Hugging Face's logo

ryan-wwj
/
pick-put-RGB01

Safetensors
Model card Files
xet
Community
ryan-wwj commited on
Commit
fcebc10
·
verified ·
1 Parent(s): 74a8068

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +61 -0
  2. model.safetensors +3 -0
  3. train_config.json +168 -0
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "n_obs_steps": 1,
3
+ "normalization_mapping": {
4
+ "VISUAL": "MEAN_STD",
5
+ "STATE": "MEAN_STD",
6
+ "ACTION": "MEAN_STD"
7
+ },
8
+ "input_features": {
9
+ "observation.state": {
10
+ "type": "STATE",
11
+ "shape": [
12
+ 7
13
+ ]
14
+ },
15
+ "observation.images.one": {
16
+ "type": "VISUAL",
17
+ "shape": [
18
+ 3,
19
+ 480,
20
+ 640
21
+ ]
22
+ },
23
+ "observation.images.two": {
24
+ "type": "VISUAL",
25
+ "shape": [
26
+ 3,
27
+ 480,
28
+ 640
29
+ ]
30
+ }
31
+ },
32
+ "output_features": {
33
+ "action": {
34
+ "type": "ACTION",
35
+ "shape": [
36
+ 7
37
+ ]
38
+ }
39
+ },
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": false,
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
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7362499dc75569ce2828bce055b0069f2aa1904f7f51c304ea9c1a5ad7853ad9
3
+ size 206709284
train_config.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "ryan-wwj/pick-put-RGB01",
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
+ 7
81
+ ]
82
+ },
83
+ "observation.images.one": {
84
+ "type": "VISUAL",
85
+ "shape": [
86
+ 3,
87
+ 480,
88
+ 640
89
+ ]
90
+ },
91
+ "observation.images.two": {
92
+ "type": "VISUAL",
93
+ "shape": [
94
+ 3,
95
+ 480,
96
+ 640
97
+ ]
98
+ }
99
+ },
100
+ "output_features": {
101
+ "action": {
102
+ "type": "ACTION",
103
+ "shape": [
104
+ 7
105
+ ]
106
+ }
107
+ },
108
+ "chunk_size": 100,
109
+ "n_action_steps": 100,
110
+ "vision_backbone": "resnet18",
111
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
112
+ "replace_final_stride_with_dilation": false,
113
+ "pre_norm": false,
114
+ "dim_model": 512,
115
+ "n_heads": 8,
116
+ "dim_feedforward": 3200,
117
+ "feedforward_activation": "relu",
118
+ "n_encoder_layers": 4,
119
+ "n_decoder_layers": 1,
120
+ "use_vae": true,
121
+ "latent_dim": 32,
122
+ "n_vae_encoder_layers": 4,
123
+ "temporal_ensemble_coeff": null,
124
+ "dropout": 0.1,
125
+ "kl_weight": 10.0,
126
+ "optimizer_lr": 1e-05,
127
+ "optimizer_weight_decay": 0.0001,
128
+ "optimizer_lr_backbone": 1e-05
129
+ },
130
+ "output_dir": "outputs/train/act-pick-put01",
131
+ "job_name": "act-pick-put01",
132
+ "resume": false,
133
+ "device": "cuda",
134
+ "use_amp": false,
135
+ "seed": 1000,
136
+ "num_workers": 4,
137
+ "batch_size": 8,
138
+ "steps": 100000,
139
+ "eval_freq": 20000,
140
+ "log_freq": 200,
141
+ "save_checkpoint": true,
142
+ "save_freq": 20000,
143
+ "use_policy_training_preset": true,
144
+ "optimizer": {
145
+ "type": "adamw",
146
+ "lr": 1e-05,
147
+ "weight_decay": 0.0001,
148
+ "grad_clip_norm": 10.0,
149
+ "betas": [
150
+ 0.9,
151
+ 0.999
152
+ ],
153
+ "eps": 1e-08
154
+ },
155
+ "scheduler": null,
156
+ "eval": {
157
+ "n_episodes": 50,
158
+ "batch_size": 50,
159
+ "use_async_envs": false
160
+ },
161
+ "wandb": {
162
+ "enable": true,
163
+ "disable_artifact": false,
164
+ "project": "lerobot",
165
+ "entity": null,
166
+ "notes": null
167
+ }
168
+ }