Hugging Face's logo

learner1119
/
act_vine2_sim_da

Robotics
LeRobot
Safetensors
act
Model card Files
xet
 Community
learner1119 commited on
Commit
afc407c
·
verified ·
1 Parent(s): 48a5c81

Upload policy weights, train config and readme

Browse files
Files changed (4) hide show
  1. README.md +62 -0
  2. config.json +71 -0
  3. model.safetensors +3 -0
  4. train_config.json +482 -0
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets: local/VINE2_sim_420_da
3
+ library_name: lerobot
4
+ license: apache-2.0
5
+ model_name: act
6
+ pipeline_tag: robotics
7
+ tags:
8
+ - robotics
9
+ - lerobot
10
+ - act
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 ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.images.cam_head": {
6
+ "type": "VISUAL",
7
+ "shape": [
8
+ 3,
9
+ 376,
10
+ 672
11
+ ]
12
+ },
13
+ "observation.images.cam_wrist_left": {
14
+ "type": "VISUAL",
15
+ "shape": [
16
+ 3,
17
+ 240,
18
+ 424
19
+ ]
20
+ },
21
+ "observation.state": {
22
+ "type": "STATE",
23
+ "shape": [
24
+ 8
25
+ ]
26
+ }
27
+ },
28
+ "output_features": {
29
+ "action": {
30
+ "type": "ACTION",
31
+ "shape": [
32
+ 8
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "use_amp": false,
38
+ "use_peft": false,
39
+ "push_to_hub": true,
40
+ "repo_id": "learner1119/act_vine2_sim_da",
41
+ "private": null,
42
+ "tags": null,
43
+ "license": null,
44
+ "pretrained_path": null,
45
+ "chunk_size": 20,
46
+ "n_action_steps": 20,
47
+ "normalization_mapping": {
48
+ "VISUAL": "MEAN_STD",
49
+ "STATE": "MEAN_STD",
50
+ "ACTION": "MEAN_STD"
51
+ },
52
+ "vision_backbone": "resnet18",
53
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
54
+ "replace_final_stride_with_dilation": false,
55
+ "pre_norm": false,
56
+ "dim_model": 512,
57
+ "n_heads": 8,
58
+ "dim_feedforward": 3200,
59
+ "feedforward_activation": "relu",
60
+ "n_encoder_layers": 4,
61
+ "n_decoder_layers": 1,
62
+ "use_vae": true,
63
+ "latent_dim": 32,
64
+ "n_vae_encoder_layers": 4,
65
+ "temporal_ensemble_coeff": null,
66
+ "dropout": 0.1,
67
+ "kl_weight": 10.0,
68
+ "optimizer_lr": 1e-05,
69
+ "optimizer_weight_decay": 0.0001,
70
+ "optimizer_lr_backbone": 1e-05
71
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4d3afff8d45f9519b071b2696d51cff66efc60b5663115434e8b83ffc1d0bf4
3
+ size 206388440
train_config.json ADDED
@@ -0,0 +1,482 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "local/VINE2_sim_420_da",
4
+ "root": "/workspace/dataset/VINE2_sim_420_da",
5
+ "episodes": [
6
+ 0,
7
+ 1,
8
+ 2,
9
+ 3,
10
+ 4,
11
+ 5,
12
+ 6,
13
+ 7,
14
+ 8,
15
+ 9,
16
+ 10,
17
+ 11,
18
+ 12,
19
+ 13,
20
+ 14,
21
+ 15,
22
+ 16,
23
+ 17,
24
+ 18,
25
+ 19,
26
+ 21,
27
+ 22,
28
+ 23,
29
+ 24,
30
+ 25,
31
+ 26,
32
+ 27,
33
+ 28,
34
+ 29,
35
+ 30,
36
+ 31,
37
+ 32,
38
+ 33,
39
+ 34,
40
+ 35,
41
+ 36,
42
+ 37,
43
+ 38,
44
+ 39,
45
+ 40,
46
+ 41,
47
+ 42,
48
+ 43,
49
+ 44,
50
+ 45,
51
+ 46,
52
+ 47,
53
+ 49,
54
+ 50,
55
+ 51,
56
+ 52,
57
+ 53,
58
+ 54,
59
+ 55,
60
+ 56,
61
+ 57,
62
+ 58,
63
+ 59,
64
+ 60,
65
+ 61,
66
+ 62,
67
+ 63,
68
+ 64,
69
+ 65,
70
+ 66,
71
+ 67,
72
+ 68,
73
+ 69,
74
+ 70,
75
+ 72,
76
+ 73,
77
+ 74,
78
+ 76,
79
+ 77,
80
+ 78,
81
+ 79,
82
+ 80,
83
+ 81,
84
+ 82,
85
+ 83,
86
+ 84,
87
+ 85,
88
+ 86,
89
+ 87,
90
+ 88,
91
+ 89,
92
+ 90,
93
+ 91,
94
+ 92,
95
+ 93,
96
+ 94,
97
+ 95,
98
+ 96,
99
+ 97,
100
+ 98,
101
+ 99,
102
+ 100,
103
+ 101,
104
+ 102,
105
+ 103,
106
+ 104,
107
+ 105,
108
+ 106,
109
+ 107,
110
+ 108,
111
+ 109,
112
+ 110,
113
+ 112,
114
+ 113,
115
+ 114,
116
+ 115,
117
+ 116,
118
+ 117,
119
+ 118,
120
+ 119,
121
+ 120,
122
+ 121,
123
+ 122,
124
+ 123,
125
+ 124,
126
+ 125,
127
+ 126,
128
+ 127,
129
+ 129,
130
+ 130,
131
+ 131,
132
+ 133,
133
+ 134,
134
+ 135,
135
+ 136,
136
+ 137,
137
+ 138,
138
+ 139,
139
+ 140,
140
+ 141,
141
+ 142,
142
+ 143,
143
+ 145,
144
+ 146,
145
+ 147,
146
+ 148,
147
+ 149,
148
+ 150,
149
+ 151,
150
+ 152,
151
+ 153,
152
+ 154,
153
+ 156,
154
+ 157,
155
+ 159,
156
+ 160,
157
+ 161,
158
+ 162,
159
+ 163,
160
+ 164,
161
+ 165,
162
+ 166,
163
+ 167,
164
+ 168,
165
+ 169,
166
+ 170,
167
+ 171,
168
+ 172,
169
+ 173,
170
+ 174,
171
+ 175,
172
+ 176,
173
+ 177,
174
+ 178,
175
+ 179,
176
+ 180,
177
+ 181,
178
+ 182,
179
+ 184,
180
+ 185,
181
+ 186,
182
+ 187,
183
+ 188,
184
+ 189,
185
+ 190,
186
+ 191,
187
+ 192,
188
+ 193,
189
+ 194,
190
+ 195,
191
+ 196,
192
+ 198,
193
+ 199,
194
+ 200,
195
+ 201,
196
+ 202,
197
+ 203,
198
+ 204,
199
+ 205,
200
+ 206,
201
+ 208,
202
+ 209,
203
+ 210,
204
+ 211,
205
+ 212,
206
+ 213,
207
+ 214,
208
+ 216,
209
+ 217,
210
+ 218,
211
+ 219,
212
+ 220,
213
+ 221,
214
+ 222,
215
+ 223,
216
+ 224,
217
+ 225,
218
+ 226,
219
+ 227,
220
+ 228,
221
+ 229,
222
+ 230,
223
+ 231,
224
+ 232,
225
+ 233,
226
+ 234,
227
+ 235,
228
+ 236,
229
+ 237,
230
+ 238,
231
+ 239,
232
+ 240,
233
+ 241,
234
+ 242,
235
+ 243,
236
+ 245,
237
+ 246,
238
+ 247,
239
+ 249,
240
+ 250,
241
+ 251,
242
+ 252,
243
+ 253,
244
+ 254,
245
+ 255,
246
+ 256,
247
+ 257,
248
+ 259,
249
+ 260,
250
+ 262,
251
+ 263,
252
+ 264,
253
+ 265,
254
+ 266,
255
+ 267,
256
+ 268,
257
+ 269,
258
+ 270,
259
+ 271,
260
+ 273,
261
+ 274,
262
+ 275,
263
+ 276,
264
+ 277,
265
+ 278,
266
+ 279,
267
+ 280,
268
+ 281,
269
+ 282,
270
+ 283,
271
+ 284,
272
+ 285,
273
+ 286,
274
+ 287,
275
+ 288,
276
+ 289,
277
+ 290,
278
+ 291,
279
+ 292,
280
+ 293,
281
+ 294,
282
+ 295,
283
+ 296,
284
+ 297,
285
+ 299
286
+ ],
287
+ "image_transforms": {
288
+ "enable": false,
289
+ "max_num_transforms": 3,
290
+ "random_order": false,
291
+ "tfs": {
292
+ "brightness": {
293
+ "weight": 1.0,
294
+ "type": "ColorJitter",
295
+ "kwargs": {
296
+ "brightness": [
297
+ 0.8,
298
+ 1.2
299
+ ]
300
+ }
301
+ },
302
+ "contrast": {
303
+ "weight": 1.0,
304
+ "type": "ColorJitter",
305
+ "kwargs": {
306
+ "contrast": [
307
+ 0.8,
308
+ 1.2
309
+ ]
310
+ }
311
+ },
312
+ "saturation": {
313
+ "weight": 1.0,
314
+ "type": "ColorJitter",
315
+ "kwargs": {
316
+ "saturation": [
317
+ 0.5,
318
+ 1.5
319
+ ]
320
+ }
321
+ },
322
+ "hue": {
323
+ "weight": 1.0,
324
+ "type": "ColorJitter",
325
+ "kwargs": {
326
+ "hue": [
327
+ -0.05,
328
+ 0.05
329
+ ]
330
+ }
331
+ },
332
+ "sharpness": {
333
+ "weight": 1.0,
334
+ "type": "SharpnessJitter",
335
+ "kwargs": {
336
+ "sharpness": [
337
+ 0.5,
338
+ 1.5
339
+ ]
340
+ }
341
+ },
342
+ "affine": {
343
+ "weight": 1.0,
344
+ "type": "RandomAffine",
345
+ "kwargs": {
346
+ "degrees": [
347
+ -5.0,
348
+ 5.0
349
+ ],
350
+ "translate": [
351
+ 0.05,
352
+ 0.05
353
+ ]
354
+ }
355
+ }
356
+ }
357
+ },
358
+ "revision": null,
359
+ "use_imagenet_stats": true,
360
+ "video_backend": "pyav",
361
+ "streaming": false
362
+ },
363
+ "env": null,
364
+ "policy": {
365
+ "type": "act",
366
+ "n_obs_steps": 1,
367
+ "input_features": {
368
+ "observation.images.cam_head": {
369
+ "type": "VISUAL",
370
+ "shape": [
371
+ 3,
372
+ 376,
373
+ 672
374
+ ]
375
+ },
376
+ "observation.images.cam_wrist_left": {
377
+ "type": "VISUAL",
378
+ "shape": [
379
+ 3,
380
+ 240,
381
+ 424
382
+ ]
383
+ },
384
+ "observation.state": {
385
+ "type": "STATE",
386
+ "shape": [
387
+ 8
388
+ ]
389
+ }
390
+ },
391
+ "output_features": {
392
+ "action": {
393
+ "type": "ACTION",
394
+ "shape": [
395
+ 8
396
+ ]
397
+ }
398
+ },
399
+ "device": "cuda",
400
+ "use_amp": false,
401
+ "use_peft": false,
402
+ "push_to_hub": true,
403
+ "repo_id": "learner1119/act_vine2_sim_da",
404
+ "private": null,
405
+ "tags": null,
406
+ "license": null,
407
+ "pretrained_path": null,
408
+ "chunk_size": 20,
409
+ "n_action_steps": 20,
410
+ "normalization_mapping": {
411
+ "VISUAL": "MEAN_STD",
412
+ "STATE": "MEAN_STD",
413
+ "ACTION": "MEAN_STD"
414
+ },
415
+ "vision_backbone": "resnet18",
416
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
417
+ "replace_final_stride_with_dilation": false,
418
+ "pre_norm": false,
419
+ "dim_model": 512,
420
+ "n_heads": 8,
421
+ "dim_feedforward": 3200,
422
+ "feedforward_activation": "relu",
423
+ "n_encoder_layers": 4,
424
+ "n_decoder_layers": 1,
425
+ "use_vae": true,
426
+ "latent_dim": 32,
427
+ "n_vae_encoder_layers": 4,
428
+ "temporal_ensemble_coeff": null,
429
+ "dropout": 0.1,
430
+ "kl_weight": 10.0,
431
+ "optimizer_lr": 1e-05,
432
+ "optimizer_weight_decay": 0.0001,
433
+ "optimizer_lr_backbone": 1e-05
434
+ },
435
+ "output_dir": "/workspace/ckpt/act_vine2_sim_da",
436
+ "job_name": "act_vine2_sim_da",
437
+ "resume": false,
438
+ "seed": 1000,
439
+ "num_workers": 4,
440
+ "batch_size": 32,
441
+ "steps": 30000,
442
+ "eval_freq": 0,
443
+ "log_freq": 200,
444
+ "tolerance_s": 0.0001,
445
+ "save_checkpoint": true,
446
+ "save_freq": 15000,
447
+ "use_policy_training_preset": true,
448
+ "optimizer": {
449
+ "type": "adamw",
450
+ "lr": 1e-05,
451
+ "weight_decay": 0.0001,
452
+ "grad_clip_norm": 10.0,
453
+ "betas": [
454
+ 0.9,
455
+ 0.999
456
+ ],
457
+ "eps": 1e-08
458
+ },
459
+ "scheduler": null,
460
+ "eval": {
461
+ "n_episodes": 50,
462
+ "batch_size": 50,
463
+ "use_async_envs": false
464
+ },
465
+ "wandb": {
466
+ "enable": false,
467
+ "disable_artifact": false,
468
+ "project": "lerobot",
469
+ "entity": null,
470
+ "notes": null,
471
+ "run_id": null,
472
+ "mode": null
473
+ },
474
+ "peft": null,
475
+ "use_rabc": false,
476
+ "rabc_progress_path": null,
477
+ "rabc_kappa": 0.01,
478
+ "rabc_epsilon": 1e-06,
479
+ "rabc_head_mode": "sparse",
480
+ "rename_map": {},
481
+ "checkpoint_path": null
482
+ }