Hugging Face's logo

facebook
/
sapiens2-pointmap-5b

Depth Estimation
sapiens
sapiens2
human-centric
pointmap
Model card Files
xet
 Community
2

Add HF-compatible model.safetensors, config.json, and preprocessor_config.json

#1
by guarin HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+271
-0
Files changed (3) hide show
  1. config.json +239 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +29 -0
config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_layernorm": true,
3
+ "architectures": [
4
+ "Sapiens2ForPointmapEstimation"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "drop_path_rate": 0.0,
8
+ "flip_pairs": null,
9
+ "head_config": {
10
+ "_name_or_path": "",
11
+ "architectures": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "conv_kernel_size": 1,
14
+ "conv_kernel_sizes": [
15
+ 3,
16
+ 3,
17
+ 3
18
+ ],
19
+ "conv_out_channels": [
20
+ 128,
21
+ 64,
22
+ 32
23
+ ],
24
+ "dtype": null,
25
+ "id2label": {
26
+ "0": "LABEL_0",
27
+ "1": "LABEL_1"
28
+ },
29
+ "is_encoder_decoder": false,
30
+ "label2id": {
31
+ "LABEL_0": 0,
32
+ "LABEL_1": 1
33
+ },
34
+ "model_type": "sapiens2_head",
35
+ "output_attentions": false,
36
+ "output_hidden_states": false,
37
+ "problem_type": null,
38
+ "return_dict": true,
39
+ "scale_conv_kernel_size": 1,
40
+ "scale_conv_kernel_sizes": [
41
+ 1,
42
+ 1,
43
+ 1
44
+ ],
45
+ "scale_conv_out_channels": [
46
+ 1536,
47
+ 512,
48
+ 128
49
+ ],
50
+ "scale_final_hidden_sizes": [
51
+ 512,
52
+ 128
53
+ ],
54
+ "scale_final_input_size": 6144,
55
+ "upsample_kernel_size": 4,
56
+ "upsample_kernel_sizes": [
57
+ 3,
58
+ 3,
59
+ 3,
60
+ 3
61
+ ],
62
+ "upsample_out_channels": [
63
+ 1536,
64
+ 768,
65
+ 768,
66
+ 768
67
+ ],
68
+ "use_pixel_shuffle": true
69
+ },
70
+ "hidden_act": "silu",
71
+ "hidden_size": 2432,
72
+ "id2label": {
73
+ "0": "LABEL_0",
74
+ "1": "LABEL_1",
75
+ "2": "LABEL_2"
76
+ },
77
+ "image_size": [
78
+ 1024,
79
+ 768
80
+ ],
81
+ "initializer_range": 0.02,
82
+ "intermediate_size": 9728,
83
+ "key_bias": true,
84
+ "label2id": {
85
+ "LABEL_0": 0,
86
+ "LABEL_1": 1,
87
+ "LABEL_2": 2
88
+ },
89
+ "layer_norm_eps": 1e-05,
90
+ "layerscale_value": 1.0,
91
+ "mlp_bias": true,
92
+ "model_type": "sapiens2",
93
+ "normalize_backbone_outputs": true,
94
+ "num_attention_heads": 32,
95
+ "num_channels": 3,
96
+ "num_first_full_attention_layers": 8,
97
+ "num_hidden_layers": 56,
98
+ "num_key_value_attention_heads": 16,
99
+ "num_key_value_heads_per_layer": [
100
+ 32,
101
+ 32,
102
+ 32,
103
+ 32,
104
+ 32,
105
+ 32,
106
+ 32,
107
+ 32,
108
+ 16,
109
+ 16,
110
+ 16,
111
+ 16,
112
+ 16,
113
+ 16,
114
+ 16,
115
+ 16,
116
+ 16,
117
+ 16,
118
+ 16,
119
+ 16,
120
+ 16,
121
+ 16,
122
+ 16,
123
+ 16,
124
+ 16,
125
+ 16,
126
+ 16,
127
+ 16,
128
+ 16,
129
+ 16,
130
+ 16,
131
+ 16,
132
+ 16,
133
+ 16,
134
+ 16,
135
+ 16,
136
+ 16,
137
+ 16,
138
+ 16,
139
+ 16,
140
+ 16,
141
+ 16,
142
+ 16,
143
+ 16,
144
+ 16,
145
+ 16,
146
+ 16,
147
+ 16,
148
+ 32,
149
+ 32,
150
+ 32,
151
+ 32,
152
+ 32,
153
+ 32,
154
+ 32,
155
+ 32
156
+ ],
157
+ "num_last_full_attention_layers": 8,
158
+ "num_register_tokens": 8,
159
+ "out_features": [
160
+ "stage56"
161
+ ],
162
+ "out_indices": [
163
+ 56
164
+ ],
165
+ "patch_size": 16,
166
+ "pos_embed_jitter": null,
167
+ "pos_embed_rescale": 2.0,
168
+ "pos_embed_shift": null,
169
+ "proj_bias": true,
170
+ "query_bias": true,
171
+ "reshape_hidden_states": true,
172
+ "rms_norm_eps": 1e-06,
173
+ "rope_theta": 100.0,
174
+ "semantic_loss_ignore_index": 255,
175
+ "stage_names": [
176
+ "stem",
177
+ "stage1",
178
+ "stage2",
179
+ "stage3",
180
+ "stage4",
181
+ "stage5",
182
+ "stage6",
183
+ "stage7",
184
+ "stage8",
185
+ "stage9",
186
+ "stage10",
187
+ "stage11",
188
+ "stage12",
189
+ "stage13",
190
+ "stage14",
191
+ "stage15",
192
+ "stage16",
193
+ "stage17",
194
+ "stage18",
195
+ "stage19",
196
+ "stage20",
197
+ "stage21",
198
+ "stage22",
199
+ "stage23",
200
+ "stage24",
201
+ "stage25",
202
+ "stage26",
203
+ "stage27",
204
+ "stage28",
205
+ "stage29",
206
+ "stage30",
207
+ "stage31",
208
+ "stage32",
209
+ "stage33",
210
+ "stage34",
211
+ "stage35",
212
+ "stage36",
213
+ "stage37",
214
+ "stage38",
215
+ "stage39",
216
+ "stage40",
217
+ "stage41",
218
+ "stage42",
219
+ "stage43",
220
+ "stage44",
221
+ "stage45",
222
+ "stage46",
223
+ "stage47",
224
+ "stage48",
225
+ "stage49",
226
+ "stage50",
227
+ "stage51",
228
+ "stage52",
229
+ "stage53",
230
+ "stage54",
231
+ "stage55",
232
+ "stage56"
233
+ ],
234
+ "transformers_version": "5.10.0.dev0",
235
+ "use_gated_mlp": true,
236
+ "use_mask_token": false,
237
+ "use_qk_norm": true,
238
+ "value_bias": true
239
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90515ff234b4dca1da1ce3744d03670fb1b5bb985b6554d8e6e358c37ad218d2
3
+ size 21393490254
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": false,
7
+ "do_normalize": true,
8
+ "do_pad": true,
9
+ "do_reduce_labels": false,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "image_mean": [
13
+ 0.485,
14
+ 0.456,
15
+ 0.406
16
+ ],
17
+ "image_processor_type": "Sapiens2ImageProcessor",
18
+ "image_std": [
19
+ 0.229,
20
+ 0.224,
21
+ 0.225
22
+ ],
23
+ "resample": 2,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 1024,
27
+ "width": 768
28
+ }
29
+ }