Upload CLIPSegForImageSegmentation
Browse files- config.json +330 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_commit_hash": null,
|
3 |
+
"architectures": [
|
4 |
+
"CLIPSegForImageSegmentation"
|
5 |
+
],
|
6 |
+
"conditional_layer": 0,
|
7 |
+
"decoder_attention_dropout": 0.0,
|
8 |
+
"decoder_hidden_act": "quick_gelu",
|
9 |
+
"decoder_intermediate_size": 2048,
|
10 |
+
"decoder_num_attention_heads": 4,
|
11 |
+
"extract_layers": [
|
12 |
+
3,
|
13 |
+
6,
|
14 |
+
9
|
15 |
+
],
|
16 |
+
"initializer_factor": 1.0,
|
17 |
+
"logit_scale_init_value": 2.6592,
|
18 |
+
"model_type": "clipseg",
|
19 |
+
"projection_dim": 512,
|
20 |
+
"reduce_dim": 64,
|
21 |
+
"text_config": {
|
22 |
+
"_name_or_path": "",
|
23 |
+
"add_cross_attention": false,
|
24 |
+
"architectures": null,
|
25 |
+
"attention_dropout": 0.0,
|
26 |
+
"bad_words_ids": null,
|
27 |
+
"begin_suppress_tokens": null,
|
28 |
+
"bos_token_id": 0,
|
29 |
+
"chunk_size_feed_forward": 0,
|
30 |
+
"cross_attention_hidden_size": null,
|
31 |
+
"decoder_start_token_id": null,
|
32 |
+
"diversity_penalty": 0.0,
|
33 |
+
"do_sample": false,
|
34 |
+
"dropout": 0.0,
|
35 |
+
"early_stopping": false,
|
36 |
+
"encoder_no_repeat_ngram_size": 0,
|
37 |
+
"eos_token_id": 2,
|
38 |
+
"exponential_decay_length_penalty": null,
|
39 |
+
"finetuning_task": null,
|
40 |
+
"forced_bos_token_id": null,
|
41 |
+
"forced_eos_token_id": null,
|
42 |
+
"hidden_act": "quick_gelu",
|
43 |
+
"hidden_size": 512,
|
44 |
+
"id2label": {
|
45 |
+
"0": "LABEL_0",
|
46 |
+
"1": "LABEL_1"
|
47 |
+
},
|
48 |
+
"initializer_factor": 1.0,
|
49 |
+
"initializer_range": 0.02,
|
50 |
+
"intermediate_size": 2048,
|
51 |
+
"is_decoder": false,
|
52 |
+
"is_encoder_decoder": false,
|
53 |
+
"label2id": {
|
54 |
+
"LABEL_0": 0,
|
55 |
+
"LABEL_1": 1
|
56 |
+
},
|
57 |
+
"layer_norm_eps": 1e-05,
|
58 |
+
"length_penalty": 1.0,
|
59 |
+
"max_length": 20,
|
60 |
+
"max_position_embeddings": 77,
|
61 |
+
"min_length": 0,
|
62 |
+
"model_type": "clipseg_text_model",
|
63 |
+
"no_repeat_ngram_size": 0,
|
64 |
+
"num_attention_heads": 8,
|
65 |
+
"num_beam_groups": 1,
|
66 |
+
"num_beams": 1,
|
67 |
+
"num_hidden_layers": 12,
|
68 |
+
"num_return_sequences": 1,
|
69 |
+
"output_attentions": false,
|
70 |
+
"output_hidden_states": false,
|
71 |
+
"output_scores": false,
|
72 |
+
"pad_token_id": 1,
|
73 |
+
"prefix": null,
|
74 |
+
"problem_type": null,
|
75 |
+
"pruned_heads": {},
|
76 |
+
"remove_invalid_values": false,
|
77 |
+
"repetition_penalty": 1.0,
|
78 |
+
"return_dict": true,
|
79 |
+
"return_dict_in_generate": false,
|
80 |
+
"sep_token_id": null,
|
81 |
+
"suppress_tokens": null,
|
82 |
+
"task_specific_params": null,
|
83 |
+
"temperature": 1.0,
|
84 |
+
"tf_legacy_loss": false,
|
85 |
+
"tie_encoder_decoder": false,
|
86 |
+
"tie_word_embeddings": true,
|
87 |
+
"tokenizer_class": null,
|
88 |
+
"top_k": 50,
|
89 |
+
"top_p": 1.0,
|
90 |
+
"torch_dtype": null,
|
91 |
+
"torchscript": false,
|
92 |
+
"transformers_version": "4.25.0.dev0",
|
93 |
+
"typical_p": 1.0,
|
94 |
+
"use_bfloat16": false,
|
95 |
+
"vocab_size": 49408
|
96 |
+
},
|
97 |
+
"text_config_dict": {
|
98 |
+
"_name_or_path": "",
|
99 |
+
"add_cross_attention": false,
|
100 |
+
"architectures": null,
|
101 |
+
"attention_dropout": 0.0,
|
102 |
+
"bad_words_ids": null,
|
103 |
+
"begin_suppress_tokens": null,
|
104 |
+
"bos_token_id": 0,
|
105 |
+
"chunk_size_feed_forward": 0,
|
106 |
+
"cross_attention_hidden_size": null,
|
107 |
+
"decoder_start_token_id": null,
|
108 |
+
"diversity_penalty": 0.0,
|
109 |
+
"do_sample": false,
|
110 |
+
"dropout": 0.0,
|
111 |
+
"early_stopping": false,
|
112 |
+
"encoder_no_repeat_ngram_size": 0,
|
113 |
+
"eos_token_id": 2,
|
114 |
+
"exponential_decay_length_penalty": null,
|
115 |
+
"finetuning_task": null,
|
116 |
+
"forced_bos_token_id": null,
|
117 |
+
"forced_eos_token_id": null,
|
118 |
+
"hidden_act": "quick_gelu",
|
119 |
+
"hidden_size": 512,
|
120 |
+
"id2label": {
|
121 |
+
"0": "LABEL_0",
|
122 |
+
"1": "LABEL_1"
|
123 |
+
},
|
124 |
+
"initializer_factor": 1.0,
|
125 |
+
"initializer_range": 0.02,
|
126 |
+
"intermediate_size": 2048,
|
127 |
+
"is_decoder": false,
|
128 |
+
"is_encoder_decoder": false,
|
129 |
+
"label2id": {
|
130 |
+
"LABEL_0": 0,
|
131 |
+
"LABEL_1": 1
|
132 |
+
},
|
133 |
+
"layer_norm_eps": 1e-05,
|
134 |
+
"length_penalty": 1.0,
|
135 |
+
"max_length": 20,
|
136 |
+
"max_position_embeddings": 77,
|
137 |
+
"min_length": 0,
|
138 |
+
"model_type": "clipseg_text_model",
|
139 |
+
"no_repeat_ngram_size": 0,
|
140 |
+
"num_attention_heads": 8,
|
141 |
+
"num_beam_groups": 1,
|
142 |
+
"num_beams": 1,
|
143 |
+
"num_hidden_layers": 12,
|
144 |
+
"num_return_sequences": 1,
|
145 |
+
"output_attentions": false,
|
146 |
+
"output_hidden_states": false,
|
147 |
+
"output_scores": false,
|
148 |
+
"pad_token_id": 1,
|
149 |
+
"prefix": null,
|
150 |
+
"problem_type": null,
|
151 |
+
"pruned_heads": {},
|
152 |
+
"remove_invalid_values": false,
|
153 |
+
"repetition_penalty": 1.0,
|
154 |
+
"return_dict": true,
|
155 |
+
"return_dict_in_generate": false,
|
156 |
+
"sep_token_id": null,
|
157 |
+
"suppress_tokens": null,
|
158 |
+
"task_specific_params": null,
|
159 |
+
"temperature": 1.0,
|
160 |
+
"tf_legacy_loss": false,
|
161 |
+
"tie_encoder_decoder": false,
|
162 |
+
"tie_word_embeddings": true,
|
163 |
+
"tokenizer_class": null,
|
164 |
+
"top_k": 50,
|
165 |
+
"top_p": 1.0,
|
166 |
+
"torch_dtype": null,
|
167 |
+
"torchscript": false,
|
168 |
+
"transformers_version": "4.25.0.dev0",
|
169 |
+
"typical_p": 1.0,
|
170 |
+
"use_bfloat16": false,
|
171 |
+
"vocab_size": 49408
|
172 |
+
},
|
173 |
+
"torch_dtype": "float32",
|
174 |
+
"transformers_version": null,
|
175 |
+
"use_complex_transposed_convolution": false,
|
176 |
+
"vision_config": {
|
177 |
+
"_name_or_path": "",
|
178 |
+
"add_cross_attention": false,
|
179 |
+
"architectures": null,
|
180 |
+
"attention_dropout": 0.0,
|
181 |
+
"bad_words_ids": null,
|
182 |
+
"begin_suppress_tokens": null,
|
183 |
+
"bos_token_id": null,
|
184 |
+
"chunk_size_feed_forward": 0,
|
185 |
+
"cross_attention_hidden_size": null,
|
186 |
+
"decoder_start_token_id": null,
|
187 |
+
"diversity_penalty": 0.0,
|
188 |
+
"do_sample": false,
|
189 |
+
"dropout": 0.0,
|
190 |
+
"early_stopping": false,
|
191 |
+
"encoder_no_repeat_ngram_size": 0,
|
192 |
+
"eos_token_id": null,
|
193 |
+
"exponential_decay_length_penalty": null,
|
194 |
+
"finetuning_task": null,
|
195 |
+
"forced_bos_token_id": null,
|
196 |
+
"forced_eos_token_id": null,
|
197 |
+
"hidden_act": "quick_gelu",
|
198 |
+
"hidden_size": 768,
|
199 |
+
"id2label": {
|
200 |
+
"0": "LABEL_0",
|
201 |
+
"1": "LABEL_1"
|
202 |
+
},
|
203 |
+
"image_size": 224,
|
204 |
+
"initializer_factor": 1.0,
|
205 |
+
"initializer_range": 0.02,
|
206 |
+
"intermediate_size": 3072,
|
207 |
+
"is_decoder": false,
|
208 |
+
"is_encoder_decoder": false,
|
209 |
+
"label2id": {
|
210 |
+
"LABEL_0": 0,
|
211 |
+
"LABEL_1": 1
|
212 |
+
},
|
213 |
+
"layer_norm_eps": 1e-05,
|
214 |
+
"length_penalty": 1.0,
|
215 |
+
"max_length": 20,
|
216 |
+
"min_length": 0,
|
217 |
+
"model_type": "clipseg_vision_model",
|
218 |
+
"no_repeat_ngram_size": 0,
|
219 |
+
"num_attention_heads": 12,
|
220 |
+
"num_beam_groups": 1,
|
221 |
+
"num_beams": 1,
|
222 |
+
"num_channels": 3,
|
223 |
+
"num_hidden_layers": 12,
|
224 |
+
"num_return_sequences": 1,
|
225 |
+
"output_attentions": false,
|
226 |
+
"output_hidden_states": false,
|
227 |
+
"output_scores": false,
|
228 |
+
"pad_token_id": null,
|
229 |
+
"patch_size": 16,
|
230 |
+
"prefix": null,
|
231 |
+
"problem_type": null,
|
232 |
+
"pruned_heads": {},
|
233 |
+
"remove_invalid_values": false,
|
234 |
+
"repetition_penalty": 1.0,
|
235 |
+
"return_dict": true,
|
236 |
+
"return_dict_in_generate": false,
|
237 |
+
"sep_token_id": null,
|
238 |
+
"suppress_tokens": null,
|
239 |
+
"task_specific_params": null,
|
240 |
+
"temperature": 1.0,
|
241 |
+
"tf_legacy_loss": false,
|
242 |
+
"tie_encoder_decoder": false,
|
243 |
+
"tie_word_embeddings": true,
|
244 |
+
"tokenizer_class": null,
|
245 |
+
"top_k": 50,
|
246 |
+
"top_p": 1.0,
|
247 |
+
"torch_dtype": null,
|
248 |
+
"torchscript": false,
|
249 |
+
"transformers_version": "4.25.0.dev0",
|
250 |
+
"typical_p": 1.0,
|
251 |
+
"use_bfloat16": false
|
252 |
+
},
|
253 |
+
"vision_config_dict": {
|
254 |
+
"_name_or_path": "",
|
255 |
+
"add_cross_attention": false,
|
256 |
+
"architectures": null,
|
257 |
+
"attention_dropout": 0.0,
|
258 |
+
"bad_words_ids": null,
|
259 |
+
"begin_suppress_tokens": null,
|
260 |
+
"bos_token_id": null,
|
261 |
+
"chunk_size_feed_forward": 0,
|
262 |
+
"cross_attention_hidden_size": null,
|
263 |
+
"decoder_start_token_id": null,
|
264 |
+
"diversity_penalty": 0.0,
|
265 |
+
"do_sample": false,
|
266 |
+
"dropout": 0.0,
|
267 |
+
"early_stopping": false,
|
268 |
+
"encoder_no_repeat_ngram_size": 0,
|
269 |
+
"eos_token_id": null,
|
270 |
+
"exponential_decay_length_penalty": null,
|
271 |
+
"finetuning_task": null,
|
272 |
+
"forced_bos_token_id": null,
|
273 |
+
"forced_eos_token_id": null,
|
274 |
+
"hidden_act": "quick_gelu",
|
275 |
+
"hidden_size": 768,
|
276 |
+
"id2label": {
|
277 |
+
"0": "LABEL_0",
|
278 |
+
"1": "LABEL_1"
|
279 |
+
},
|
280 |
+
"image_size": 224,
|
281 |
+
"initializer_factor": 1.0,
|
282 |
+
"initializer_range": 0.02,
|
283 |
+
"intermediate_size": 3072,
|
284 |
+
"is_decoder": false,
|
285 |
+
"is_encoder_decoder": false,
|
286 |
+
"label2id": {
|
287 |
+
"LABEL_0": 0,
|
288 |
+
"LABEL_1": 1
|
289 |
+
},
|
290 |
+
"layer_norm_eps": 1e-05,
|
291 |
+
"length_penalty": 1.0,
|
292 |
+
"max_length": 20,
|
293 |
+
"min_length": 0,
|
294 |
+
"model_type": "clipseg_vision_model",
|
295 |
+
"no_repeat_ngram_size": 0,
|
296 |
+
"num_attention_heads": 12,
|
297 |
+
"num_beam_groups": 1,
|
298 |
+
"num_beams": 1,
|
299 |
+
"num_channels": 3,
|
300 |
+
"num_hidden_layers": 12,
|
301 |
+
"num_return_sequences": 1,
|
302 |
+
"output_attentions": false,
|
303 |
+
"output_hidden_states": false,
|
304 |
+
"output_scores": false,
|
305 |
+
"pad_token_id": null,
|
306 |
+
"patch_size": 16,
|
307 |
+
"prefix": null,
|
308 |
+
"problem_type": null,
|
309 |
+
"pruned_heads": {},
|
310 |
+
"remove_invalid_values": false,
|
311 |
+
"repetition_penalty": 1.0,
|
312 |
+
"return_dict": true,
|
313 |
+
"return_dict_in_generate": false,
|
314 |
+
"sep_token_id": null,
|
315 |
+
"suppress_tokens": null,
|
316 |
+
"task_specific_params": null,
|
317 |
+
"temperature": 1.0,
|
318 |
+
"tf_legacy_loss": false,
|
319 |
+
"tie_encoder_decoder": false,
|
320 |
+
"tie_word_embeddings": true,
|
321 |
+
"tokenizer_class": null,
|
322 |
+
"top_k": 50,
|
323 |
+
"top_p": 1.0,
|
324 |
+
"torch_dtype": null,
|
325 |
+
"torchscript": false,
|
326 |
+
"transformers_version": "4.25.0.dev0",
|
327 |
+
"typical_p": 1.0,
|
328 |
+
"use_bfloat16": false
|
329 |
+
}
|
330 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79c104db0649852953b74d432153f7c3392d11d5246f56fce93476674f09becb
|
3 |
+
size 602928233
|