我执行了这个优秀的教程： https ://towardsdatascience.com/building-a-multi-label-text-classifier-using-bert-and-tensorflow-f188e0ecdc5d
我理解了大部分内容，除了创建模型的地方。我想知道它并迁移到 TF2 伯特。
- 当他说“基本上我们加载预训练的模型，然后训练最后一层进行分类任务。”时，这是否意味着他正在冻结所有其他层并微调最后一层？这是我无法理解的相关代码（在 TF1 中）：
def create_model(bert_config, is_training, input_ids, input_mask, segment_ids,
labels, num_labels, use_one_hot_embeddings):
"""Creates a classification model."""
model = modeling.BertModel(
config=bert_config,
is_training=is_training,
input_ids=input_ids,
input_mask=input_mask,
token_type_ids=segment_ids,
use_one_hot_embeddings=use_one_hot_embeddings)
output_layer = model.get_pooled_output()
hidden_size = output_layer.shape[-1].value
output_weights = tf.get_variable(
"output_weights", [num_labels, hidden_size],
initializer=tf.truncated_normal_initializer(stddev=0.02))
output_bias = tf.get_variable(
"output_bias", [num_labels], initializer=tf.zeros_initializer())
with tf.variable_scope("loss"):
if is_training:
# I.e., 0.1 dropout
output_layer = tf.nn.dropout(output_layer, keep_prob=0.9)
logits = tf.matmul(output_layer, output_weights, transpose_b=True)
logits = tf.nn.bias_add(logits, output_bias)
# probabilities = tf.nn.softmax(logits, axis=-1) ### multiclass case
probabilities = tf.nn.sigmoid(logits)#### multi-label case
labels = tf.cast(labels, tf.float32)
tf.logging.info("num_labels:{};logits:{};labels:{}".format(num_labels, logits, labels))
per_example_loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=labels, logits=logits)
loss = tf.reduce_mean(per_example_loss)
return (loss, per_example_loss, logits, probabilities)
- 我浏览了 BERT 的 TF2 微调教程，但我该如何实现呢？我能够训练不需要步骤 1 的其他模型。