first version of the LayoutXLM model
Browse files- .gitattributes +1 -0
- config.json +171 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +40 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/layoutxlm-base",
|
3 |
+
"architectures": [
|
4 |
+
"LayoutLMv2ForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"convert_sync_batchnorm": true,
|
9 |
+
"coordinate_size": 128,
|
10 |
+
"detectron2_config_args": {
|
11 |
+
"MODEL.ANCHOR_GENERATOR.SIZES": [
|
12 |
+
[
|
13 |
+
32
|
14 |
+
],
|
15 |
+
[
|
16 |
+
64
|
17 |
+
],
|
18 |
+
[
|
19 |
+
128
|
20 |
+
],
|
21 |
+
[
|
22 |
+
256
|
23 |
+
],
|
24 |
+
[
|
25 |
+
512
|
26 |
+
]
|
27 |
+
],
|
28 |
+
"MODEL.BACKBONE.NAME": "build_resnet_fpn_backbone",
|
29 |
+
"MODEL.FPN.IN_FEATURES": [
|
30 |
+
"res2",
|
31 |
+
"res3",
|
32 |
+
"res4",
|
33 |
+
"res5"
|
34 |
+
],
|
35 |
+
"MODEL.MASK_ON": true,
|
36 |
+
"MODEL.PIXEL_STD": [
|
37 |
+
57.375,
|
38 |
+
57.12,
|
39 |
+
58.395
|
40 |
+
],
|
41 |
+
"MODEL.POST_NMS_TOPK_TEST": 1000,
|
42 |
+
"MODEL.RESNETS.ASPECT_RATIOS": [
|
43 |
+
[
|
44 |
+
0.5,
|
45 |
+
1.0,
|
46 |
+
2.0
|
47 |
+
]
|
48 |
+
],
|
49 |
+
"MODEL.RESNETS.DEPTH": 101,
|
50 |
+
"MODEL.RESNETS.NUM_GROUPS": 32,
|
51 |
+
"MODEL.RESNETS.OUT_FEATURES": [
|
52 |
+
"res2",
|
53 |
+
"res3",
|
54 |
+
"res4",
|
55 |
+
"res5"
|
56 |
+
],
|
57 |
+
"MODEL.RESNETS.SIZES": [
|
58 |
+
[
|
59 |
+
32
|
60 |
+
],
|
61 |
+
[
|
62 |
+
64
|
63 |
+
],
|
64 |
+
[
|
65 |
+
128
|
66 |
+
],
|
67 |
+
[
|
68 |
+
256
|
69 |
+
],
|
70 |
+
[
|
71 |
+
512
|
72 |
+
]
|
73 |
+
],
|
74 |
+
"MODEL.RESNETS.STRIDE_IN_1X1": false,
|
75 |
+
"MODEL.RESNETS.WIDTH_PER_GROUP": 8,
|
76 |
+
"MODEL.ROI_BOX_HEAD.NAME": "FastRCNNConvFCHead",
|
77 |
+
"MODEL.ROI_BOX_HEAD.NUM_FC": 2,
|
78 |
+
"MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION": 14,
|
79 |
+
"MODEL.ROI_HEADS.IN_FEATURES": [
|
80 |
+
"p2",
|
81 |
+
"p3",
|
82 |
+
"p4",
|
83 |
+
"p5"
|
84 |
+
],
|
85 |
+
"MODEL.ROI_HEADS.NAME": "StandardROIHeads",
|
86 |
+
"MODEL.ROI_HEADS.NUM_CLASSES": 5,
|
87 |
+
"MODEL.ROI_MASK_HEAD.NAME": "MaskRCNNConvUpsampleHead",
|
88 |
+
"MODEL.ROI_MASK_HEAD.NUM_CONV": 4,
|
89 |
+
"MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION": 7,
|
90 |
+
"MODEL.RPN.IN_FEATURES": [
|
91 |
+
"p2",
|
92 |
+
"p3",
|
93 |
+
"p4",
|
94 |
+
"p5",
|
95 |
+
"p6"
|
96 |
+
],
|
97 |
+
"MODEL.RPN.POST_NMS_TOPK_TRAIN": 1000,
|
98 |
+
"MODEL.RPN.PRE_NMS_TOPK_TEST": 1000,
|
99 |
+
"MODEL.RPN.PRE_NMS_TOPK_TRAIN": 2000
|
100 |
+
},
|
101 |
+
"eos_token_id": 2,
|
102 |
+
"fast_qkv": false,
|
103 |
+
"gradient_checkpointing": false,
|
104 |
+
"has_relative_attention_bias": false,
|
105 |
+
"has_spatial_attention_bias": false,
|
106 |
+
"has_visual_segment_embedding": true,
|
107 |
+
"hidden_act": "gelu",
|
108 |
+
"hidden_dropout_prob": 0.1,
|
109 |
+
"hidden_size": 768,
|
110 |
+
"id2label": {
|
111 |
+
"0": "DIC",
|
112 |
+
"1": "IBAN",
|
113 |
+
"2": "ICO",
|
114 |
+
"3": "O",
|
115 |
+
"4": "account_number",
|
116 |
+
"5": "bank_code",
|
117 |
+
"6": "const_symbol",
|
118 |
+
"7": "contr_address",
|
119 |
+
"8": "contr_name",
|
120 |
+
"9": "due_date",
|
121 |
+
"10": "invoice_date",
|
122 |
+
"11": "invoice_number",
|
123 |
+
"12": "qr_code",
|
124 |
+
"13": "spec_symbol",
|
125 |
+
"14": "total_amount",
|
126 |
+
"15": "var_symbol"
|
127 |
+
},
|
128 |
+
"image_feature_pool_shape": [
|
129 |
+
7,
|
130 |
+
7,
|
131 |
+
256
|
132 |
+
],
|
133 |
+
"initializer_range": 0.02,
|
134 |
+
"intermediate_size": 3072,
|
135 |
+
"label2id": {
|
136 |
+
"DIC": 0,
|
137 |
+
"IBAN": 1,
|
138 |
+
"ICO": 2,
|
139 |
+
"O": 3,
|
140 |
+
"account_number": 4,
|
141 |
+
"bank_code": 5,
|
142 |
+
"const_symbol": 6,
|
143 |
+
"contr_address": 7,
|
144 |
+
"contr_name": 8,
|
145 |
+
"due_date": 9,
|
146 |
+
"invoice_date": 10,
|
147 |
+
"invoice_number": 11,
|
148 |
+
"qr_code": 12,
|
149 |
+
"spec_symbol": 13,
|
150 |
+
"total_amount": 14,
|
151 |
+
"var_symbol": 15
|
152 |
+
},
|
153 |
+
"layer_norm_eps": 1e-05,
|
154 |
+
"max_2d_position_embeddings": 1024,
|
155 |
+
"max_position_embeddings": 514,
|
156 |
+
"max_rel_2d_pos": 256,
|
157 |
+
"max_rel_pos": 128,
|
158 |
+
"model_type": "layoutlmv2",
|
159 |
+
"num_attention_heads": 12,
|
160 |
+
"num_hidden_layers": 12,
|
161 |
+
"output_past": true,
|
162 |
+
"pad_token_id": 1,
|
163 |
+
"rel_2d_pos_bins": 64,
|
164 |
+
"rel_pos_bins": 32,
|
165 |
+
"shape_size": 128,
|
166 |
+
"tokenizer_class": "LayoutXLMTokenizer",
|
167 |
+
"torch_dtype": "float32",
|
168 |
+
"transformers_version": "4.21.0",
|
169 |
+
"type_vocab_size": 1,
|
170 |
+
"vocab_size": 250002
|
171 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac19dd2d206d9d32d4943f82b0264b9cd11c19f6b81420f732be97883135c781
|
3 |
+
size 2927197221
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16555bd4694690a857500431c25c887eaee7175e523910ebdcda4bab7a5630c2
|
3 |
+
size 1476532839
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8669f00edd0b32ca7b1bb177b4651e13e6658736ad30f57ec3d5b55b9484d7ad
|
3 |
+
size 14439
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2abec65dbb5e4a1dd55349356b8fa4205dc40428dd6d205d656ace5671b238e8
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8666fdab5ac4930b05db388cb079d1e8848f7db3e786d5f53994e3666d18a0b4
|
3 |
+
size 17082660
|
tokenizer_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"cls_token_box": [
|
5 |
+
0,
|
6 |
+
0,
|
7 |
+
0,
|
8 |
+
0
|
9 |
+
],
|
10 |
+
"eos_token": "</s>",
|
11 |
+
"mask_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "<mask>",
|
14 |
+
"lstrip": true,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"model_max_length": 512,
|
20 |
+
"name_or_path": "microsoft/layoutxlm-base",
|
21 |
+
"only_label_first_subword": true,
|
22 |
+
"pad_token": "<pad>",
|
23 |
+
"pad_token_box": [
|
24 |
+
0,
|
25 |
+
0,
|
26 |
+
0,
|
27 |
+
0
|
28 |
+
],
|
29 |
+
"pad_token_label": -100,
|
30 |
+
"sep_token": "</s>",
|
31 |
+
"sep_token_box": [
|
32 |
+
1000,
|
33 |
+
1000,
|
34 |
+
1000,
|
35 |
+
1000
|
36 |
+
],
|
37 |
+
"special_tokens_map_file": null,
|
38 |
+
"tokenizer_class": "LayoutXLMTokenizer",
|
39 |
+
"unk_token": "<unk>"
|
40 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8181a85a5ff97746474415332317849a41b47e0b7199380483a6afba98926a37
|
3 |
+
size 3375
|