Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
configuration_layoutxlm.py 2.95 KB
Newer Older
HHL's avatar
v  
HHL committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86 
# coding=utf-8
from transformers.utils import logging

from ..layoutlmv2 import LayoutLMv2Config


logger = logging.get_logger(__name__)

LAYOUTXLM_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "layoutxlm-base": "https://huggingface.co/layoutxlm-base/resolve/main/config.json",
    "layoutxlm-large": "https://huggingface.co/layoutxlm-large/resolve/main/config.json",
}


class LayoutXLMConfig(LayoutLMv2Config):
    model_type = "layoutxlm"

    def __init__(
        self,
        vocab_size=30522,
        hidden_size=768,
        num_hidden_layers=12,
        num_attention_heads=12,
        intermediate_size=3072,
        hidden_act="gelu",
        hidden_dropout_prob=0.1,
        attention_probs_dropout_prob=0.1,
        max_position_embeddings=512,
        type_vocab_size=2,
        initializer_range=0.02,
        layer_norm_eps=1e-12,
        pad_token_id=0,
        gradient_checkpointing=False,
        max_2d_position_embeddings=1024,
        max_rel_pos=128,
        rel_pos_bins=32,
        fast_qkv=True,
        max_rel_2d_pos=256,
        rel_2d_pos_bins=64,
        convert_sync_batchnorm=True,
        image_feature_pool_shape=[7, 7, 256],
        coordinate_size=128,
        shape_size=128,
        has_relative_attention_bias=True,
        has_spatial_attention_bias=True,
        has_visual_segment_embedding=False,
        num_tokens=2,
        mvlm_alpha=4,
        tia_alpha=3,
        tim_alpha=3,
        **kwargs
    ):
        super().__init__(
            vocab_size=vocab_size,
            hidden_size=hidden_size,
            num_hidden_layers=num_hidden_layers,
            num_attention_heads=num_attention_heads,
            intermediate_size=intermediate_size,
            hidden_act=hidden_act,
            hidden_dropout_prob=hidden_dropout_prob,
            attention_probs_dropout_prob=attention_probs_dropout_prob,
            max_position_embeddings=max_position_embeddings,
            type_vocab_size=type_vocab_size,
            initializer_range=initializer_range,
            layer_norm_eps=layer_norm_eps,
            pad_token_id=pad_token_id,
            gradient_checkpointing=gradient_checkpointing,
            **kwargs,
        )
        self.max_2d_position_embeddings = max_2d_position_embeddings
        self.max_rel_pos = max_rel_pos
        self.rel_pos_bins = rel_pos_bins
        self.fast_qkv = fast_qkv
        self.max_rel_2d_pos = max_rel_2d_pos
        self.rel_2d_pos_bins = rel_2d_pos_bins
        self.convert_sync_batchnorm = convert_sync_batchnorm
        self.image_feature_pool_shape = image_feature_pool_shape
        self.coordinate_size = coordinate_size
        self.shape_size = shape_size
        self.has_relative_attention_bias = has_relative_attention_bias
        self.has_spatial_attention_bias = has_spatial_attention_bias
        self.has_visual_segment_embedding = has_visual_segment_embedding
        self.num_tokens = num_tokens
        self.mvlm_alpha = mvlm_alpha
        self.tia_alpha = tia_alpha
        self.tim_alpha = tim_alpha