def __init__(
self,
task: str = None,
load_checkpoint: str = None,
label_map: Dict = None,
num_classes: int = 2,
**kwargs,
):
super(ErnieV2, self).__init__()
if label_map:
self.label_map = label_map
self.num_classes = len(label_map)
else:
self.num_classes = num_classes
if task == 'sequence_classification':
task = 'seq-cls'
logger.warning(
"current task name 'sequence_classification' was renamed to 'seq-cls', "
"'sequence_classification' has been deprecated and will be removed in the future.",
)
if task == 'seq-cls':
self.model = ErnieForSequenceClassification.from_pretrained(
pretrained_model_name_or_path='ernie-2.0-en',
num_classes=self.num_classes,
**kwargs)
self.criterion = paddle.nn.loss.CrossEntropyLoss()
self.metric = paddle.metric.Accuracy()
elif task == 'token-cls':
self.model = ErnieForTokenClassification.from_pretrained(
pretrained_model_name_or_path='ernie-2.0-en',
num_classes=self.num_classes,
**kwargs)
self.criterion = paddle.nn.loss.CrossEntropyLoss()
self.metric = ChunkEvaluator(label_list=[
self.label_map[i] for i in sorted(self.label_map.keys())
])
elif task == 'text-matching':
self.model = ErnieModel.from_pretrained(
pretrained_model_name_or_path='ernie-2.0-en', **kwargs)
self.dropout = paddle.nn.Dropout(0.1)
self.classifier = paddle.nn.Linear(
self.model.config['hidden_size'] * 3, 2)
self.criterion = paddle.nn.loss.CrossEntropyLoss()
self.metric = paddle.metric.Accuracy()
elif task is None:
self.model = ErnieModel.from_pretrained(
pretrained_model_name_or_path='ernie-2.0-en', **kwargs)
else:
raise RuntimeError(
"Unknown task {}, task should be one in {}".format(
task, self._tasks_supported))
self.task = task
if load_checkpoint is not None and os.path.isfile(load_checkpoint):
state_dict = paddle.load(load_checkpoint)
self.set_state_dict(state_dict)
logger.info('Loaded parameters from %s' %
os.path.abspath(load_checkpoint))
def __init__(self, config: CNNConfig, name_scope=None, dtype="float32"):
super().__init__(name_scope, dtype)
self.pretrained_model = ErnieModel.from_pretrained(
config.pretrained_model)
self.encoder = CNNEncoder(emb_dim=768,
num_filter=config.num_filter,
ngram_filter_sizes=config.filter_sizes,
conv_layer_activation=get_activation(
config.activation))
self.dropout = nn.Dropout(p=config.dropout)
self.classifier = nn.Linear(in_features=self.encoder.get_output_dim(),
out_features=config.num_labels)
def __init__(
self,
task=None,
load_checkpoint=None,
label_map=None,
num_classes=2,
**kwargs,
):
super(ErnieTiny, self).__init__()
if label_map:
self.num_classes = len(label_map)
else:
self.num_classes = num_classes
if task == 'sequence_classification':
task = 'seq-cls'
logger.warning(
"current task name 'sequence_classification' was renamed to 'seq-cls', "
"'sequence_classification' has been deprecated and will be removed the future.",
)
if task == 'seq-cls':
self.model = ErnieForSequenceClassification.from_pretrained(
pretrained_model_name_or_path='ernie-tiny',
num_classes=self.num_classes,
**kwargs)
self.criterion = paddle.nn.loss.CrossEntropyLoss()
self.metric = paddle.metric.Accuracy()
elif task == 'token-cls':
self.model = ErnieForTokenClassification.from_pretrained(
pretrained_model_name_or_path='ernie-tiny',
num_classes=self.num_classes,
**kwargs)
self.criterion = paddle.nn.loss.CrossEntropyLoss()
self.metric = paddle.metric.Accuracy()
elif task is None:
self.model = ErnieModel.from_pretrained(
pretrained_model_name_or_path='ernie-tiny', **kwargs)
else:
raise RuntimeError(
"Unknown task {}, task should be one in {}".format(
task, self._tasks_supported))
self.task = task
self.label_map = label_map
if load_checkpoint is not None and os.path.isfile(load_checkpoint):
state_dict = paddle.load(load_checkpoint)
self.set_state_dict(state_dict)
logger.info('Loaded parameters from %s' %
os.path.abspath(load_checkpoint))
def __init__(self, config: RNNConfig, name_scope=None, dtype="float32"):
super().__init__(name_scope, dtype)
self.pretrained_model = ErnieModel.from_pretrained(
config.pretrained_model)
self.encoder = RNNEncoder(
input_size=768,
hidden_size=config.hidden_size,
num_layers=config.num_layers,
direction='bidirect' if config.bidirection else 'forward',
dropout=config.dropout,
pooling_type=config.pooling_type)
self.dropout = nn.Dropout(p=config.dropout)
self.classifier = nn.Linear(in_features=self.encoder.get_output_dim(),
out_features=config.num_labels)
self.config = config