Hugging Face's logo

YinXuanLi
/
diffusion_v2

Safetensors
Model card Files
xet
 Community
YinXuanLi commited on
Commit
58a6c38
·
verified ·
1 Parent(s): 8eddd98

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +95 -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 +229 -0
config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 2,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 9
9
+ ]
10
+ },
11
+ "observation.images.wrist": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.images.front": {
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
+ 8
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "use_amp": false,
38
+ "use_peft": false,
39
+ "push_to_hub": true,
40
+ "repo_id": "YinXuanLi/diffusion_v2",
41
+ "private": null,
42
+ "tags": null,
43
+ "license": null,
44
+ "pretrained_path": null,
45
+ "horizon": 16,
46
+ "n_action_steps": 8,
47
+ "normalization_mapping": {
48
+ "VISUAL": "MEAN_STD",
49
+ "STATE": "MIN_MAX",
50
+ "ACTION": "MIN_MAX"
51
+ },
52
+ "drop_n_last_frames": 7,
53
+ "vision_backbone": "resnet18",
54
+ "resize_shape": [
55
+ 240,
56
+ 320
57
+ ],
58
+ "crop_ratio": 1.0,
59
+ "crop_shape": null,
60
+ "crop_is_random": true,
61
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
62
+ "use_group_norm": false,
63
+ "spatial_softmax_num_keypoints": 32,
64
+ "use_separate_rgb_encoder_per_camera": true,
65
+ "down_dims": [
66
+ 512,
67
+ 1024,
68
+ 2048
69
+ ],
70
+ "kernel_size": 5,
71
+ "n_groups": 8,
72
+ "diffusion_step_embed_dim": 128,
73
+ "use_film_scale_modulation": true,
74
+ "noise_scheduler_type": "DDIM",
75
+ "num_train_timesteps": 100,
76
+ "beta_schedule": "squaredcos_cap_v2",
77
+ "beta_start": 0.0001,
78
+ "beta_end": 0.02,
79
+ "prediction_type": "epsilon",
80
+ "clip_sample": true,
81
+ "clip_sample_range": 1.0,
82
+ "num_inference_steps": 10,
83
+ "compile_model": false,
84
+ "compile_mode": "reduce-overhead",
85
+ "do_mask_loss_for_padding": false,
86
+ "optimizer_lr": 0.0001,
87
+ "optimizer_betas": [
88
+ 0.95,
89
+ 0.999
90
+ ],
91
+ "optimizer_eps": 1e-08,
92
+ "optimizer_weight_decay": 1e-06,
93
+ "scheduler_name": "cosine",
94
+ "scheduler_warmup_steps": 500
95
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea161afc67514a7a87dfd212788705744751330a041aa71f6ea6d173c97c3b0
3
+ size 1112121896
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
+ 8
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 sha256:382f31c4ba02db58f1ee543f339fd18039ec13c009093ed0629c18baceb63be1
3
+ size 7756
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
+ 9
30
+ ]
31
+ },
32
+ "observation.images.wrist": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 480,
37
+ 640
38
+ ]
39
+ },
40
+ "observation.images.front": {
41
+ "type": "VISUAL",
42
+ "shape": [
43
+ 3,
44
+ 480,
45
+ 640
46
+ ]
47
+ },
48
+ "action": {
49
+ "type": "ACTION",
50
+ "shape": [
51
+ 8
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 sha256:382f31c4ba02db58f1ee543f339fd18039ec13c009093ed0629c18baceb63be1
3
+ size 7756
train_config.json ADDED
@@ -0,0 +1,229 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "YinXuanLi/gen_dataset",
4
+ "root": null,
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": null,
78
+ "use_imagenet_stats": true,
79
+ "video_backend": "pyav",
80
+ "streaming": false
81
+ },
82
+ "env": null,
83
+ "policy": {
84
+ "type": "diffusion",
85
+ "n_obs_steps": 2,
86
+ "input_features": {
87
+ "observation.state": {
88
+ "type": "STATE",
89
+ "shape": [
90
+ 9
91
+ ]
92
+ },
93
+ "observation.images.wrist": {
94
+ "type": "VISUAL",
95
+ "shape": [
96
+ 3,
97
+ 480,
98
+ 640
99
+ ]
100
+ },
101
+ "observation.images.front": {
102
+ "type": "VISUAL",
103
+ "shape": [
104
+ 3,
105
+ 480,
106
+ 640
107
+ ]
108
+ }
109
+ },
110
+ "output_features": {
111
+ "action": {
112
+ "type": "ACTION",
113
+ "shape": [
114
+ 8
115
+ ]
116
+ }
117
+ },
118
+ "device": "cuda",
119
+ "use_amp": false,
120
+ "use_peft": false,
121
+ "push_to_hub": true,
122
+ "repo_id": "YinXuanLi/diffusion_v2",
123
+ "private": null,
124
+ "tags": null,
125
+ "license": null,
126
+ "pretrained_path": null,
127
+ "horizon": 16,
128
+ "n_action_steps": 8,
129
+ "normalization_mapping": {
130
+ "VISUAL": "MEAN_STD",
131
+ "STATE": "MIN_MAX",
132
+ "ACTION": "MIN_MAX"
133
+ },
134
+ "drop_n_last_frames": 7,
135
+ "vision_backbone": "resnet18",
136
+ "resize_shape": [
137
+ 240,
138
+ 320
139
+ ],
140
+ "crop_ratio": 1.0,
141
+ "crop_shape": null,
142
+ "crop_is_random": true,
143
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
144
+ "use_group_norm": false,
145
+ "spatial_softmax_num_keypoints": 32,
146
+ "use_separate_rgb_encoder_per_camera": true,
147
+ "down_dims": [
148
+ 512,
149
+ 1024,
150
+ 2048
151
+ ],
152
+ "kernel_size": 5,
153
+ "n_groups": 8,
154
+ "diffusion_step_embed_dim": 128,
155
+ "use_film_scale_modulation": true,
156
+ "noise_scheduler_type": "DDIM",
157
+ "num_train_timesteps": 100,
158
+ "beta_schedule": "squaredcos_cap_v2",
159
+ "beta_start": 0.0001,
160
+ "beta_end": 0.02,
161
+ "prediction_type": "epsilon",
162
+ "clip_sample": true,
163
+ "clip_sample_range": 1.0,
164
+ "num_inference_steps": 10,
165
+ "compile_model": false,
166
+ "compile_mode": "reduce-overhead",
167
+ "do_mask_loss_for_padding": false,
168
+ "optimizer_lr": 0.0001,
169
+ "optimizer_betas": [
170
+ 0.95,
171
+ 0.999
172
+ ],
173
+ "optimizer_eps": 1e-08,
174
+ "optimizer_weight_decay": 1e-06,
175
+ "scheduler_name": "cosine",
176
+ "scheduler_warmup_steps": 500
177
+ },
178
+ "output_dir": "outputs/train/diffusion_cupstacking_v2",
179
+ "job_name": "cup_diff_v2",
180
+ "resume": false,
181
+ "seed": 1000,
182
+ "num_workers": 4,
183
+ "batch_size": 16,
184
+ "steps": 100000,
185
+ "eval_freq": 5000,
186
+ "log_freq": 200,
187
+ "tolerance_s": 0.0001,
188
+ "save_checkpoint": true,
189
+ "save_freq": 5000,
190
+ "use_policy_training_preset": true,
191
+ "optimizer": {
192
+ "type": "adam",
193
+ "lr": 0.0001,
194
+ "weight_decay": 1e-06,
195
+ "grad_clip_norm": 10.0,
196
+ "betas": [
197
+ 0.95,
198
+ 0.999
199
+ ],
200
+ "eps": 1e-08
201
+ },
202
+ "scheduler": {
203
+ "type": "diffuser",
204
+ "num_warmup_steps": 500,
205
+ "name": "cosine"
206
+ },
207
+ "eval": {
208
+ "n_episodes": 50,
209
+ "batch_size": 50,
210
+ "use_async_envs": false
211
+ },
212
+ "wandb": {
213
+ "enable": true,
214
+ "disable_artifact": false,
215
+ "project": "lerobot",
216
+ "entity": null,
217
+ "notes": null,
218
+ "run_id": "8oxfx1vs",
219
+ "mode": null
220
+ },
221
+ "peft": null,
222
+ "use_rabc": false,
223
+ "rabc_progress_path": null,
224
+ "rabc_kappa": 0.01,
225
+ "rabc_epsilon": 1e-06,
226
+ "rabc_head_mode": "sparse",
227
+ "rename_map": {},
228
+ "checkpoint_path": null
229
+ }