Hugging Face's logo

RoboEval
/
roboeval-diffusion

Robotics
Safetensors
roboeval
diffusion
Model card Files
xet
 Community
helen9975 commited on
Commit
ff5b9ab
·
verified ·
1 Parent(s): ee15aba

v3_merged: step 030000 weights

Browse files
Files changed (7) hide show
  1. v3_merged/config.json +99 -0
  2. v3_merged/model.safetensors +3 -0
  3. v3_merged/policy_postprocessor.json +32 -0
  4. v3_merged/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. v3_merged/policy_preprocessor.json +72 -0
  6. v3_merged/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  7. v3_merged/train_config.json +233 -0
v3_merged/config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 2,
4
+ "input_features": {
5
+ "observation.images.cam_head": {
6
+ "type": "VISUAL",
7
+ "shape": [
8
+ 3,
9
+ 256,
10
+ 256
11
+ ]
12
+ },
13
+ "observation.images.cam_left_wrist": {
14
+ "type": "VISUAL",
15
+ "shape": [
16
+ 3,
17
+ 256,
18
+ 256
19
+ ]
20
+ },
21
+ "observation.images.cam_right_wrist": {
22
+ "type": "VISUAL",
23
+ "shape": [
24
+ 3,
25
+ 256,
26
+ 256
27
+ ]
28
+ },
29
+ "observation.state": {
30
+ "type": "STATE",
31
+ "shape": [
32
+ 16
33
+ ]
34
+ }
35
+ },
36
+ "output_features": {
37
+ "action": {
38
+ "type": "ACTION",
39
+ "shape": [
40
+ 14
41
+ ]
42
+ }
43
+ },
44
+ "device": "cuda",
45
+ "use_amp": false,
46
+ "use_peft": false,
47
+ "push_to_hub": false,
48
+ "repo_id": null,
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": null,
53
+ "horizon": 16,
54
+ "n_action_steps": 8,
55
+ "normalization_mapping": {
56
+ "VISUAL": "MEAN_STD",
57
+ "STATE": "MIN_MAX",
58
+ "ACTION": "MIN_MAX"
59
+ },
60
+ "drop_n_last_frames": 7,
61
+ "vision_backbone": "resnet18",
62
+ "crop_shape": [
63
+ 84,
64
+ 84
65
+ ],
66
+ "crop_is_random": true,
67
+ "pretrained_backbone_weights": null,
68
+ "use_group_norm": true,
69
+ "spatial_softmax_num_keypoints": 32,
70
+ "use_separate_rgb_encoder_per_camera": false,
71
+ "down_dims": [
72
+ 512,
73
+ 1024,
74
+ 2048
75
+ ],
76
+ "kernel_size": 5,
77
+ "n_groups": 8,
78
+ "diffusion_step_embed_dim": 128,
79
+ "use_film_scale_modulation": true,
80
+ "noise_scheduler_type": "DDPM",
81
+ "num_train_timesteps": 100,
82
+ "beta_schedule": "squaredcos_cap_v2",
83
+ "beta_start": 0.0001,
84
+ "beta_end": 0.02,
85
+ "prediction_type": "epsilon",
86
+ "clip_sample": true,
87
+ "clip_sample_range": 1.0,
88
+ "num_inference_steps": null,
89
+ "do_mask_loss_for_padding": false,
90
+ "optimizer_lr": 0.0001,
91
+ "optimizer_betas": [
92
+ 0.95,
93
+ 0.999
94
+ ],
95
+ "optimizer_eps": 1e-08,
96
+ "optimizer_weight_decay": 1e-06,
97
+ "scheduler_name": "cosine",
98
+ "scheduler_warmup_steps": 500
99
+ }
v3_merged/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ade6d2b43de4a5e989bdaaf423960e195a062b34cb1b860f6b88ab5712a93ca4
3
+ size 1083604936
v3_merged/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
+ 14
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "MEAN_STD",
18
+ "STATE": "MIN_MAX",
19
+ "ACTION": "MIN_MAX"
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
+ }
v3_merged/policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eade2702b8d51ae35e9e76ef4a2240b31c1185f77711c1f36c7f184e6b063026
3
+ size 9856
v3_merged/policy_preprocessor.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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.images.cam_head": {
27
+ "type": "VISUAL",
28
+ "shape": [
29
+ 3,
30
+ 256,
31
+ 256
32
+ ]
33
+ },
34
+ "observation.images.cam_left_wrist": {
35
+ "type": "VISUAL",
36
+ "shape": [
37
+ 3,
38
+ 256,
39
+ 256
40
+ ]
41
+ },
42
+ "observation.images.cam_right_wrist": {
43
+ "type": "VISUAL",
44
+ "shape": [
45
+ 3,
46
+ 256,
47
+ 256
48
+ ]
49
+ },
50
+ "observation.state": {
51
+ "type": "STATE",
52
+ "shape": [
53
+ 16
54
+ ]
55
+ },
56
+ "action": {
57
+ "type": "ACTION",
58
+ "shape": [
59
+ 14
60
+ ]
61
+ }
62
+ },
63
+ "norm_map": {
64
+ "VISUAL": "MEAN_STD",
65
+ "STATE": "MIN_MAX",
66
+ "ACTION": "MIN_MAX"
67
+ }
68
+ },
69
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
70
+ }
71
+ ]
72
+ }
v3_merged/policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eade2702b8d51ae35e9e76ef4a2240b31c1185f77711c1f36c7f184e6b063026
3
+ size 9856
v3_merged/train_config.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "roboeval_ee_delta_20hz_v3_merged",
4
+ "root": "/weka/helenw/data/huggingface/lerobot/roboeval_ee_delta_20hz_v3_merged",
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
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": "local",
78
+ "use_imagenet_stats": true,
79
+ "video_backend": "torchcodec",
80
+ "streaming": false
81
+ },
82
+ "env": null,
83
+ "policy": {
84
+ "type": "diffusion",
85
+ "n_obs_steps": 2,
86
+ "input_features": {
87
+ "observation.images.cam_head": {
88
+ "type": "VISUAL",
89
+ "shape": [
90
+ 3,
91
+ 256,
92
+ 256
93
+ ]
94
+ },
95
+ "observation.images.cam_left_wrist": {
96
+ "type": "VISUAL",
97
+ "shape": [
98
+ 3,
99
+ 256,
100
+ 256
101
+ ]
102
+ },
103
+ "observation.images.cam_right_wrist": {
104
+ "type": "VISUAL",
105
+ "shape": [
106
+ 3,
107
+ 256,
108
+ 256
109
+ ]
110
+ },
111
+ "observation.state": {
112
+ "type": "STATE",
113
+ "shape": [
114
+ 16
115
+ ]
116
+ }
117
+ },
118
+ "output_features": {
119
+ "action": {
120
+ "type": "ACTION",
121
+ "shape": [
122
+ 14
123
+ ]
124
+ }
125
+ },
126
+ "device": "cuda",
127
+ "use_amp": false,
128
+ "use_peft": false,
129
+ "push_to_hub": false,
130
+ "repo_id": null,
131
+ "private": null,
132
+ "tags": null,
133
+ "license": null,
134
+ "pretrained_path": null,
135
+ "horizon": 16,
136
+ "n_action_steps": 8,
137
+ "normalization_mapping": {
138
+ "VISUAL": "MEAN_STD",
139
+ "STATE": "MIN_MAX",
140
+ "ACTION": "MIN_MAX"
141
+ },
142
+ "drop_n_last_frames": 7,
143
+ "vision_backbone": "resnet18",
144
+ "crop_shape": [
145
+ 84,
146
+ 84
147
+ ],
148
+ "crop_is_random": true,
149
+ "pretrained_backbone_weights": null,
150
+ "use_group_norm": true,
151
+ "spatial_softmax_num_keypoints": 32,
152
+ "use_separate_rgb_encoder_per_camera": false,
153
+ "down_dims": [
154
+ 512,
155
+ 1024,
156
+ 2048
157
+ ],
158
+ "kernel_size": 5,
159
+ "n_groups": 8,
160
+ "diffusion_step_embed_dim": 128,
161
+ "use_film_scale_modulation": true,
162
+ "noise_scheduler_type": "DDPM",
163
+ "num_train_timesteps": 100,
164
+ "beta_schedule": "squaredcos_cap_v2",
165
+ "beta_start": 0.0001,
166
+ "beta_end": 0.02,
167
+ "prediction_type": "epsilon",
168
+ "clip_sample": true,
169
+ "clip_sample_range": 1.0,
170
+ "num_inference_steps": null,
171
+ "do_mask_loss_for_padding": false,
172
+ "optimizer_lr": 0.0001,
173
+ "optimizer_betas": [
174
+ 0.95,
175
+ 0.999
176
+ ],
177
+ "optimizer_eps": 1e-08,
178
+ "optimizer_weight_decay": 1e-06,
179
+ "scheduler_name": "cosine",
180
+ "scheduler_warmup_steps": 500
181
+ },
182
+ "output_dir": "/weka/helenw/outputs/diffusion_roboeval_v3_merged",
183
+ "job_name": "diffusion_roboeval_v3_merged",
184
+ "resume": false,
185
+ "seed": 1000,
186
+ "num_workers": 2,
187
+ "batch_size": 64,
188
+ "steps": 30000,
189
+ "eval_freq": 20000,
190
+ "log_freq": 10,
191
+ "tolerance_s": 0.0001,
192
+ "save_checkpoint": true,
193
+ "save_freq": 5000,
194
+ "use_policy_training_preset": true,
195
+ "optimizer": {
196
+ "type": "adam",
197
+ "lr": 0.0001,
198
+ "weight_decay": 1e-06,
199
+ "grad_clip_norm": 10.0,
200
+ "betas": [
201
+ 0.95,
202
+ 0.999
203
+ ],
204
+ "eps": 1e-08
205
+ },
206
+ "scheduler": {
207
+ "type": "diffuser",
208
+ "num_warmup_steps": 500,
209
+ "name": "cosine"
210
+ },
211
+ "eval": {
212
+ "n_episodes": 50,
213
+ "batch_size": 50,
214
+ "use_async_envs": false
215
+ },
216
+ "wandb": {
217
+ "enable": true,
218
+ "disable_artifact": true,
219
+ "project": "lerobot",
220
+ "entity": null,
221
+ "notes": null,
222
+ "run_id": "rfycouw8",
223
+ "mode": null
224
+ },
225
+ "peft": null,
226
+ "use_rabc": false,
227
+ "rabc_progress_path": null,
228
+ "rabc_kappa": 0.01,
229
+ "rabc_epsilon": 1e-06,
230
+ "rabc_head_mode": "sparse",
231
+ "rename_map": {},
232
+ "checkpoint_path": null
233
+ }