bert源码(pytorch)超详细解读！！！

modeling.py
此文章是对transformers的bert源码的解读

# coding=utf-8

from __future__ import absolute_import, division, print_function, unicode_literals

import copy
import json
import logging
import math
import os
import shutil
import tarfile
import tempfile
import sys
from io import open

import torch
from torch import nn
from torch.nn import CrossEntropyLoss

from .file_utils import cached_path, WEIGHTS_NAME, CONFIG_NAME

logger = logging.getLogger(__name__)


# uncased不分大小写 multilingual多语种的
PRETRAINED_MODEL_ARCHIVE_MAP = {
   
    'bert-base-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased.tar.gz",
    'bert-large-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased.tar.gz",
    'bert-base-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased.tar.gz",
    'bert-large-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased.tar.gz",
    'bert-base-multilingual-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased.tar.gz",
    'bert-base-multilingual-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased.tar.gz",
    'bert-base-chinese': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese.tar.gz",
}
BERT_CONFIG_NAME = 'bert_config.json'
TF_WEIGHTS_NAME = 'model.ckpt'

def load_tf_weights_in_bert(model, tf_checkpoint_path):
    """ Load tf checkpoints in a pytorch model
    """
    try:
        import re
        import numpy as np
        import tensorflow as tf
    except ImportError:
        print("Loading a TensorFlow models in PyTorch, requires TensorFlow to be installed. Please see "
            "https://www.tensorflow.org/install/ for installation instructions.")
        raise
    tf_path = os.path.abspath(tf_checkpoint_path)
    print("Converting TensorFlow checkpoint from {}".format(tf_path))
    # Load weights from TF model
    init_vars = tf.train.list_variables(tf_path)
    names = []
    arrays = []
    for name, shape in init_vars:
        print("Loading TF weight {} with shape {}".format(name, shape))
        array = tf.train.load_variable(tf_path, name)
        names.append(name)
        arrays.append(array)

    for name, array in zip(names, arrays):
        name = name.split('/')
        # adam_v and adam_m are variables used in AdamWeightDecayOptimizer to calculated m and v
        # which are not required for using pretrained model
        if any(n in ["adam_v", "adam_m", "global_step"] for n in name):
            print("Skipping {}".format("/".join(name)))
            continue
        pointer = model
        for m_name in name:
            if re.fullmatch(r'[A-Za-z]+_\d+', m_name):
                l = re.split(r'_(\d+)', m_name)
            else:
                l = [m_name]
            if l[0] == 'kernel' or l[0] == 'gamma':
                pointer = getattr(pointer, 'weight')
            elif l[0] == 'output_bias' or l[0] == 'beta':
                pointer = getattr(pointer, 'bias')
            elif l[0] == 'output_weights':
                pointer = getattr(pointer, 'weight')
            elif l[0] == 'squad':
                pointer = getattr(pointer, 'classifier')
            else:
                try:
                    pointer = getattr(pointer, l[0])
                except AttributeError:
                    print("Skipping {}".format("/".join(name)))
                    continue
            if len(l) >= 2:
                num = int(l[1])
                pointer = pointer[num]
        if m_name[-11:] == '_embeddings':
            pointer = getattr(pointer, 'weight')
        elif m_name == 'kernel':
            array = np.transpose(array)
        try:
            assert pointer.shape == array.shape
        except AssertionError as e:
            e.args += (pointer.shape, array.shape)
            raise
        print("Initialize PyTorch weight {}".format(name))
        pointer.data = torch.from_numpy(array)
    return model


def gelu(x):  # bert的激活函数
    """Implementation of the gelu activation function.
        For information: OpenAI GPT's gelu is slightly different (and gives slightly different results):
        0.5 * x * (1 + torch.tanh(math.sqrt(2 / math.pi) * (x + 0.044715 * torch.pow(x, 3))))
        Also see https://arxiv.org/abs/1606.08415
    """
    return x * 0.5 * (1.0 + torch.erf(x / math.sqrt(2.0)))


def swish(x):
    return x * torch.sigmoid(x)


ACT2FN = {
   "gelu": gelu, "relu": torch.nn.functional.relu, "swish": swish}


class BertConfig(object):
    """Configuration class to store the configuration of a `BertModel`.
    """
    def __init__(self,
                 vocab_size_or_config_json_file,
                 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):
        """Constructs BertConfig.

        Args:
            vocab_size_or_config_json_file: Vocabulary size of `inputs_ids` in `BertModel`.
            hidden_size: Size of the encoder layers and the pooler layer.
            num_hidden_layers: Number of hidden layers in the Transformer encoder.
            num_attention_heads: Number of attention heads for each attention layer in
                the Transformer encoder.
            intermediate_size: The size of the "intermediate" (i.e., feed-forward)
                layer in the Transformer encoder.
            hidden_act: The non-linear activation function (function or string) in the
                encoder and pooler. If string, "gelu", "relu" and "swish" are supported.
            hidden_dropout_prob: The dropout probabilitiy for all fully connected
                layers in the embeddings, encoder, and pooler.
            attention_probs_dropout_prob: The dropout ratio for the attention
                probabilities.
            max_position_embeddings: The maximum sequence length that this model might
                ever be used with. Typically set this to something large just in case
                (e.g., 512 or 1024 or 2048).
            type_vocab_size: The vocabulary size of the `token_type_ids` passed into
                `BertModel`.
            initializer_range: The sttdev of the truncated_normal_initializer for
                initializing all weight matrices.
        """
        if isinstance(vocab_size_or_config_json_file, str) or (sys.version_info[0] == 2
                        and isinstance(vocab_size_or_config_json_file, unicode)):
            with open(vocab_size_or_config_json_file, "r", encoding='utf-8') as reader:
                json_config = json.loads(reader.read())
            for key, value in json_config.items():
                self.__dict__[key] = value
        elif isinstance(vocab_size_or_config_json_file, int):    # isinstance() 函数来判断一个对象是否是一个已知的类型，类似 type()
            self.vocab_size = vocab_size_or_config_json_file
            self.hidden_size = hidden_size
            self.num_hidden_layers = num_hidden_layers
            self.num_attention_heads = num_attention_heads
            self.hidden_act = hidden_act
            self.intermediate_size = intermediate_size
            self.hidden_dropout_prob = hidden_dropout_prob
            self.attention_probs_dropout_prob = attention_probs_dropout_prob
            self.max_position_embeddings = max_position_embeddings
            self.type_vocab_size = type_vocab_size
            self.initializer_range = initializer_range
        else:
            raise ValueError("First argument must be either a vocabulary size (int)"
                             "or the path to a pretrained model config file (str)")

    @classmethod
    def from_dict(cls, json_object):
        """Constructs a `BertConfig` from a Python dictionary of parameters."""
        config = BertConfig(vocab_size_or_config_json_file=-1)
        for key, value in json_object.items():
            config.__dict__[key] = value
        return config

    @classmethod
    def from_json_file(cls, json_file):
        """Constructs a `BertConfig` from a json file of parameters."""
        with open(json_file, "r", encoding='utf-8') as reader:
            text = reader.read()
        return cls.from_dict(json.loads(text))

    def __repr__(self):
        return str(self.to_json_string())

    def to_dict(self):
        """Serializes this instance to a Python dictionary."""
        output = copy.deepcopy(self.__dict__)
        return output

    def to_json_string(self):
        """Serializes this instance to a JSON string."""
        return json.dumps(self.to_dict(), indent=2, sort_keys=True) + "\n"

    def to_json_file(self, json_file_path):
        """ Save this instance to a json file."""
        with open(json_file_path, "w", encoding='utf-8') as writer:
            writer.write(self.to_json_string())

try:
    from apex.normalization.fused_layer_norm import FusedLayerNorm as BertLayerNorm
except ImportError:
    logger.info("Better speed can be achieved with apex installed from https://www.github.com/nvidia/apex .")
    class BertLayerNorm(nn.Module):
        def __init__(self, hidden_size, eps=1e-12):
            """Construct a layernorm module in the TF style (epsilon inside the square root).
            """
            super(BertLayerNorm, self).__init__()
            self.weight = nn.Parameter(torch.ones(hidden_size))
            self.bias = nn.Parameter(torch.zeros(hidden_size))
            self.variance_epsilon = eps

        def forward(self, x):
            u = x.mean(-1, keepdim=True)  # 求均值
            s = (x - u).pow(2).mean(-1, keepdim=True)  # 求方差
            x = (x - u) / torch.sqrt