From 0d7026d371d2da9efb34ccddd9ee829550fe00f5 Mon Sep 17 00:00:00 2001 From: benjas <909336740@qq.com> Date: Fri, 8 Jan 2021 09:38:00 +0800 Subject: [PATCH] Add. embedding_postprocessor --- .../源码解读.md | 168 ++++++++++++++++++ 1 file changed, 168 insertions(+) diff --git a/NLP通用框架BERT项目实战/第二章——BERT源码解读与应用实例/源码解读.md b/NLP通用框架BERT项目实战/第二章——BERT源码解读与应用实例/源码解读.md index 4a72883..c56e772 100644 --- a/NLP通用框架BERT项目实战/第二章——BERT源码解读与应用实例/源码解读.md +++ b/NLP通用框架BERT项目实战/第二章——BERT源码解读与应用实例/源码解读.md @@ -344,3 +344,171 @@ def embedding_lookup(input_ids, +#### 位置编码 + +~~~python +class BertModel(object): + """BERT model ("Bidirectional Encoder Representations from Transformers"). + + Example usage: + + ```python + # Already been converted into WordPiece token ids + input_ids = tf.constant([[31, 51, 99], [15, 5, 0]]) + input_mask = tf.constant([[1, 1, 1], [1, 1, 0]]) + token_type_ids = tf.constant([[0, 0, 1], [0, 2, 0]]) + + config = modeling.BertConfig(vocab_size=32000, hidden_size=512, + num_hidden_layers=8, num_attention_heads=6, intermediate_size=1024) + + model = modeling.BertModel(config=config, is_training=True, + input_ids=input_ids, input_mask=input_mask, token_type_ids=token_type_ids) + + label_embeddings = tf.get_variable(...) + pooled_output = model.get_pooled_output() + logits = tf.matmul(pooled_output, label_embeddings) + ... + ``` + """ + + def __init__(self, + config, + is_training, + input_ids, + input_mask=None, + token_type_ids=None, + use_one_hot_embeddings=False, + scope=None): + """Constructor for BertModel. + + Args: + config: `BertConfig` instance. + is_training: bool. true for training model, false for eval model. Controls + whether dropout will be applied. + input_ids: int32 Tensor of shape [batch_size, seq_length]. + input_mask: (optional) int32 Tensor of shape [batch_size, seq_length]. + token_type_ids: (optional) int32 Tensor of shape [batch_size, seq_length]. + use_one_hot_embeddings: (optional) bool. Whether to use one-hot word + embeddings or tf.embedding_lookup() for the word embeddings. + scope: (optional) variable scope. Defaults to "bert". + + Raises: + ValueError: The config is invalid or one of the input tensor shapes + is invalid. + """ + ... + + # Add positional embeddings and token type embeddings, then layer + # normalize and perform dropout. + self.embedding_output = embedding_postprocessor( # 制作位置编码，ctrl点击embedding_postprocessor + input_tensor=self.embedding_output, + use_token_type=True, + token_type_ids=token_type_ids, + token_type_vocab_size=config.type_vocab_size, + token_type_embedding_name="token_type_embeddings", + use_position_embeddings=True, + position_embedding_name="position_embeddings", + initializer_range=config.initializer_range, + max_position_embeddings=config.max_position_embeddings, + dropout_prob=config.hidden_dropout_prob) +~~~ + + + +~~~python +def embedding_postprocessor(input_tensor, + use_token_type=False, + token_type_ids=None, + token_type_vocab_size=16, + token_type_embedding_name="token_type_embeddings", + use_position_embeddings=True, + position_embedding_name="position_embeddings", + initializer_range=0.02, + max_position_embeddings=512, + dropout_prob=0.1): + """Performs various post-processing on a word embedding tensor. + + Args: + input_tensor: float Tensor of shape [batch_size, seq_length, + embedding_size]. + use_token_type: bool. Whether to add embeddings for `token_type_ids`. + token_type_ids: (optional) int32 Tensor of shape [batch_size, seq_length]. + Must be specified if `use_token_type` is True. + token_type_vocab_size: int. The vocabulary size of `token_type_ids`. + token_type_embedding_name: string. The name of the embedding table variable + for token type ids. + use_position_embeddings: bool. Whether to add position embeddings for the + position of each token in the sequence. + position_embedding_name: string. The name of the embedding table variable + for positional embeddings. + initializer_range: float. Range of the weight initialization. + max_position_embeddings: int. Maximum sequence length that might ever be + used with this model. This can be longer than the sequence length of + input_tensor, but cannot be shorter. + dropout_prob: float. Dropout probability applied to the final output tensor. + + Returns: + float tensor with same shape as `input_tensor`. + + Raises: + ValueError: One of the tensor shapes or input values is invalid. + """ + input_shape = get_shape_list(input_tensor, expected_rank=3) + batch_size = input_shape[0] + seq_length = input_shape[1] + width = input_shape[2] + + output = input_tensor + + if use_token_type: # 判断是第一句还是第二句，再做相应处理 + if token_type_ids is None: + raise ValueError("`token_type_ids` must be specified if" + "`use_token_type` is True.") + token_type_table = tf.get_variable( + name=token_type_embedding_name, + shape=[token_type_vocab_size, width], + initializer=create_initializer(initializer_range)) + # This vocab will be small so we always do one-hot here, since it is always + # faster for a small vocabulary. + flat_token_type_ids = tf.reshape(token_type_ids, [-1]) + one_hot_ids = tf.one_hot(flat_token_type_ids, depth=token_type_vocab_size) + token_type_embeddings = tf.matmul(one_hot_ids, token_type_table) + token_type_embeddings = tf.reshape(token_type_embeddings, + [batch_size, seq_length, width]) + output += token_type_embeddings + + if use_position_embeddings: # 判断是否要做位置编码信息 + assert_op = tf.assert_less_equal(seq_length, max_position_embeddings) + with tf.control_dependencies([assert_op]): + full_position_embeddings = tf.get_variable( + name=position_embedding_name, + shape=[max_position_embeddings, width], + initializer=create_initializer(initializer_range)) + # Since the position embedding table is a learned variable, we create it + # using a (long) sequence length `max_position_embeddings`. The actual + # sequence length might be shorter than this, for faster training of + # tasks that do not have long sequences. + # + # So `full_position_embeddings` is effectively an embedding table + # for position [0, 1, 2, ..., max_position_embeddings-1], and the current + # sequence has positions [0, 1, 2, ... seq_length-1], so we can just + # perform a slice. + position_embeddings = tf.slice(full_position_embeddings, [0, 0], + [seq_length, -1]) # 如果位置编码给的过大，为了加速只需取出部分 + num_dims = len(output.shape.as_list()) + + # Only the last two dimensions are relevant (`seq_length` and `width`), so + # we broadcast among the first dimensions, which is typically just + # the batch size. + position_broadcast_shape = [] + for _ in range(num_dims - 2): + position_broadcast_shape.append(1) + position_broadcast_shape.extend([seq_length, width]) + position_embeddings = tf.reshape(position_embeddings, + position_broadcast_shape) + output += position_embeddings + + output = layer_norm_and_dropout(output, dropout_prob) + return output +~~~ +