Upload DetrForObjectDetection
Browse files- config.json +217 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_commit_hash": "70120ba84d68ca1211e007c4fb61d0cd5424be54",
|
3 |
+
"_name_or_path": "facebook/detr-resnet-50",
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "relu",
|
6 |
+
"architectures": [
|
7 |
+
"DetrForObjectDetection"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"auxiliary_loss": false,
|
11 |
+
"backbone": null,
|
12 |
+
"backbone_config": {
|
13 |
+
"_name_or_path": "",
|
14 |
+
"add_cross_attention": false,
|
15 |
+
"architectures": null,
|
16 |
+
"bad_words_ids": null,
|
17 |
+
"begin_suppress_tokens": null,
|
18 |
+
"bos_token_id": null,
|
19 |
+
"chunk_size_feed_forward": 0,
|
20 |
+
"cross_attention_hidden_size": null,
|
21 |
+
"decoder_start_token_id": null,
|
22 |
+
"depths": [
|
23 |
+
3,
|
24 |
+
4,
|
25 |
+
6,
|
26 |
+
3
|
27 |
+
],
|
28 |
+
"diversity_penalty": 0.0,
|
29 |
+
"do_sample": false,
|
30 |
+
"downsample_in_first_stage": false,
|
31 |
+
"early_stopping": false,
|
32 |
+
"embedding_size": 64,
|
33 |
+
"encoder_no_repeat_ngram_size": 0,
|
34 |
+
"eos_token_id": null,
|
35 |
+
"exponential_decay_length_penalty": null,
|
36 |
+
"finetuning_task": null,
|
37 |
+
"forced_bos_token_id": null,
|
38 |
+
"forced_eos_token_id": null,
|
39 |
+
"hidden_act": "relu",
|
40 |
+
"hidden_sizes": [
|
41 |
+
256,
|
42 |
+
512,
|
43 |
+
1024,
|
44 |
+
2048
|
45 |
+
],
|
46 |
+
"id2label": {
|
47 |
+
"0": "LABEL_0",
|
48 |
+
"1": "LABEL_1"
|
49 |
+
},
|
50 |
+
"is_decoder": false,
|
51 |
+
"is_encoder_decoder": false,
|
52 |
+
"label2id": {
|
53 |
+
"LABEL_0": 0,
|
54 |
+
"LABEL_1": 1
|
55 |
+
},
|
56 |
+
"layer_type": "bottleneck",
|
57 |
+
"length_penalty": 1.0,
|
58 |
+
"max_length": 20,
|
59 |
+
"min_length": 0,
|
60 |
+
"model_type": "resnet",
|
61 |
+
"no_repeat_ngram_size": 0,
|
62 |
+
"num_beam_groups": 1,
|
63 |
+
"num_beams": 1,
|
64 |
+
"num_channels": 3,
|
65 |
+
"num_return_sequences": 1,
|
66 |
+
"out_features": [
|
67 |
+
"stage4"
|
68 |
+
],
|
69 |
+
"output_attentions": false,
|
70 |
+
"output_hidden_states": false,
|
71 |
+
"output_scores": false,
|
72 |
+
"pad_token_id": null,
|
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 |
+
"stage_names": [
|
82 |
+
"stem",
|
83 |
+
"stage1",
|
84 |
+
"stage2",
|
85 |
+
"stage3",
|
86 |
+
"stage4"
|
87 |
+
],
|
88 |
+
"suppress_tokens": null,
|
89 |
+
"task_specific_params": null,
|
90 |
+
"temperature": 1.0,
|
91 |
+
"tf_legacy_loss": false,
|
92 |
+
"tie_encoder_decoder": false,
|
93 |
+
"tie_word_embeddings": true,
|
94 |
+
"tokenizer_class": null,
|
95 |
+
"top_k": 50,
|
96 |
+
"top_p": 1.0,
|
97 |
+
"torch_dtype": null,
|
98 |
+
"torchscript": false,
|
99 |
+
"transformers_version": "4.27.0.dev0",
|
100 |
+
"typical_p": 1.0,
|
101 |
+
"use_bfloat16": false
|
102 |
+
},
|
103 |
+
"bbox_cost": 5,
|
104 |
+
"bbox_loss_coefficient": 5,
|
105 |
+
"class_cost": 1,
|
106 |
+
"d_model": 256,
|
107 |
+
"decoder_attention_heads": 8,
|
108 |
+
"decoder_ffn_dim": 2048,
|
109 |
+
"decoder_layerdrop": 0.0,
|
110 |
+
"decoder_layers": 6,
|
111 |
+
"dice_loss_coefficient": 1,
|
112 |
+
"dilation": null,
|
113 |
+
"dropout": 0.1,
|
114 |
+
"encoder_attention_heads": 8,
|
115 |
+
"encoder_ffn_dim": 2048,
|
116 |
+
"encoder_layerdrop": 0.0,
|
117 |
+
"encoder_layers": 6,
|
118 |
+
"eos_coefficient": 0.1,
|
119 |
+
"giou_cost": 2,
|
120 |
+
"giou_loss_coefficient": 2,
|
121 |
+
"id2label": {
|
122 |
+
"0": "LABEL_0",
|
123 |
+
"1": "LABEL_1",
|
124 |
+
"2": "LABEL_2",
|
125 |
+
"3": "LABEL_3",
|
126 |
+
"4": "LABEL_4",
|
127 |
+
"5": "LABEL_5",
|
128 |
+
"6": "LABEL_6",
|
129 |
+
"7": "LABEL_7",
|
130 |
+
"8": "LABEL_8",
|
131 |
+
"9": "LABEL_9",
|
132 |
+
"10": "LABEL_10",
|
133 |
+
"11": "LABEL_11",
|
134 |
+
"12": "LABEL_12",
|
135 |
+
"13": "LABEL_13",
|
136 |
+
"14": "LABEL_14",
|
137 |
+
"15": "LABEL_15",
|
138 |
+
"16": "LABEL_16",
|
139 |
+
"17": "LABEL_17",
|
140 |
+
"18": "LABEL_18",
|
141 |
+
"19": "LABEL_19",
|
142 |
+
"20": "LABEL_20",
|
143 |
+
"21": "LABEL_21",
|
144 |
+
"22": "LABEL_22",
|
145 |
+
"23": "LABEL_23",
|
146 |
+
"24": "LABEL_24",
|
147 |
+
"25": "LABEL_25",
|
148 |
+
"26": "LABEL_26",
|
149 |
+
"27": "LABEL_27",
|
150 |
+
"28": "LABEL_28",
|
151 |
+
"29": "LABEL_29",
|
152 |
+
"30": "LABEL_30",
|
153 |
+
"31": "LABEL_31",
|
154 |
+
"32": "LABEL_32",
|
155 |
+
"33": "LABEL_33",
|
156 |
+
"34": "LABEL_34",
|
157 |
+
"35": "LABEL_35",
|
158 |
+
"36": "LABEL_36",
|
159 |
+
"37": "LABEL_37",
|
160 |
+
"38": "LABEL_38"
|
161 |
+
},
|
162 |
+
"init_std": 0.02,
|
163 |
+
"init_xavier_std": 1.0,
|
164 |
+
"is_encoder_decoder": true,
|
165 |
+
"label2id": {
|
166 |
+
"LABEL_0": 0,
|
167 |
+
"LABEL_1": 1,
|
168 |
+
"LABEL_10": 10,
|
169 |
+
"LABEL_11": 11,
|
170 |
+
"LABEL_12": 12,
|
171 |
+
"LABEL_13": 13,
|
172 |
+
"LABEL_14": 14,
|
173 |
+
"LABEL_15": 15,
|
174 |
+
"LABEL_16": 16,
|
175 |
+
"LABEL_17": 17,
|
176 |
+
"LABEL_18": 18,
|
177 |
+
"LABEL_19": 19,
|
178 |
+
"LABEL_2": 2,
|
179 |
+
"LABEL_20": 20,
|
180 |
+
"LABEL_21": 21,
|
181 |
+
"LABEL_22": 22,
|
182 |
+
"LABEL_23": 23,
|
183 |
+
"LABEL_24": 24,
|
184 |
+
"LABEL_25": 25,
|
185 |
+
"LABEL_26": 26,
|
186 |
+
"LABEL_27": 27,
|
187 |
+
"LABEL_28": 28,
|
188 |
+
"LABEL_29": 29,
|
189 |
+
"LABEL_3": 3,
|
190 |
+
"LABEL_30": 30,
|
191 |
+
"LABEL_31": 31,
|
192 |
+
"LABEL_32": 32,
|
193 |
+
"LABEL_33": 33,
|
194 |
+
"LABEL_34": 34,
|
195 |
+
"LABEL_35": 35,
|
196 |
+
"LABEL_36": 36,
|
197 |
+
"LABEL_37": 37,
|
198 |
+
"LABEL_38": 38,
|
199 |
+
"LABEL_4": 4,
|
200 |
+
"LABEL_5": 5,
|
201 |
+
"LABEL_6": 6,
|
202 |
+
"LABEL_7": 7,
|
203 |
+
"LABEL_8": 8,
|
204 |
+
"LABEL_9": 9
|
205 |
+
},
|
206 |
+
"mask_loss_coefficient": 1,
|
207 |
+
"model_type": "detr",
|
208 |
+
"num_channels": 3,
|
209 |
+
"num_hidden_layers": 6,
|
210 |
+
"num_queries": 100,
|
211 |
+
"position_embedding_type": "sine",
|
212 |
+
"scale_embedding": false,
|
213 |
+
"torch_dtype": "float32",
|
214 |
+
"transformers_version": null,
|
215 |
+
"use_pretrained_backbone": null,
|
216 |
+
"use_timm_backbone": false
|
217 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ac75b60a58466d49310cedd6603ddb980002de375dca96496ac8481d945628f
|
3 |
+
size 166655189
|