
+ 0.9,
205
+ 0.999
206
+ ],
207
+ "eps": 1e-08
208
+ },
209
+ "scheduler": null,
210
+ "eval": {
211
+ "n_episodes": 50,
212
+ "batch_size": 8,
213
+ "use_async_envs": false
214
+ },
215
+ "wandb": {
216
+ "enable": true,
217
+ "disable_artifact": false,
218
+ "project": "lerobot",
219
+ "entity": null,
220
+ "notes": null,
221
+ "run_id": "40pagqb0",
222
+ "mode": null
223
+ },
224
+ "checkpoint_path": null,
225
+ "rename_map": {}
226
+ }