Hugging Face's logo

samithva
/
pick_and_place_bert

Safetensors
Model card Files
xet
Community
samithva commited on
Commit
5b14ef1
·
verified ·
1 Parent(s): 3e6eb48

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +72 -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 +68 -0
  6. policy_preprocessor_step_4_normalizer_processor.safetensors +3 -0
  7. train_config.json +195 -0
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 7
9
+ ]
10
+ },
11
+ "observation.images.wrist": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 640,
16
+ 480
17
+ ]
18
+ },
19
+ "observation.images.ground": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 640,
24
+ 480
25
+ ]
26
+ }
27
+ },
28
+ "output_features": {
29
+ "action": {
30
+ "type": "ACTION",
31
+ "shape": [
32
+ 7
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "use_amp": false,
38
+ "push_to_hub": true,
39
+ "repo_id": "samitva/act_with_language",
40
+ "private": null,
41
+ "tags": null,
42
+ "license": null,
43
+ "pretrained_path": null,
44
+ "chunk_size": 50,
45
+ "n_action_steps": 50,
46
+ "normalization_mapping": {
47
+ "VISUAL": "MEAN_STD",
48
+ "STATE": "MEAN_STD",
49
+ "ACTION": "MEAN_STD"
50
+ },
51
+ "vision_backbone": "resnet18",
52
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
53
+ "replace_final_stride_with_dilation": false,
54
+ "use_text_conditioning": true,
55
+ "text_encoder_model": "distilbert-base-uncased",
56
+ "pre_norm": false,
57
+ "dim_model": 512,
58
+ "n_heads": 8,
59
+ "dim_feedforward": 3200,
60
+ "feedforward_activation": "relu",
61
+ "n_encoder_layers": 4,
62
+ "n_decoder_layers": 1,
63
+ "use_vae": false,
64
+ "latent_dim": 32,
65
+ "n_vae_encoder_layers": 4,
66
+ "temporal_ensemble_coeff": null,
67
+ "dropout": 0.1,
68
+ "kl_weight": 10.0,
69
+ "optimizer_lr": 1e-05,
70
+ "optimizer_weight_decay": 0.0001,
71
+ "optimizer_lr_backbone": 1e-05
72
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b99848f7fd328874c3edf187bdc7a006237e63da809a956fe1bbb6e9f622527a
3
+ size 403935436
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
+ 7
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:bd5c50455eef33c299582fd383ca83a887eda8d70403ab9e0ec1e519661edfd6
3
+ size 7632
policy_preprocessor.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "act_text_processor",
12
+ "config": {}
13
+ },
14
+ {
15
+ "registry_name": "to_batch_processor",
16
+ "config": {}
17
+ },
18
+ {
19
+ "registry_name": "device_processor",
20
+ "config": {
21
+ "device": "cuda",
22
+ "float_dtype": null
23
+ }
24
+ },
25
+ {
26
+ "registry_name": "normalizer_processor",
27
+ "config": {
28
+ "eps": 1e-08,
29
+ "features": {
30
+ "observation.state": {
31
+ "type": "STATE",
32
+ "shape": [
33
+ 7
34
+ ]
35
+ },
36
+ "observation.images.wrist": {
37
+ "type": "VISUAL",
38
+ "shape": [
39
+ 3,
40
+ 640,
41
+ 480
42
+ ]
43
+ },
44
+ "observation.images.ground": {
45
+ "type": "VISUAL",
46
+ "shape": [
47
+ 3,
48
+ 640,
49
+ 480
50
+ ]
51
+ },
52
+ "action": {
53
+ "type": "ACTION",
54
+ "shape": [
55
+ 7
56
+ ]
57
+ }
58
+ },
59
+ "norm_map": {
60
+ "VISUAL": "MEAN_STD",
61
+ "STATE": "MEAN_STD",
62
+ "ACTION": "MEAN_STD"
63
+ }
64
+ },
65
+ "state_file": "policy_preprocessor_step_4_normalizer_processor.safetensors"
66
+ }
67
+ ]
68
+ }
policy_preprocessor_step_4_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd5c50455eef33c299582fd383ca83a887eda8d70403ab9e0ec1e519661edfd6
3
+ size 7632
train_config.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "samithva/pick_and_place",
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
+ 7
91
+ ]
92
+ },
93
+ "observation.images.wrist": {
94
+ "type": "VISUAL",
95
+ "shape": [
96
+ 3,
97
+ 640,
98
+ 480
99
+ ]
100
+ },
101
+ "observation.images.ground": {
102
+ "type": "VISUAL",
103
+ "shape": [
104
+ 3,
105
+ 640,
106
+ 480
107
+ ]
108
+ }
109
+ },
110
+ "output_features": {
111
+ "action": {
112
+ "type": "ACTION",
113
+ "shape": [
114
+ 7
115
+ ]
116
+ }
117
+ },
118
+ "device": "cuda",
119
+ "use_amp": false,
120
+ "push_to_hub": true,
121
+ "repo_id": "samitva/act_with_language",
122
+ "private": null,
123
+ "tags": null,
124
+ "license": null,
125
+ "pretrained_path": null,
126
+ "chunk_size": 50,
127
+ "n_action_steps": 50,
128
+ "normalization_mapping": {
129
+ "VISUAL": "MEAN_STD",
130
+ "STATE": "MEAN_STD",
131
+ "ACTION": "MEAN_STD"
132
+ },
133
+ "vision_backbone": "resnet18",
134
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
135
+ "replace_final_stride_with_dilation": false,
136
+ "use_text_conditioning": true,
137
+ "text_encoder_model": "distilbert-base-uncased",
138
+ "pre_norm": false,
139
+ "dim_model": 512,
140
+ "n_heads": 8,
141
+ "dim_feedforward": 3200,
142
+ "feedforward_activation": "relu",
143
+ "n_encoder_layers": 4,
144
+ "n_decoder_layers": 1,
145
+ "use_vae": false,
146
+ "latent_dim": 32,
147
+ "n_vae_encoder_layers": 4,
148
+ "temporal_ensemble_coeff": null,
149
+ "dropout": 0.1,
150
+ "kl_weight": 10.0,
151
+ "optimizer_lr": 1e-05,
152
+ "optimizer_weight_decay": 0.0001,
153
+ "optimizer_lr_backbone": 1e-05
154
+ },
155
+ "output_dir": "outputs/train/act_with_language",
156
+ "job_name": "act_finetune_with_language",
157
+ "resume": false,
158
+ "seed": 1000,
159
+ "num_workers": 32,
160
+ "batch_size": 128,
161
+ "steps": 20000,
162
+ "eval_freq": 20000,
163
+ "log_freq": 50,
164
+ "save_checkpoint": true,
165
+ "save_freq": 20000,
166
+ "use_policy_training_preset": true,
167
+ "optimizer": {
168
+ "type": "adamw",
169
+ "lr": 1e-05,
170
+ "weight_decay": 0.0001,
171
+ "grad_clip_norm": 10.0,
172
+ "betas": [
173
+ 0.9,
174
+ 0.999
175
+ ],
176
+ "eps": 1e-08
177
+ },
178
+ "scheduler": null,
179
+ "eval": {
180
+ "n_episodes": 50,
181
+ "batch_size": 50,
182
+ "use_async_envs": false
183
+ },
184
+ "wandb": {
185
+ "enable": true,
186
+ "disable_artifact": false,
187
+ "project": "lerobot",
188
+ "entity": null,
189
+ "notes": null,
190
+ "run_id": "m50ffvqr",
191
+ "mode": null
192
+ },
193
+ "checkpoint_path": null,
194
+ "rename_map": {}
195
+ }