Hugging Face's logo

fushh7
/
llmdet_swin_large_hf

Zero-Shot Object Detection
PyTorch
Safetensors
grounding-dino
Model card Files Community
1
fushh7 commited on
Commit
bff7612
·
verified ·
1 Parent(s): 82815b2

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +83 -0
  2. preprocessor_config.json +27 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +56 -0
  7. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "relu",
4
+ "architectures": [
5
+ "GroundingDinoForObjectDetection"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "auxiliary_loss": false,
9
+ "backbone": null,
10
+ "backbone_config": {
11
+ "depths": [
12
+ 2,
13
+ 2,
14
+ 18,
15
+ 2
16
+ ],
17
+ "embed_dim": 192,
18
+ "hidden_size": 1536,
19
+ "image_size": 384,
20
+ "model_type": "swin",
21
+ "num_heads": [
22
+ 6,
23
+ 12,
24
+ 24,
25
+ 48
26
+ ],
27
+ "out_features": [
28
+ "stage1",
29
+ "stage2",
30
+ "stage3",
31
+ "stage4"
32
+ ],
33
+ "out_indices": [
34
+ 1,
35
+ 2,
36
+ 3,
37
+ 4
38
+ ],
39
+ "window_size": 12
40
+ },
41
+ "backbone_kwargs": null,
42
+ "bbox_cost": 5.0,
43
+ "bbox_loss_coefficient": 5.0,
44
+ "class_cost": 1.0,
45
+ "d_model": 256,
46
+ "decoder_attention_heads": 8,
47
+ "decoder_bbox_embed_share": true,
48
+ "decoder_ffn_dim": 2048,
49
+ "decoder_layers": 6,
50
+ "decoder_n_points": 4,
51
+ "disable_custom_kernels": false,
52
+ "dropout": 0.1,
53
+ "embedding_init_target": true,
54
+ "encoder_attention_heads": 8,
55
+ "encoder_ffn_dim": 2048,
56
+ "encoder_layers": 6,
57
+ "encoder_n_points": 4,
58
+ "focal_alpha": 0.25,
59
+ "fusion_dropout": 0.0,
60
+ "fusion_droppath": 0.1,
61
+ "giou_cost": 2.0,
62
+ "giou_loss_coefficient": 2.0,
63
+ "init_std": 0.02,
64
+ "is_encoder_decoder": true,
65
+ "layer_norm_eps": 1e-05,
66
+ "max_text_len": 256,
67
+ "model_type": "grounding-dino",
68
+ "num_feature_levels": 5,
69
+ "num_queries": 900,
70
+ "position_embedding_type": "sine",
71
+ "positional_embedding_temperature": 20,
72
+ "query_dim": 4,
73
+ "text_config": {
74
+ "model_type": "bert"
75
+ },
76
+ "text_enhancer_dropout": 0.0,
77
+ "torch_dtype": "float32",
78
+ "transformers_version": "4.42.0",
79
+ "two_stage": true,
80
+ "two_stage_bbox_embed_share": false,
81
+ "use_pretrained_backbone": false,
82
+ "use_timm_backbone": false
83
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_annotations": true,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "format": "coco_detection",
8
+ "image_mean": [
9
+ 0.485,
10
+ 0.456,
11
+ 0.406
12
+ ],
13
+ "image_processor_type": "GroundingDinoImageProcessor",
14
+ "image_std": [
15
+ 0.229,
16
+ 0.224,
17
+ 0.225
18
+ ],
19
+ "pad_size": null,
20
+ "processor_class": "GroundingDinoProcessor",
21
+ "resample": 2,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "longest_edge": 1333,
25
+ "shortest_edge": 800
26
+ }
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b12a3fc8daf55f79edc9d160c614f286821e08bc216770f6f6c494b82daaa0d
3
+ size 1373963931
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "processor_class": "GroundingDinoProcessor",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff