本文整理汇总了Python中pytorch_pretrained_bert.modeling.BertConfig.from_json_file方法的典型用法代码示例。如果您正苦于以下问题：Python BertConfig.from_json_file方法的具体用法？Python BertConfig.from_json_file怎么用？Python BertConfig.from_json_file使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类pytorch_pretrained_bert.modeling.BertConfig的用法示例。
在下文中一共展示了BertConfig.from_json_file方法的2个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: __init__
# 需要导入模块: from pytorch_pretrained_bert.modeling import BertConfig [as 别名]
# 或者: from pytorch_pretrained_bert.modeling.BertConfig import from_json_file [as 别名]
def __init__(self, bert_config: str,
requires_grad: bool = False,
dropout: float = 0.1,
layer_dropout: float = 0.1,
combine_layers: str = "mix") -> None:
model = BertModel(BertConfig.from_json_file(bert_config))
for param in model.parameters():
param.requires_grad = requires_grad
super().__init__(bert_model=model,
layer_dropout=layer_dropout,
combine_layers=combine_layers)
self.model = model
self.dropout = dropout
self.set_dropout(dropout) 示例2: convert_tf_checkpoint_to_pytorch
# 需要导入模块: from pytorch_pretrained_bert.modeling import BertConfig [as 别名]
# 或者: from pytorch_pretrained_bert.modeling.BertConfig import from_json_file [as 别名]
def convert_tf_checkpoint_to_pytorch(tf_checkpoint_path, bert_config_file, pytorch_dump_path):
# Initialise PyTorch model
config = BertConfig.from_json_file(bert_config_file)
print("Building PyTorch model from configuration: {}".format(str(config)))
model = BertForPreTraining(config)
# Load weights from tf checkpoint
load_tf_weights_in_bert(model, tf_checkpoint_path)
# Save pytorch-model
print("Save PyTorch model to {}".format(pytorch_dump_path))
torch.save(model.state_dict(), pytorch_dump_path) 开发者ID:649453932，项目名称:Bert-Chinese-Text-Classification-Pytorch，代码行数:14，代码来源:convert_tf_checkpoint_to_pytorch.py