def __init__(self, train_data, model, loss=None, metrics=None, n_epochs=3, batch_size=32, print_every=50,
validate_every=-1, dev_data=None, use_cuda=False, save_path=None,
optimizer=Adam(lr=0.01, weight_decay=0), check_code_level=0,
metric_key=None, sampler=RandomSampler(), use_tqdm=True):
super(Trainer, self).__init__()
if not isinstance(train_data, DataSet):
raise TypeError(f"The type of train_data must be fastNLP.DataSet, got {type(train_data)}.")
if not isinstance(model, nn.Module):
raise TypeError(f"The type of model must be torch.nn.Module, got {type(model)}.")
# check metrics and dev_data
if (not metrics) and dev_data is not None:
raise ValueError("No metric for dev_data evaluation.")
if metrics and (dev_data is None):
raise ValueError("No dev_data for evaluations, pass dev_data or set metrics to None. ")
# check save_path
if not (save_path is None or isinstance(save_path, str)):
raise ValueError("save_path can only be None or `str`.")
# prepare evaluate
metrics = _prepare_metrics(metrics)
# parse metric_key
# increase_better is True. It means the exp result gets better if the indicator increases.
# It is true by default.
self.increase_better = True
if metric_key is not None:
self.increase_better = False if metric_key[0] == "-" else True
self.metric_key = metric_key[1:] if metric_key[0] == "+" or metric_key[0] == "-" else metric_key
elif len(metrics) > 0:
self.metric_key = metrics[0].__class__.__name__.lower().strip('metric')
# prepare loss
losser = _prepare_losser(loss)
# sampler check
if not isinstance(sampler, BaseSampler):
raise ValueError("The type of sampler should be fastNLP.BaseSampler, got {}.".format(type(sampler)))
if check_code_level > -1:
_check_code(dataset=train_data, model=model, losser=losser, metrics=metrics, dev_data=dev_data,
metric_key=metric_key, check_level=check_code_level,
batch_size=min(batch_size, DEFAULT_CHECK_BATCH_SIZE))
self.train_data = train_data
self.dev_data = dev_data # If None, No validation.
self.model = model
self.losser = losser
self.metrics = metrics
self.n_epochs = int(n_epochs)
self.batch_size = int(batch_size)
self.use_cuda = bool(use_cuda)
self.save_path = save_path
self.print_every = int(print_every)
self.validate_every = int(validate_every)
self.best_metric_indicator = None
self.sampler = sampler
if isinstance(optimizer, torch.optim.Optimizer):
self.optimizer = optimizer
else:
self.optimizer = optimizer.construct_from_pytorch(self.model.parameters())
self.use_tqdm = use_tqdm
if self.use_tqdm:
tester_verbose = 0
self.print_every = abs(self.print_every)
else:
tester_verbose = 1
if self.dev_data is not None:
self.tester = Tester(model=self.model,
data=self.dev_data,
metrics=self.metrics,
batch_size=self.batch_size,
use_cuda=self.use_cuda,
verbose=tester_verbose)
self.step = 0
self.start_time = None # start timestamp
def __init__(self,
train_data,
model,
loss=None,
metrics=None,
n_epochs=3,
batch_size=32,
print_every=50,
validate_every=-1,
dev_data=None,
use_cuda=False,
save_path=None,
optimizer=Adam(lr=0.01, weight_decay=0),
check_code_level=0,
metric_key=None,
sampler=RandomSampler(),
use_tqdm=True):
"""
:param DataSet train_data: the training data
:param torch.nn.modules.module model: a PyTorch model
:param LossBase loss: a loss object
:param MetricBase or List[MetricBase] metrics: a metric object or a list of metrics
:param int n_epochs: the number of training epochs
:param int batch_size: batch size for training and validation
:param int print_every: step interval to print next training information. Default: -1(no print).
:param int validate_every: step interval to do next validation. Default: -1(validate every epoch).
:param DataSet dev_data: the validation data
:param use_cuda:
:param save_path: file path to save models
:param Optimizer optimizer: an optimizer object
:param int check_code_level: level of FastNLP code checker. -1: don't check, 0: ignore. 1: warning. 2: strict.
`ignore` will not check unused field; `warning` when warn if some field are not used; `strict` means
it will raise error if some field are not used.
:param str metric_key: a single indicator used to decide the best model based on metric results. It must be one
of the keys returned by the FIRST metric in `metrics`. If the overall result gets better if the indicator gets
smaller, add a `-` character in front of the string. For example
::
metric_key="-PPL" # language model gets better as perplexity gets smaller
:param sampler: method used to generate batch data.
:param use_tqdm: boolean, use tqdm to show train progress.
"""
super(Trainer, self).__init__()
if not isinstance(train_data, DataSet):
raise TypeError(
f"The type of train_data must be fastNLP.DataSet, got {type(train_data)}."
)
if not isinstance(model, nn.Module):
raise TypeError(
f"The type of model must be torch.nn.Module, got {type(model)}."
)
# check metrics and dev_data
if (not metrics) and dev_data is not None:
raise ValueError("No metric for dev_data evaluation.")
if metrics and (dev_data is None):
raise ValueError(
"No dev_data for evaluations, pass dev_data or set metrics to None. "
)
# check save_path
if not (save_path is None or isinstance(save_path, str)):
raise ValueError("save_path can only be None or `str`.")
# prepare evaluate
metrics = _prepare_metrics(metrics)
# parse metric_key
# increase_better is True. It means the exp result gets better if the indicator increases.
# It is true by default.
self.increase_better = True
if metric_key is not None:
self.increase_better = False if metric_key[0] == "-" else True
self.metric_key = metric_key[1:] if metric_key[
0] == "+" or metric_key[0] == "-" else metric_key
elif len(metrics) > 0:
self.metric_key = metrics[0].__class__.__name__.lower().strip(
'metric')
# prepare loss
losser = _prepare_losser(loss)
# sampler check
if not isinstance(sampler, BaseSampler):
raise ValueError(
"The type of sampler should be fastNLP.BaseSampler, got {}.".
format(type(sampler)))
if check_code_level > -1:
_check_code(dataset=train_data,
model=model,
losser=losser,
metrics=metrics,
dev_data=dev_data,
metric_key=metric_key,
check_level=check_code_level,
batch_size=min(batch_size, DEFAULT_CHECK_BATCH_SIZE))
self.train_data = train_data
self.dev_data = dev_data # If None, No validation.
self.model = model
self.losser = losser
self.metrics = metrics
self.n_epochs = int(n_epochs)
self.batch_size = int(batch_size)
self.use_cuda = bool(use_cuda)
self.save_path = save_path
self.print_every = int(print_every)
self.validate_every = int(validate_every)
self.best_metric_indicator = None
self.sampler = sampler
if isinstance(optimizer, torch.optim.Optimizer):
self.optimizer = optimizer
else:
self.optimizer = optimizer.construct_from_pytorch(
self.model.parameters())
self.use_tqdm = use_tqdm
if self.use_tqdm:
tester_verbose = 0
self.print_every = abs(self.print_every)
else:
tester_verbose = 1
if self.dev_data is not None:
self.tester = Tester(model=self.model,
data=self.dev_data,
metrics=self.metrics,
batch_size=self.batch_size,
use_cuda=self.use_cuda,
verbose=tester_verbose)
self.step = 0
self.start_time = None # start timestamp
def __init__(self, train_data, model, loss=None, metrics=None, n_epochs=3, batch_size=32, print_every=50,
validate_every=-1, dev_data=None, save_path=None, optimizer=Adam(lr=0.01, weight_decay=0),
check_code_level=0, metric_key=None, sampler=RandomSampler(), prefetch=False, use_tqdm=True,
use_cuda=False, callbacks=None):
"""
:param DataSet train_data: the training data
:param torch.nn.modules.module model: a PyTorch model
:param LossBase loss: a loss object
:param MetricBase metrics: a metric object or a list of metrics (List[MetricBase])
:param int n_epochs: the number of training epochs
:param int batch_size: batch size for training and validation
:param int print_every: step interval to print next training information. Default: -1(no print).
:param int validate_every: step interval to do next validation. Default: -1(validate every epoch).
:param DataSet dev_data: the validation data
:param str save_path: file path to save models
:param Optimizer optimizer: an optimizer object
:param int check_code_level: level of FastNLP code checker. -1: don't check, 0: ignore. 1: warning. 2: strict.\\
`ignore` will not check unused field; `warning` when warn if some field are not used; `strict` means
it will raise error if some field are not used. 检查的原理是通过使用很小的batch(默认两个sample)来检查代码是
否能够运行，但是这个过程理论上不会修改任何参数，只是会检查能否运行。但如果(1)模型中存在将batch_size写为某个
固定值的情况；(2)模型中存在累加前向计算次数的，可能会多计算几次。以上情况建议将check_code_level设置为-1
:param str metric_key: a single indicator used to decide the best model based on metric results. It must be one
of the keys returned by the FIRST metric in `metrics`. If the overall result gets better if the indicator gets
smaller, add "-" in front of the string. For example::
metric_key="-PPL" # language model gets better as perplexity gets smaller
:param BaseSampler sampler: method used to generate batch data.
:param prefetch: bool, 是否使用额外的进程对产生batch数据。
:param bool use_tqdm: whether to use tqdm to show train progress.
:param callbacks: List[Callback]. 用于在train过程中起调节作用的回调函数。比如early stop，negative sampling等可以
通过callback机制实现。
"""
super(Trainer, self).__init__()
if not isinstance(train_data, DataSet):
raise TypeError(f"The type of train_data must be fastNLP.DataSet, got {type(train_data)}.")
if not isinstance(model, nn.Module):
raise TypeError(f"The type of model must be torch.nn.Module, got {type(model)}.")
# check metrics and dev_data
if (not metrics) and dev_data is not None:
raise ValueError("No metric for dev_data evaluation.")
if metrics and (dev_data is None):
raise ValueError("No dev_data for evaluations, pass dev_data or set metrics to None. ")
# check save_path
if not (save_path is None or isinstance(save_path, str)):
raise ValueError("save_path can only be None or `str`.")
# prepare evaluate
metrics = _prepare_metrics(metrics)
# parse metric_key
# increase_better is True. It means the exp result gets better if the indicator increases.
# It is true by default.
self.increase_better = True
if metric_key is not None:
self.increase_better = False if metric_key[0] == "-" else True
self.metric_key = metric_key[1:] if metric_key[0] == "+" or metric_key[0] == "-" else metric_key
elif len(metrics) > 0:
self.metric_key = metrics[0].__class__.__name__.lower().strip('metric')
# prepare loss
losser = _prepare_losser(loss)
# sampler check
if not isinstance(sampler, BaseSampler):
raise ValueError("The type of sampler should be fastNLP.BaseSampler, got {}.".format(type(sampler)))
if check_code_level > -1:
_check_code(dataset=train_data, model=model, losser=losser, metrics=metrics, dev_data=dev_data,
metric_key=metric_key, check_level=check_code_level,
batch_size=min(batch_size, DEFAULT_CHECK_BATCH_SIZE))
self.train_data = train_data
self.dev_data = dev_data # If None, No validation.
self.model = model
self.losser = losser
self.metrics = metrics
self.n_epochs = int(n_epochs)
self.batch_size = int(batch_size)
self.use_cuda = bool(use_cuda)
self.save_path = save_path
self.print_every = int(print_every)
self.validate_every = int(validate_every) if validate_every!=0 else -1
self.best_metric_indicator = None
self.best_dev_epoch = None
self.best_dev_step = None
self.best_dev_perf = None
self.sampler = sampler
self.prefetch = prefetch
self.callback_manager = CallbackManager(env={"trainer": self}, callbacks=callbacks)
if isinstance(optimizer, torch.optim.Optimizer):
self.optimizer = optimizer
else:
self.optimizer = optimizer.construct_from_pytorch(self.model.parameters())
self.use_tqdm = use_tqdm
self.print_every = abs(self.print_every)
if self.dev_data is not None:
self.tester = Tester(model=self.model,
data=self.dev_data,
metrics=self.metrics,
batch_size=self.batch_size,
use_cuda=self.use_cuda,
verbose=0)
self.step = 0
self.start_time = None # start timestamp