Hugging Face's logo

Blueway
/
inference-endpoint-for-omdet-turbo-swin-tiny-hf

Zero-Shot Object Detection
Transformers
Safetensors
French
English
omdet-turbo
endpoints-template
Model card Files
xet
Community
1
LDanielBlueway commited on
Commit
a24eb5f
·
verified ·
1 Parent(s): b49ce6d

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +92 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +27 -0
  5. special_tokens_map.json +30 -0
  6. tokenizer_config.json +31 -0
  7. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_layernorm_after_vision_backbone": true,
3
+ "architectures": [
4
+ "OmDetTurboForObjectDetection"
5
+ ],
6
+ "backbone": "swin_tiny_patch4_window7_224",
7
+ "backbone_config": null,
8
+ "backbone_depths": [
9
+ 2,
10
+ 2,
11
+ 6,
12
+ 2
13
+ ],
14
+ "backbone_embed_dim": 96,
15
+ "backbone_image_size": 640,
16
+ "backbone_kwargs": {
17
+ "always_partition": true,
18
+ "img_size": 640,
19
+ "out_indices": [
20
+ 1,
21
+ 2,
22
+ 3
23
+ ]
24
+ },
25
+ "backbone_num_heads": [
26
+ 3,
27
+ 6,
28
+ 12,
29
+ 24
30
+ ],
31
+ "backbone_out_indices": [
32
+ 1,
33
+ 2,
34
+ 3
35
+ ],
36
+ "backbone_window_size": 7,
37
+ "batch_norm_eps": 1e-05,
38
+ "cache_size": 100,
39
+ "class_distance_type": "cosine",
40
+ "class_embed_dim": 512,
41
+ "conv_norm_activation": "gelu",
42
+ "csp_activation": "silu",
43
+ "d_model": 256,
44
+ "decoder_activation": "relu",
45
+ "decoder_dim_feedforward": 2048,
46
+ "decoder_dropout": 0.0,
47
+ "decoder_hidden_dim": 256,
48
+ "decoder_num_heads": 8,
49
+ "decoder_num_layers": 6,
50
+ "decoder_num_points": 4,
51
+ "disable_custom_kernels": false,
52
+ "encoder_attention_heads": 8,
53
+ "encoder_dim_feedforward": 2048,
54
+ "encoder_dropout": 0.0,
55
+ "encoder_feedforward_activation": "relu",
56
+ "encoder_feedforward_dropout": 0.0,
57
+ "encoder_in_channels": [
58
+ 192,
59
+ 384,
60
+ 768
61
+ ],
62
+ "encoder_layers": 1,
63
+ "encoder_projection_indices": [
64
+ 2
65
+ ],
66
+ "eval_size": null,
67
+ "hidden_expansion": 1,
68
+ "image_size": 640,
69
+ "init_std": 0.02,
70
+ "is_encoder_decoder": true,
71
+ "layer_norm_eps": 1e-05,
72
+ "learn_initial_query": false,
73
+ "model_type": "omdet-turbo",
74
+ "num_feature_levels": 3,
75
+ "num_queries": 900,
76
+ "positional_encoding_temperature": 10000,
77
+ "task_encoder_hidden_dim": 1024,
78
+ "text_config": {
79
+ "model_type": "clip_text_model"
80
+ },
81
+ "text_projection_in_dim": 512,
82
+ "text_projection_out_dim": 512,
83
+ "torch_dtype": "float32",
84
+ "transformers_version": "4.45.0.dev0",
85
+ "use_pretrained_backbone": false,
86
+ "use_timm_backbone": true,
87
+ "vision_features_channels": [
88
+ 256,
89
+ 256,
90
+ 256
91
+ ]
92
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439d1575d7e237ad565ed6969ea2a2dfcedf2086155e9ca3ac96cd6180a48cfd
3
+ size 461822656
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_annotations": true,
3
+ "do_normalize": true,
4
+ "do_pad": false,
5
+ "do_rescale": false,
6
+ "do_resize": true,
7
+ "format": "coco_detection",
8
+ "image_mean": [
9
+ 123.675,
10
+ 116.28,
11
+ 103.53
12
+ ],
13
+ "image_processor_type": "DetrImageProcessor",
14
+ "image_std": [
15
+ 58.395,
16
+ 57.12,
17
+ 57.375
18
+ ],
19
+ "pad_size": null,
20
+ "processor_class": "OmDetTurboProcessor",
21
+ "resample": 2,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "height": 640,
25
+ "width": 640
26
+ }
27
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|startoftext|>",
22
+ "clean_up_tokenization_spaces": true,
23
+ "do_lower_case": true,
24
+ "eos_token": "<|endoftext|>",
25
+ "errors": "replace",
26
+ "model_max_length": 77,
27
+ "pad_token": "<|endoftext|>",
28
+ "processor_class": "OmDetTurboProcessor",
29
+ "tokenizer_class": "CLIPTokenizer",
30
+ "unk_token": "<|endoftext|>"
31
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff