Hugging Face's logo

Sepehrmo
/
act_my_robot

Robotics
LeRobot
Safetensors
act
Model card Files
xet
Community
Sepehrmo commited on
Commit
36d7b4e
·
verified ·
1 Parent(s): cc9ef01

Upload policy weights, train config and readme

Browse files
Files changed (4) hide show
  1. README.md +62 -0
  2. config.json +61 -60
  3. model.safetensors +2 -2
  4. train_config.json +184 -166
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets: Sepehrmo/my-robot-demo1
3
+ library_name: lerobot
4
+ license: apache-2.0
5
+ model_name: act
6
+ pipeline_tag: robotics
7
+ tags:
8
+ - act
9
+ - lerobot
10
+ - robotics
11
+ ---
12
+
13
+ # Model Card for act
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+ [Action Chunking with Transformers (ACT)](https://huggingface.co/papers/2304.13705) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates.
19
+
20
+
21
+ This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
22
+ See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
23
+
24
+ ---
25
+
26
+ ## How to Get Started with the Model
27
+
28
+ For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).
29
+ Below is the short version on how to train and run inference/eval:
30
+
31
+ ### Train from scratch
32
+
33
+ ```bash
34
+ lerobot-train \
35
+ --dataset.repo_id=${HF_USER}/<dataset> \
36
+ --policy.type=act \
37
+ --output_dir=outputs/train/<desired_policy_repo_id> \
38
+ --job_name=lerobot_training \
39
+ --policy.device=cuda \
40
+ --policy.repo_id=${HF_USER}/<desired_policy_repo_id>
41
+ --wandb.enable=true
42
+ ```
43
+
44
+ _Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
45
+
46
+ ### Evaluate the policy/run inference
47
+
48
+ ```bash
49
+ lerobot-record \
50
+ --robot.type=so100_follower \
51
+ --dataset.repo_id=<hf_user>/eval_<dataset> \
52
+ --policy.path=<hf_user>/<desired_policy_repo_id> \
53
+ --episodes=10
54
+ ```
55
+
56
+ Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.
57
+
58
+ ---
59
+
60
+ ## Model Details
61
+
62
+ - **License:** apache-2.0
config.json CHANGED
@@ -1,61 +1,62 @@
1
- {
2
- "type": "act",
3
- "n_obs_steps": 1,
4
- "normalization_mapping": {
5
- "VISUAL": "MEAN_STD",
6
- "STATE": "MEAN_STD",
7
- "ACTION": "MEAN_STD"
8
- },
9
- "input_features": {
10
- "observation.state": {
11
- "type": "STATE",
12
- "shape": [
13
- 6
14
- ]
15
- },
16
- "observation.images.front": {
17
- "type": "VISUAL",
18
- "shape": [
19
- 3,
20
- 480,
21
- 640
22
- ]
23
- }
24
- },
25
- "output_features": {
26
- "action": {
27
- "type": "ACTION",
28
- "shape": [
29
- 6
30
- ]
31
- }
32
- },
33
- "device": "cuda",
34
- "use_amp": false,
35
- "push_to_hub": true,
36
- "repo_id": "Sepehrmo/my_trained_policy",
37
- "private": null,
38
- "tags": null,
39
- "license": null,
40
- "chunk_size": 100,
41
- "n_action_steps": 100,
42
- "vision_backbone": "resnet18",
43
- "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
44
- "replace_final_stride_with_dilation": 0,
45
- "pre_norm": false,
46
- "dim_model": 512,
47
- "n_heads": 8,
48
- "dim_feedforward": 3200,
49
- "feedforward_activation": "relu",
50
- "n_encoder_layers": 4,
51
- "n_decoder_layers": 1,
52
- "use_vae": true,
53
- "latent_dim": 32,
54
- "n_vae_encoder_layers": 4,
55
- "temporal_ensemble_coeff": null,
56
- "dropout": 0.1,
57
- "kl_weight": 10.0,
58
- "optimizer_lr": 1e-05,
59
- "optimizer_weight_decay": 0.0001,
60
- "optimizer_lr_backbone": 1e-05
 
61
  }
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.front": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ }
19
+ },
20
+ "output_features": {
21
+ "action": {
22
+ "type": "ACTION",
23
+ "shape": [
24
+ 6
25
+ ]
26
+ }
27
+ },
28
+ "device": "cuda",
29
+ "use_amp": false,
30
+ "push_to_hub": true,
31
+ "repo_id": "Sepehrmo/act_my_robot",
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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1984a253fc01786b9494615bb15a49df17da30d90aebb5a66552a3c5b60e404f
3
- size 206700792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659d9be0ed711d75d82b5f6e1a69911751001fb5f3b637f1842359dba0d4b817
3
+ size 206699736
train_config.json CHANGED
@@ -1,167 +1,185 @@
1
- {
2
- "dataset": {
3
- "repo_id": "Sepehrmo/my-robot-demo1",
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
- }
62
- },
63
- "revision": null,
64
- "use_imagenet_stats": true,
65
- "video_backend": "pyav"
66
- },
67
- "env": null,
68
- "policy": {
69
- "type": "act",
70
- "n_obs_steps": 1,
71
- "normalization_mapping": {
72
- "VISUAL": "MEAN_STD",
73
- "STATE": "MEAN_STD",
74
- "ACTION": "MEAN_STD"
75
- },
76
- "input_features": {
77
- "observation.state": {
78
- "type": "STATE",
79
- "shape": [
80
- 6
81
- ]
82
- },
83
- "observation.images.front": {
84
- "type": "VISUAL",
85
- "shape": [
86
- 3,
87
- 480,
88
- 640
89
- ]
90
- }
91
- },
92
- "output_features": {
93
- "action": {
94
- "type": "ACTION",
95
- "shape": [
96
- 6
97
- ]
98
- }
99
- },
100
- "device": "cuda",
101
- "use_amp": false,
102
- "push_to_hub": true,
103
- "repo_id": "Sepehrmo/my_trained_policy",
104
- "private": null,
105
- "tags": null,
106
- "license": null,
107
- "chunk_size": 100,
108
- "n_action_steps": 100,
109
- "vision_backbone": "resnet18",
110
- "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
111
- "replace_final_stride_with_dilation": 0,
112
- "pre_norm": false,
113
- "dim_model": 512,
114
- "n_heads": 8,
115
- "dim_feedforward": 3200,
116
- "feedforward_activation": "relu",
117
- "n_encoder_layers": 4,
118
- "n_decoder_layers": 1,
119
- "use_vae": true,
120
- "latent_dim": 32,
121
- "n_vae_encoder_layers": 4,
122
- "temporal_ensemble_coeff": null,
123
- "dropout": 0.1,
124
- "kl_weight": 10.0,
125
- "optimizer_lr": 1e-05,
126
- "optimizer_weight_decay": 0.0001,
127
- "optimizer_lr_backbone": 1e-05
128
- },
129
- "output_dir": "outputs\\train\\act_my_robot",
130
- "job_name": "act_my_robot_training",
131
- "resume": true,
132
- "seed": 1000,
133
- "num_workers": 4,
134
- "batch_size": 8,
135
- "steps": 100000,
136
- "eval_freq": 20000,
137
- "log_freq": 200,
138
- "save_checkpoint": true,
139
- "save_freq": 20000,
140
- "use_policy_training_preset": true,
141
- "optimizer": {
142
- "type": "adamw",
143
- "lr": 1e-05,
144
- "weight_decay": 0.0001,
145
- "grad_clip_norm": 10.0,
146
- "betas": [
147
- 0.9,
148
- 0.999
149
- ],
150
- "eps": 1e-08
151
- },
152
- "scheduler": null,
153
- "eval": {
154
- "n_episodes": 50,
155
- "batch_size": 50,
156
- "use_async_envs": false
157
- },
158
- "wandb": {
159
- "enable": false,
160
- "disable_artifact": false,
161
- "project": "lerobot",
162
- "entity": null,
163
- "notes": null,
164
- "run_id": null,
165
- "mode": null
166
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
167
  }
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "Sepehrmo/my-robot-demo1",
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": null,
83
+ "policy": {
84
+ "type": "act",
85
+ "n_obs_steps": 1,
86
+ "input_features": {
87
+ "observation.state": {
88
+ "type": "STATE",
89
+ "shape": [
90
+ 6
91
+ ]
92
+ },
93
+ "observation.images.front": {
94
+ "type": "VISUAL",
95
+ "shape": [
96
+ 3,
97
+ 480,
98
+ 640
99
+ ]
100
+ }
101
+ },
102
+ "output_features": {
103
+ "action": {
104
+ "type": "ACTION",
105
+ "shape": [
106
+ 6
107
+ ]
108
+ }
109
+ },
110
+ "device": "cuda",
111
+ "use_amp": false,
112
+ "push_to_hub": true,
113
+ "repo_id": "Sepehrmo/act_my_robot",
114
+ "private": null,
115
+ "tags": null,
116
+ "license": null,
117
+ "pretrained_path": null,
118
+ "chunk_size": 100,
119
+ "n_action_steps": 100,
120
+ "normalization_mapping": {
121
+ "VISUAL": "MEAN_STD",
122
+ "STATE": "MEAN_STD",
123
+ "ACTION": "MEAN_STD"
124
+ },
125
+ "vision_backbone": "resnet18",
126
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
127
+ "replace_final_stride_with_dilation": false,
128
+ "pre_norm": false,
129
+ "dim_model": 512,
130
+ "n_heads": 8,
131
+ "dim_feedforward": 3200,
132
+ "feedforward_activation": "relu",
133
+ "n_encoder_layers": 4,
134
+ "n_decoder_layers": 1,
135
+ "use_vae": true,
136
+ "latent_dim": 32,
137
+ "n_vae_encoder_layers": 4,
138
+ "temporal_ensemble_coeff": null,
139
+ "dropout": 0.1,
140
+ "kl_weight": 10.0,
141
+ "optimizer_lr": 1e-05,
142
+ "optimizer_weight_decay": 0.0001,
143
+ "optimizer_lr_backbone": 1e-05
144
+ },
145
+ "output_dir": "outputs/train/il_sim_test1",
146
+ "job_name": "il_sim_test",
147
+ "resume": false,
148
+ "seed": 1000,
149
+ "num_workers": 4,
150
+ "batch_size": 8,
151
+ "steps": 100000,
152
+ "eval_freq": 20000,
153
+ "log_freq": 200,
154
+ "save_checkpoint": true,
155
+ "save_freq": 20000,
156
+ "use_policy_training_preset": true,
157
+ "optimizer": {
158
+ "type": "adamw",
159
+ "lr": 1e-05,
160
+ "weight_decay": 0.0001,
161
+ "grad_clip_norm": 10.0,
162
+ "betas": [
163
+ 0.9,
164
+ 0.999
165
+ ],
166
+ "eps": 1e-08
167
+ },
168
+ "scheduler": null,
169
+ "eval": {
170
+ "n_episodes": 50,
171
+ "batch_size": 50,
172
+ "use_async_envs": false
173
+ },
174
+ "wandb": {
175
+ "enable": true,
176
+ "disable_artifact": false,
177
+ "project": "lerobot",
178
+ "entity": null,
179
+ "notes": null,
180
+ "run_id": "ojtwi96f",
181
+ "mode": null
182
+ },
183
+ "checkpoint_path": null,
184
+ "rename_map": {}
185
  }