ybelkada commited on
Commit
bf4ebd0
1 Parent(s): a821219

Upload SamForImageSegmentation

Browse files
Files changed (2) hide show
  1. config.json +246 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "SamForImageSegmentation"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "initializer_range": 0.02,
8
+ "mask_decoder_config": {
9
+ "_name_or_path": "",
10
+ "add_cross_attention": false,
11
+ "architectures": null,
12
+ "attention_downsample_rate": 2,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": null,
16
+ "chunk_size_feed_forward": 0,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": null,
24
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "hidden_act": "relu",
29
+ "hidden_size": 256,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "iou_head_depth": 3,
35
+ "iou_head_hidden_dim": 256,
36
+ "is_decoder": false,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "min_length": 0,
45
+ "mlp_dim": 2048,
46
+ "model_type": "",
47
+ "no_repeat_ngram_size": 0,
48
+ "num_attention_heads": 8,
49
+ "num_beam_groups": 1,
50
+ "num_beams": 1,
51
+ "num_hidden_layers": 2,
52
+ "num_multimask_outputs": 3,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": null,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "repetition_penalty": 1.0,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "sep_token_id": null,
66
+ "suppress_tokens": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tf_legacy_loss": false,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": true,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": null,
76
+ "torchscript": false,
77
+ "transformers_version": "4.28.0.dev0",
78
+ "typical_p": 1.0,
79
+ "use_bfloat16": false
80
+ },
81
+ "model_type": "sam",
82
+ "prompt_encoder_config": {
83
+ "_name_or_path": "",
84
+ "add_cross_attention": false,
85
+ "architectures": null,
86
+ "bad_words_ids": null,
87
+ "begin_suppress_tokens": null,
88
+ "bos_token_id": null,
89
+ "chunk_size_feed_forward": 0,
90
+ "cross_attention_hidden_size": null,
91
+ "decoder_start_token_id": null,
92
+ "diversity_penalty": 0.0,
93
+ "do_sample": false,
94
+ "early_stopping": false,
95
+ "encoder_no_repeat_ngram_size": 0,
96
+ "eos_token_id": null,
97
+ "exponential_decay_length_penalty": null,
98
+ "finetuning_task": null,
99
+ "forced_bos_token_id": null,
100
+ "forced_eos_token_id": null,
101
+ "hidden_act": "gelu",
102
+ "hidden_size": 256,
103
+ "id2label": {
104
+ "0": "LABEL_0",
105
+ "1": "LABEL_1"
106
+ },
107
+ "image_embedding_size": 64,
108
+ "input_image_size": 1024,
109
+ "is_decoder": false,
110
+ "is_encoder_decoder": false,
111
+ "label2id": {
112
+ "LABEL_0": 0,
113
+ "LABEL_1": 1
114
+ },
115
+ "length_penalty": 1.0,
116
+ "mask_input_channels": 16,
117
+ "max_length": 20,
118
+ "min_length": 0,
119
+ "model_type": "",
120
+ "no_repeat_ngram_size": 0,
121
+ "num_beam_groups": 1,
122
+ "num_beams": 1,
123
+ "num_point_embeddings": 4,
124
+ "num_return_sequences": 1,
125
+ "output_attentions": false,
126
+ "output_hidden_states": false,
127
+ "output_scores": false,
128
+ "pad_token_id": null,
129
+ "patch_size": 16,
130
+ "prefix": null,
131
+ "problem_type": null,
132
+ "pruned_heads": {},
133
+ "remove_invalid_values": false,
134
+ "repetition_penalty": 1.0,
135
+ "return_dict": true,
136
+ "return_dict_in_generate": false,
137
+ "sep_token_id": null,
138
+ "suppress_tokens": null,
139
+ "task_specific_params": null,
140
+ "temperature": 1.0,
141
+ "tf_legacy_loss": false,
142
+ "tie_encoder_decoder": false,
143
+ "tie_word_embeddings": true,
144
+ "tokenizer_class": null,
145
+ "top_k": 50,
146
+ "top_p": 1.0,
147
+ "torch_dtype": null,
148
+ "torchscript": false,
149
+ "transformers_version": "4.28.0.dev0",
150
+ "typical_p": 1.0,
151
+ "use_bfloat16": false
152
+ },
153
+ "torch_dtype": "float16",
154
+ "transformers_version": null,
155
+ "vision_config": {
156
+ "_name_or_path": "",
157
+ "add_cross_attention": false,
158
+ "architectures": null,
159
+ "attention_dropout": 0.0,
160
+ "bad_words_ids": null,
161
+ "begin_suppress_tokens": null,
162
+ "bos_token_id": null,
163
+ "chunk_size_feed_forward": 0,
164
+ "cross_attention_hidden_size": null,
165
+ "decoder_start_token_id": null,
166
+ "diversity_penalty": 0.0,
167
+ "do_sample": false,
168
+ "dropout": 0.0,
169
+ "early_stopping": false,
170
+ "encoder_no_repeat_ngram_size": 0,
171
+ "eos_token_id": null,
172
+ "exponential_decay_length_penalty": null,
173
+ "finetuning_task": null,
174
+ "forced_bos_token_id": null,
175
+ "forced_eos_token_id": null,
176
+ "global_attn_indexes": [
177
+ 7,
178
+ 15,
179
+ 23,
180
+ 31
181
+ ],
182
+ "hidden_act": "gelu",
183
+ "hidden_size": 1280,
184
+ "id2label": {
185
+ "0": "LABEL_0",
186
+ "1": "LABEL_1"
187
+ },
188
+ "image_size": 1024,
189
+ "initializer_factor": 1.0,
190
+ "initializer_range": 1e-10,
191
+ "intermediate_size": 6144,
192
+ "is_decoder": false,
193
+ "is_encoder_decoder": false,
194
+ "label2id": {
195
+ "LABEL_0": 0,
196
+ "LABEL_1": 1
197
+ },
198
+ "layer_norm_eps": 1e-05,
199
+ "length_penalty": 1.0,
200
+ "max_length": 20,
201
+ "min_length": 0,
202
+ "mlp_ratio": 4.0,
203
+ "model_type": "sam_vision_model",
204
+ "no_repeat_ngram_size": 0,
205
+ "num_attention_heads": 16,
206
+ "num_beam_groups": 1,
207
+ "num_beams": 1,
208
+ "num_channels": 3,
209
+ "num_hidden_layers": 32,
210
+ "num_return_sequences": 1,
211
+ "output_attentions": false,
212
+ "output_channels": 256,
213
+ "output_hidden_states": false,
214
+ "output_scores": false,
215
+ "pad_token_id": null,
216
+ "patch_size": 16,
217
+ "prefix": null,
218
+ "problem_type": null,
219
+ "projection_dim": 512,
220
+ "pruned_heads": {},
221
+ "qkv_bias": true,
222
+ "rel_pos_zero_init": false,
223
+ "remove_invalid_values": false,
224
+ "repetition_penalty": 1.0,
225
+ "return_dict": true,
226
+ "return_dict_in_generate": false,
227
+ "sep_token_id": null,
228
+ "suppress_tokens": null,
229
+ "task_specific_params": null,
230
+ "temperature": 1.0,
231
+ "tf_legacy_loss": false,
232
+ "tie_encoder_decoder": false,
233
+ "tie_word_embeddings": true,
234
+ "tokenizer_class": null,
235
+ "top_k": 50,
236
+ "top_p": 1.0,
237
+ "torch_dtype": null,
238
+ "torchscript": false,
239
+ "transformers_version": "4.28.0.dev0",
240
+ "typical_p": 1.0,
241
+ "use_abs_pos": true,
242
+ "use_bfloat16": false,
243
+ "use_rel_pos": true,
244
+ "window_size": 14
245
+ }
246
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d9ced09901119ebcbf97b53ca9a3bb5c62ee746c8fbf206b947214427182ac0
3
+ size 1282379669