Hugging Face's logo

gfx-labs
/
gfx-labs-layout-fine-tunedv2

Text Classification
Transformers
PyTorch
layoutlmv2
Inference Endpoints
Model card Files Community
gfx-labs commited on
Commit
754d64d
·
1 Parent(s): 345b2ad

image-classification

Browse files
Files changed (6) hide show
  1. config.json +149 -0
  2. preprocessor_config.json +13 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer_config.json +37 -0
  6. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/layoutlmv2-base-uncased",
3
+ "architectures": [
4
+ "LayoutLMv2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "convert_sync_batchnorm": true,
8
+ "coordinate_size": 128,
9
+ "detectron2_config_args": {
10
+ "MODEL.ANCHOR_GENERATOR.SIZES": [
11
+ [
12
+ 32
13
+ ],
14
+ [
15
+ 64
16
+ ],
17
+ [
18
+ 128
19
+ ],
20
+ [
21
+ 256
22
+ ],
23
+ [
24
+ 512
25
+ ]
26
+ ],
27
+ "MODEL.BACKBONE.NAME": "build_resnet_fpn_backbone",
28
+ "MODEL.FPN.IN_FEATURES": [
29
+ "res2",
30
+ "res3",
31
+ "res4",
32
+ "res5"
33
+ ],
34
+ "MODEL.MASK_ON": true,
35
+ "MODEL.PIXEL_STD": [
36
+ 57.375,
37
+ 57.12,
38
+ 58.395
39
+ ],
40
+ "MODEL.POST_NMS_TOPK_TEST": 1000,
41
+ "MODEL.RESNETS.ASPECT_RATIOS": [
42
+ [
43
+ 0.5,
44
+ 1.0,
45
+ 2.0
46
+ ]
47
+ ],
48
+ "MODEL.RESNETS.DEPTH": 101,
49
+ "MODEL.RESNETS.NUM_GROUPS": 32,
50
+ "MODEL.RESNETS.OUT_FEATURES": [
51
+ "res2",
52
+ "res3",
53
+ "res4",
54
+ "res5"
55
+ ],
56
+ "MODEL.RESNETS.SIZES": [
57
+ [
58
+ 32
59
+ ],
60
+ [
61
+ 64
62
+ ],
63
+ [
64
+ 128
65
+ ],
66
+ [
67
+ 256
68
+ ],
69
+ [
70
+ 512
71
+ ]
72
+ ],
73
+ "MODEL.RESNETS.STRIDE_IN_1X1": false,
74
+ "MODEL.RESNETS.WIDTH_PER_GROUP": 8,
75
+ "MODEL.ROI_BOX_HEAD.NAME": "FastRCNNConvFCHead",
76
+ "MODEL.ROI_BOX_HEAD.NUM_FC": 2,
77
+ "MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION": 14,
78
+ "MODEL.ROI_HEADS.IN_FEATURES": [
79
+ "p2",
80
+ "p3",
81
+ "p4",
82
+ "p5"
83
+ ],
84
+ "MODEL.ROI_HEADS.NAME": "StandardROIHeads",
85
+ "MODEL.ROI_HEADS.NUM_CLASSES": 5,
86
+ "MODEL.ROI_MASK_HEAD.NAME": "MaskRCNNConvUpsampleHead",
87
+ "MODEL.ROI_MASK_HEAD.NUM_CONV": 4,
88
+ "MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION": 7,
89
+ "MODEL.RPN.IN_FEATURES": [
90
+ "p2",
91
+ "p3",
92
+ "p4",
93
+ "p5",
94
+ "p6"
95
+ ],
96
+ "MODEL.RPN.POST_NMS_TOPK_TRAIN": 1000,
97
+ "MODEL.RPN.PRE_NMS_TOPK_TEST": 1000,
98
+ "MODEL.RPN.PRE_NMS_TOPK_TRAIN": 2000
99
+ },
100
+ "fast_qkv": true,
101
+ "gradient_checkpointing": false,
102
+ "has_relative_attention_bias": true,
103
+ "has_spatial_attention_bias": true,
104
+ "has_visual_segment_embedding": false,
105
+ "hidden_act": "gelu",
106
+ "hidden_dropout_prob": 0.1,
107
+ "hidden_size": 768,
108
+ "id2label": {
109
+ "0": "LABEL_0",
110
+ "1": "LABEL_1",
111
+ "2": "LABEL_2",
112
+ "3": "LABEL_3",
113
+ "4": "LABEL_4",
114
+ "5": "LABEL_5"
115
+ },
116
+ "image_feature_pool_shape": [
117
+ 7,
118
+ 7,
119
+ 256
120
+ ],
121
+ "initializer_range": 0.02,
122
+ "intermediate_size": 3072,
123
+ "label2id": {
124
+ "LABEL_0": 0,
125
+ "LABEL_1": 1,
126
+ "LABEL_2": 2,
127
+ "LABEL_3": 3,
128
+ "LABEL_4": 4,
129
+ "LABEL_5": 5
130
+ },
131
+ "layer_norm_eps": 1e-12,
132
+ "max_2d_position_embeddings": 1024,
133
+ "max_position_embeddings": 512,
134
+ "max_rel_2d_pos": 256,
135
+ "max_rel_pos": 128,
136
+ "model_type": "layoutlmv2",
137
+ "num_attention_heads": 12,
138
+ "num_hidden_layers": 12,
139
+ "output_past": true,
140
+ "pad_token_id": 0,
141
+ "problem_type": "single_label_classification",
142
+ "rel_2d_pos_bins": 64,
143
+ "rel_pos_bins": 32,
144
+ "shape_size": 128,
145
+ "torch_dtype": "float32",
146
+ "transformers_version": "4.29.2",
147
+ "type_vocab_size": 2,
148
+ "vocab_size": 30522
149
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": true,
3
+ "do_resize": true,
4
+ "image_processor_type": "LayoutLMv2FeatureExtractor",
5
+ "ocr_lang": null,
6
+ "processor_class": "LayoutLMv2Processor",
7
+ "resample": 2,
8
+ "size": {
9
+ "height": 224,
10
+ "width": 224
11
+ },
12
+ "tesseract_config": ""
13
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:758c71a319dfebdc5314de75ad899d70db8d3366ff42aa1a2c94f501f75f3b8d
3
+ size 802254841
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_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "cls_token_box": [
6
+ 0,
7
+ 0,
8
+ 0,
9
+ 0
10
+ ],
11
+ "do_basic_tokenize": true,
12
+ "do_lower_case": true,
13
+ "mask_token": "[MASK]",
14
+ "model_max_length": 512,
15
+ "never_split": null,
16
+ "only_label_first_subword": true,
17
+ "pad_token": "[PAD]",
18
+ "pad_token_box": [
19
+ 0,
20
+ 0,
21
+ 0,
22
+ 0
23
+ ],
24
+ "pad_token_label": -100,
25
+ "processor_class": "LayoutLMv2Processor",
26
+ "sep_token": "[SEP]",
27
+ "sep_token_box": [
28
+ 1000,
29
+ 1000,
30
+ 1000,
31
+ 1000
32
+ ],
33
+ "strip_accents": null,
34
+ "tokenize_chinese_chars": true,
35
+ "tokenizer_class": "LayoutLMv2Tokenizer",
36
+ "unk_token": "[UNK]"
37
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff