Hugging Face's logo

sonpha
/
so101-diffusion-task001

Safetensors
Model card Files
xet
 Community
sonpha commited on
Commit
cd37afe
·
verified ·
1 Parent(s): 7f99739

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +96 -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 +64 -0
  6. policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  7. train_config.json +247 -0
config.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 2,
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
+ "observation.images.wrist": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 480,
24
+ 640
25
+ ]
26
+ }
27
+ },
28
+ "output_features": {
29
+ "action": {
30
+ "type": "ACTION",
31
+ "shape": [
32
+ 6
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "use_amp": false,
38
+ "use_peft": false,
39
+ "push_to_hub": false,
40
+ "repo_id": null,
41
+ "private": null,
42
+ "tags": null,
43
+ "license": null,
44
+ "pretrained_path": null,
45
+ "pretrained_revision": null,
46
+ "horizon": 16,
47
+ "n_action_steps": 8,
48
+ "normalization_mapping": {
49
+ "VISUAL": "MEAN_STD",
50
+ "STATE": "MIN_MAX",
51
+ "ACTION": "MIN_MAX"
52
+ },
53
+ "drop_n_last_frames": 7,
54
+ "vision_backbone": "resnet18",
55
+ "resize_shape": [
56
+ 224,
57
+ 224
58
+ ],
59
+ "crop_ratio": 1.0,
60
+ "crop_shape": null,
61
+ "crop_is_random": true,
62
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
63
+ "use_group_norm": false,
64
+ "spatial_softmax_num_keypoints": 32,
65
+ "use_separate_rgb_encoder_per_camera": true,
66
+ "down_dims": [
67
+ 128,
68
+ 256,
69
+ 512
70
+ ],
71
+ "kernel_size": 5,
72
+ "n_groups": 8,
73
+ "diffusion_step_embed_dim": 128,
74
+ "use_film_scale_modulation": true,
75
+ "noise_scheduler_type": "DDIM",
76
+ "num_train_timesteps": 100,
77
+ "beta_schedule": "squaredcos_cap_v2",
78
+ "beta_start": 0.0001,
79
+ "beta_end": 0.02,
80
+ "prediction_type": "epsilon",
81
+ "clip_sample": true,
82
+ "clip_sample_range": 1.0,
83
+ "num_inference_steps": 10,
84
+ "compile_model": false,
85
+ "compile_mode": "reduce-overhead",
86
+ "do_mask_loss_for_padding": false,
87
+ "optimizer_lr": 0.0001,
88
+ "optimizer_betas": [
89
+ 0.95,
90
+ 0.999
91
+ ],
92
+ "optimizer_eps": 1e-08,
93
+ "optimizer_weight_decay": 1e-06,
94
+ "scheduler_name": "cosine",
95
+ "scheduler_warmup_steps": 5
96
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fb00ffe0838730274a8683a0727d2338b73a74a5b5e4f385883456894d29905
3
+ size 162677040
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
+ 6
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
+ }
policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d02cabf8e504ece1774440b0238358fc749ab665331b6044214978815cf5be
3
+ size 7552
policy_preprocessor.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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.state": {
27
+ "type": "STATE",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ },
32
+ "observation.images.front": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 480,
37
+ 640
38
+ ]
39
+ },
40
+ "observation.images.wrist": {
41
+ "type": "VISUAL",
42
+ "shape": [
43
+ 3,
44
+ 480,
45
+ 640
46
+ ]
47
+ },
48
+ "action": {
49
+ "type": "ACTION",
50
+ "shape": [
51
+ 6
52
+ ]
53
+ }
54
+ },
55
+ "norm_map": {
56
+ "VISUAL": "MEAN_STD",
57
+ "STATE": "MIN_MAX",
58
+ "ACTION": "MIN_MAX"
59
+ }
60
+ },
61
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
62
+ }
63
+ ]
64
+ }
policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aa8b2a6671f84356bba74e3e9ec8a8cbcb973c70e1ca0288237901e9e2aa1ae
3
+ size 7560
train_config.json ADDED
@@ -0,0 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "pjhun/so101-task001",
4
+ "root": "/home/ssafy/ssafy_results/DAY4/datasets/external/so101-task001",
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
+ "return_uint8": false,
81
+ "depth_output_unit": "mm",
82
+ "streaming": false,
83
+ "eval_split": 0.0
84
+ },
85
+ "env": null,
86
+ "policy": {
87
+ "type": "diffusion",
88
+ "n_obs_steps": 2,
89
+ "input_features": {
90
+ "observation.state": {
91
+ "type": "STATE",
92
+ "shape": [
93
+ 6
94
+ ]
95
+ },
96
+ "observation.images.front": {
97
+ "type": "VISUAL",
98
+ "shape": [
99
+ 3,
100
+ 480,
101
+ 640
102
+ ]
103
+ },
104
+ "observation.images.wrist": {
105
+ "type": "VISUAL",
106
+ "shape": [
107
+ 3,
108
+ 480,
109
+ 640
110
+ ]
111
+ }
112
+ },
113
+ "output_features": {
114
+ "action": {
115
+ "type": "ACTION",
116
+ "shape": [
117
+ 6
118
+ ]
119
+ }
120
+ },
121
+ "device": "cuda",
122
+ "use_amp": false,
123
+ "use_peft": false,
124
+ "push_to_hub": false,
125
+ "repo_id": null,
126
+ "private": null,
127
+ "tags": null,
128
+ "license": null,
129
+ "pretrained_path": null,
130
+ "pretrained_revision": null,
131
+ "horizon": 16,
132
+ "n_action_steps": 8,
133
+ "normalization_mapping": {
134
+ "VISUAL": "MEAN_STD",
135
+ "STATE": "MIN_MAX",
136
+ "ACTION": "MIN_MAX"
137
+ },
138
+ "drop_n_last_frames": 7,
139
+ "vision_backbone": "resnet18",
140
+ "resize_shape": [
141
+ 224,
142
+ 224
143
+ ],
144
+ "crop_ratio": 1.0,
145
+ "crop_shape": null,
146
+ "crop_is_random": true,
147
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
148
+ "use_group_norm": false,
149
+ "spatial_softmax_num_keypoints": 32,
150
+ "use_separate_rgb_encoder_per_camera": true,
151
+ "down_dims": [
152
+ 128,
153
+ 256,
154
+ 512
155
+ ],
156
+ "kernel_size": 5,
157
+ "n_groups": 8,
158
+ "diffusion_step_embed_dim": 128,
159
+ "use_film_scale_modulation": true,
160
+ "noise_scheduler_type": "DDIM",
161
+ "num_train_timesteps": 100,
162
+ "beta_schedule": "squaredcos_cap_v2",
163
+ "beta_start": 0.0001,
164
+ "beta_end": 0.02,
165
+ "prediction_type": "epsilon",
166
+ "clip_sample": true,
167
+ "clip_sample_range": 1.0,
168
+ "num_inference_steps": 10,
169
+ "compile_model": false,
170
+ "compile_mode": "reduce-overhead",
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": 5
181
+ },
182
+ "reward_model": null,
183
+ "output_dir": "outputs/train/diffusion_task001_10000",
184
+ "job_name": "diffusion_task001_10000",
185
+ "resume": false,
186
+ "seed": 1000,
187
+ "cudnn_deterministic": false,
188
+ "num_workers": 0,
189
+ "batch_size": 1,
190
+ "prefetch_factor": 4,
191
+ "persistent_workers": true,
192
+ "steps": 10000,
193
+ "env_eval_freq": 20000,
194
+ "log_freq": 100,
195
+ "eval_steps": 0,
196
+ "max_eval_samples": 0,
197
+ "tolerance_s": 0.0001,
198
+ "save_checkpoint": true,
199
+ "save_freq": 2000,
200
+ "use_policy_training_preset": true,
201
+ "optimizer": {
202
+ "type": "adam",
203
+ "lr": 0.0001,
204
+ "weight_decay": 1e-06,
205
+ "grad_clip_norm": 10.0,
206
+ "betas": [
207
+ 0.95,
208
+ 0.999
209
+ ],
210
+ "eps": 1e-08
211
+ },
212
+ "scheduler": {
213
+ "type": "diffuser",
214
+ "num_warmup_steps": 5,
215
+ "name": "cosine"
216
+ },
217
+ "eval": {
218
+ "n_episodes": 50,
219
+ "batch_size": 14,
220
+ "use_async_envs": true,
221
+ "recording": false,
222
+ "recording_repo_id": null,
223
+ "recording_private": false
224
+ },
225
+ "wandb": {
226
+ "enable": false,
227
+ "disable_artifact": false,
228
+ "project": "lerobot",
229
+ "entity": null,
230
+ "notes": null,
231
+ "run_id": null,
232
+ "mode": null,
233
+ "add_tags": true
234
+ },
235
+ "peft": null,
236
+ "job": {
237
+ "target": null,
238
+ "image": "huggingface/lerobot-gpu:latest",
239
+ "timeout": "2d",
240
+ "detach": false,
241
+ "tags": []
242
+ },
243
+ "save_checkpoint_to_hub": false,
244
+ "sample_weighting": null,
245
+ "rename_map": {},
246
+ "checkpoint_path": null
247
+ }