Files changed (3) hide show
  1. config.json +189 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +36 -0
config.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "silu",
4
+ "anchor_image_size": null,
5
+ "architectures": [
6
+ "PPDocLayoutV2ForObjectDetection"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "backbone": null,
10
+ "backbone_config": {
11
+ "model_type": "hgnet_v2",
12
+ "arch": "L",
13
+ "return_idx": [1, 2, 3],
14
+ "freeze_stem_only": true,
15
+ "freeze_at": 0,
16
+ "freeze_norm": true,
17
+ "lr_mult_list": [0, 0.05, 0.05, 0.05, 0.05],
18
+ "out_features": ["stage2", "stage3", "stage4"]
19
+ },
20
+ "backbone_kwargs": null,
21
+ "batch_norm_eps": 1e-05,
22
+ "box_noise_scale": 1.0,
23
+ "d_model": 256,
24
+ "decoder_activation_function": "relu",
25
+ "decoder_attention_heads": 8,
26
+ "decoder_ffn_dim": 1024,
27
+ "decoder_in_channels": [
28
+ 256,
29
+ 256,
30
+ 256
31
+ ],
32
+ "decoder_layers": 6,
33
+ "decoder_n_points": 4,
34
+ "disable_custom_kernels": true,
35
+ "dropout": 0.0,
36
+ "encode_proj_layers": [
37
+ 2
38
+ ],
39
+ "encoder_activation_function": "gelu",
40
+ "encoder_attention_heads": 8,
41
+ "encoder_ffn_dim": 1024,
42
+ "encoder_hidden_dim": 256,
43
+ "encoder_in_channels": [
44
+ 512,
45
+ 1024,
46
+ 2048
47
+ ],
48
+ "encoder_layers": 1,
49
+ "eos_coefficient": 0.0001,
50
+ "eval_size": null,
51
+ "feat_strides": [
52
+ 8,
53
+ 16,
54
+ 32
55
+ ],
56
+ "hidden_expansion": 1.0,
57
+ "id2label": {
58
+ "0": "abstract",
59
+ "1": "algorithm",
60
+ "2": "aside_text",
61
+ "3": "chart",
62
+ "4": "content",
63
+ "5": "formula",
64
+ "6": "doc_title",
65
+ "7": "figure_title",
66
+ "8": "footer",
67
+ "9": "footer",
68
+ "10": "footnote",
69
+ "11": "formula_number",
70
+ "12": "header",
71
+ "13": "header",
72
+ "14": "image",
73
+ "15": "formula",
74
+ "16": "number",
75
+ "17": "paragraph_title",
76
+ "18": "reference",
77
+ "19": "reference_content",
78
+ "20": "seal",
79
+ "21": "table",
80
+ "22": "text",
81
+ "23": "text",
82
+ "24": "vision_footnote"
83
+ },
84
+ "initializer_range": 0.01,
85
+ "is_encoder_decoder": true,
86
+ "label2id": {},
87
+ "label_noise_ratio": 0.5,
88
+ "layer_norm_eps": 1e-05,
89
+ "learn_initial_query": false,
90
+ "matcher_alpha": 0.25,
91
+ "matcher_bbox_cost": 5.0,
92
+ "matcher_class_cost": 2.0,
93
+ "matcher_gamma": 2.0,
94
+ "matcher_giou_cost": 2.0,
95
+ "model_type": "pp_doclayout_v2",
96
+ "normalize_before": false,
97
+ "num_denoising": 100,
98
+ "num_feature_levels": 3,
99
+ "num_queries": 300,
100
+ "positional_encoding_temperature": 10000,
101
+ "torch_dtype": "float32",
102
+ "use_pretrained_backbone": false,
103
+ "use_timm_backbone": false,
104
+ "reading_oreder": {
105
+ "hidden_size": 512,
106
+ "num_attention_heads": 8,
107
+ "attention_probs_dropout_prob": 0.1,
108
+ "has_relative_attention_bias": false,
109
+ "has_spatial_attention_bias": true,
110
+ "layer_norm_eps": 1e-5,
111
+ "hidden_dropout_prob": 0.1,
112
+ "intermediate_size": 2048,
113
+ "hidden_act": "gelu",
114
+ "num_hidden_layers": 6,
115
+ "rel_pos_bins": 32,
116
+ "max_rel_pos": 128,
117
+ "rel_2d_pos_bins": 64,
118
+ "max_rel_2d_pos": 256,
119
+ "num_labels": 510,
120
+ "max_position_embeddings": 514,
121
+ "max_2d_position_embeddings": 1024,
122
+ "type_vocab_size": 1,
123
+ "vocab_size": 4,
124
+ "start_token_id": 0,
125
+ "pad_token_id": 1,
126
+ "end_token_id": 2,
127
+ "pred_token_id": 3,
128
+ "coordinate_size": 171,
129
+ "shape_size": 170,
130
+ "num_classes": 20,
131
+ "rel_bias_embed_dim": 16,
132
+ "rel_bias_temperature": 10000,
133
+ "rel_bias_scale": 100,
134
+ "relative_head_num": 1,
135
+ "relative_head_size": 64,
136
+ "tril_mask": true
137
+ },
138
+ "threshold_mapping": {
139
+ "abstract": 0.50,
140
+ "algorithm": 0.50,
141
+ "aside_text": 0.50,
142
+ "chart": 0.50,
143
+ "content": 0.50,
144
+ "formula": 0.40,
145
+ "doc_title": 0.40,
146
+ "figure_title": 0.50,
147
+ "footer": 0.50,
148
+ "footnote": 0.50,
149
+ "formula_number": 0.50,
150
+ "header": 0.50,
151
+ "image": 0.50,
152
+ "number": 0.50,
153
+ "paragraph_title": 0.40,
154
+ "reference": 0.50,
155
+ "reference_content": 0.50,
156
+ "seal": 0.45,
157
+ "table": 0.50,
158
+ "text": 0.40,
159
+ "vision_footnote": 0.50
160
+ },
161
+ "order_map": {
162
+ "abstract": 4,
163
+ "algorithm": 2,
164
+ "aside_text": 14,
165
+ "chart": 1,
166
+ "content": 5,
167
+ "display_formula": 7,
168
+ "doc_title": 8,
169
+ "figure_title": 6,
170
+ "footer": 11,
171
+ "footer_image": 11,
172
+ "footnote": 9,
173
+ "formula_number": 13,
174
+ "header": 10,
175
+ "header_image": 10,
176
+ "image": 1,
177
+ "inline_formula": 2,
178
+ "number": 3,
179
+ "paragraph_title": 0,
180
+ "reference": 2,
181
+ "reference_content": 2,
182
+ "seal": 12,
183
+ "table": 1,
184
+ "text": 2,
185
+ "vertical_text": 15,
186
+ "vision_footnote": 6
187
+ }
188
+ }
189
+
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ecb953cc68bd6e419f4df046cec9ba90815af605658b6ea392e985c4fe173d
3
+ size 214798572
preprocessor_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_rescale",
8
+ "rescale_factor",
9
+ "do_normalize",
10
+ "image_mean",
11
+ "image_std",
12
+ "return_tensors",
13
+ "data_format",
14
+ "input_data_format"
15
+ ],
16
+ "do_normalize": true,
17
+ "do_rescale": true,
18
+ "do_resize": true,
19
+ "image_mean": [
20
+ 0,
21
+ 0,
22
+ 0
23
+ ],
24
+ "image_processor_type": "PPDocLayoutV2ImageProcessor",
25
+ "image_std": [
26
+ 1,
27
+ 1,
28
+ 1
29
+ ],
30
+ "resample": 3,
31
+ "rescale_factor": 0.00392156862745098,
32
+ "size": {
33
+ "height": 800,
34
+ "width": 800
35
+ }
36
+ }