def from_config(cls, task_config, metadata=None, model_state=None):
"""
Create the task from config, and optionally load metadata/model_state
This function will create components including :class:`~DataHandler`,
:class:`~Trainer`, :class:`~MetricReporter`,
:class:`~Exporter`, and wire them up.
Args:
task_config (Task.Config): the config of the current task
metadata: saved global context of this task, e.g: vocabulary, will be
generated by :class:`~DataHandler` if it's None
model_state: saved model parameters, will be loaded into model when given
"""
if hasattr(task_config.labels, "target_prob"):
assert task_config.labels.target_prob == isinstance(
task_config.model.output_layer.loss,
(
KLDivergenceBCELoss.Config,
KLDivergenceCELoss.Config,
SoftHardBCELoss.Config,
),
), "target_prob must be set to True for KD losses"
featurizer = create_featurizer(task_config.featurizer,
task_config.features)
# load data
data_handler = create_data_handler(
task_config.data_handler,
task_config.features,
task_config.labels,
featurizer=featurizer,
)
print("\nLoading data...")
if metadata:
data_handler.load_metadata(metadata)
else:
data_handler.init_metadata()
metadata = data_handler.metadata
model = create_model(task_config.model, task_config.features, metadata)
if model_state:
model.load_state_dict(model_state)
if cuda.CUDA_ENABLED:
model = model.cuda()
metric_reporter = create_metric_reporter(task_config.metric_reporter,
metadata)
exporter = (create_exporter(
task_config.exporter,
task_config.features,
task_config.labels,
data_handler.metadata,
task_config.model,
) if task_config.exporter else None)
return cls(
trainer=create_trainer(task_config.trainer, model),
data_handler=data_handler,
model=model,
metric_reporter=metric_reporter,
exporter=exporter,
)
def _create_dummy_data_handler(self):
feat = WordFeatConfig(
vocab_size=4,
vocab_from_all_data=True,
vocab_from_train_data=True,
vocab_from_pretrained_embeddings=False,
pretrained_embeddings_path=None,
)
featurizer = create_featurizer(SimpleFeaturizer.Config(),
FeatureConfig(word_feat=feat))
data_handler = DocClassificationDataHandler.from_config(
DocClassificationDataHandler.Config(),
ModelInputConfig(word_feat=feat),
TargetConfig(),
featurizer=featurizer,
)
train_data = data_handler.gen_dataset([{
"text": "<pad>"
}],
include_label_fields=False)
eval_data = data_handler.gen_dataset([{
"text": "<pad>"
}],
include_label_fields=False)
test_data = data_handler.gen_dataset([{
"text": "<pad>"
}],
include_label_fields=False)
data_handler.init_feature_metadata(train_data, eval_data, test_data)
return data_handler
def from_config(cls, task_config, metadata=None, model_state=None):
"""
Create the task from config, and optionally load metadata/model_state
This function will create components including :class:`~DataHandler`,
:class:`~Trainer`, :class:`~Optimizer`, :class:`~Scheduler`,
:class:`~MetricReporter`, :class:`~Exporter`, and wire them up.
Args:
task_config (Task.Config): the config of the current task
metadata: saved global context of this task, e.g: vocabulary, will be
generated by :class:`~DataHandler` if it's None
model_state: saved model parameters, will be loaded into model when given
"""
print("Task parameters:\n")
pprint(config_to_json(type(task_config), task_config))
featurizer = create_featurizer(task_config.featurizer, task_config.features)
# load data
data_handler = create_data_handler(
task_config.data_handler,
task_config.features,
task_config.labels,
featurizer=featurizer,
)
print("\nLoading data...")
if metadata:
data_handler.load_metadata(metadata)
else:
data_handler.init_metadata()
metadata = data_handler.metadata
model = create_model(task_config.model, task_config.features, metadata)
if model_state:
model.load_state_dict(model_state)
if cuda_utils.CUDA_ENABLED:
model = model.cuda()
metric_reporter = create_metric_reporter(task_config.metric_reporter, metadata)
optimizer = create_optimizer(task_config.optimizer, model)
exporter = (
create_exporter(
task_config.exporter,
task_config.features,
task_config.labels,
data_handler.metadata,
task_config.model,
)
if task_config.exporter
else None
)
return cls(
trainer=create_trainer(task_config.trainer),
data_handler=data_handler,
model=model,
metric_reporter=metric_reporter,
optimizer=optimizer,
lr_scheduler=Scheduler(
optimizer, task_config.scheduler, metric_reporter.lower_is_better
),
exporter=exporter,
)
def test_read_partially_from_csv(self):
file_name = tests_module.test_file("train_data_tiny.tsv")
columns = {DFColumn.DOC_LABEL: 0, DFColumn.UTTERANCE: 2}
feat = WordFeatConfig(
vocab_from_all_data=True,
vocab_from_train_data=False,
vocab_from_pretrained_embeddings=False,
)
featurizer = create_featurizer(
SimpleFeaturizer.Config(), FeatureConfig(word_feat=feat)
)
data_handler = DocClassificationDataHandler.from_config(
DocClassificationDataHandler.Config(),
ModelInputConfig(word_feat=feat),
TargetConfig(),
featurizer=featurizer,
)
data = list(data_handler.read_from_file(file_name, columns))
for col in columns:
self.assertTrue(col in data[0], "{} must in the data".format(col))
self.assertEqual("alarm/modify_alarm", data[0][DFColumn.DOC_LABEL])
self.assertEqual(
"change my alarm tomorrow to wake me up 30 minutes earlier",
data[0][DFColumn.UTTERANCE],
)
def from_config(cls, task_config, metadata=None, model_state=None):
print("Task parameters:\n")
pprint(config_to_json(type(task_config), task_config))
data_handlers = OrderedDict()
exporters = OrderedDict()
for name, task in task_config.tasks.items():
featurizer = create_featurizer(task.featurizer, task.features)
data_handlers[name] = create_data_handler(task.data_handler,
task.features,
task.labels,
featurizer=featurizer)
data_handler = DisjointMultitaskDataHandler(task_config.data_handler,
data_handlers)
print("\nLoading data...")
if metadata:
data_handler.load_metadata(metadata)
else:
data_handler.init_metadata()
metadata = data_handler.metadata
exporters = {
name: (create_exporter(
task.exporter,
task.features,
task.labels,
data_handler.data_handlers[name].metadata,
task.model,
) if task.exporter else None)
for name, task in task_config.tasks.items()
}
metric_reporter = DisjointMultitaskMetricReporter(
OrderedDict(
(name,
create_metric_reporter(task.metric_reporter, metadata[name]))
for name, task in task_config.tasks.items()),
target_task_name=task_config.metric_reporter.target_task_name,
)
model = DisjointMultitaskModel(
OrderedDict(
(name, create_model(task.model, task.features, metadata[name]))
for name, task in task_config.tasks.items()))
if model_state:
model.load_state_dict(model_state)
if cuda_utils.CUDA_ENABLED:
model = model.cuda()
optimizers = create_optimizer(model, task_config.optimizer)
return cls(
exporters=exporters,
trainer=create_trainer(task_config.trainer),
data_handler=data_handler,
model=model,
metric_reporter=metric_reporter,
optimizers=optimizers,
lr_scheduler=Scheduler(optimizers, task_config.scheduler,
metric_reporter.lower_is_better),
)
def _init_data_handler(self):
data_handler = LanguageModelDataHandler.from_config(
LanguageModelDataHandler.Config(),
FeatureConfig(),
WordLabelConfig(),
featurizer=create_featurizer(SimpleFeaturizer.Config(), FeatureConfig()),
shuffle=False,
)
data_handler.init_metadata_from_path(FILE_NAME, FILE_NAME, FILE_NAME)
return data_handler
def from_config(cls, task_config, metadata=None, model_state=None):
print("(mldc/task/gpt_task.py def from_config) Task parameters:\n")
pprint(config_to_json(type(task_config), task_config))
featurizer = create_featurizer(
task_config.featurizer,
task_config.features,
text_embedder_config=task_config.text_embedder
) # featurizer :: text embedder GPT2Embed
# load data
data_handler = create_data_handler(
task_config.data_handler,
task_config.features,
task_config.labels,
text_embedder_config=task_config.text_embedder,
featurizer=featurizer,
)
print(
"\n(mldc/task/retrieval.py GptTask def from_config) Loading data..."
)
if metadata:
data_handler.load_metadata(metadata)
else:
data_handler.init_metadata()
metadata = data_handler.metadata
task_config.features.seq_word_feat.embed_dim = data_handler.text_embedder.embed_dim
print("create model!")
model = create_model(task_config.model, task_config.features, metadata)
if model_state:
model.load_state_dict(model_state)
if cuda_utils.CUDA_ENABLED:
model = model.cuda()
metric_reporter = create_metric_reporter(
task_config.metric_reporter,
metadata,
text_embedder=task_config.text_embedder)
return cls(
trainer=create_trainer(task_config.trainer),
data_handler=data_handler,
model=model,
metric_reporter=metric_reporter,
model_needs_meta_training=task_config.model_needs_meta_training,
)
def create_language_model_data_handler(cls) -> LanguageModelDataHandler:
# TODO: Refactor this after Shicong refactors PyText config and removes
# Thrift. After that directly use Data Handler's from config method
# with synthetic configs
columns = [DFColumn.UTTERANCE]
features: Dict[str, Field] = {
DatasetFieldName.TEXT_FIELD: TextFeatureField(
eos_token=VocabMeta.EOS_TOKEN, init_token=VocabMeta.INIT_TOKEN
)
}
return LanguageModelDataHandler(
raw_columns=columns,
features=features,
labels={},
featurizer=create_featurizer(SimpleFeaturizer.Config(), FeatureConfig()),
)
def from_config(
cls,
task_config: Config,
metadata=None,
model_state=None,
tensorizers=None,
rank=0,
world_size=1,
):
print("Task parameters:\n")
pprint(config_to_json(type(task_config), task_config))
data_handlers = OrderedDict()
exporters = OrderedDict()
for name, task in task_config.tasks.items():
featurizer = create_featurizer(task.featurizer, task.features)
data_handlers[name] = create_data_handler(
task.data_handler, task.features, task.labels, featurizer=featurizer
)
data_handler = DisjointMultitaskDataHandler(
task_config.data_handler,
data_handlers,
target_task_name=task_config.target_task_name,
)
print("\nLoading data...")
if metadata:
data_handler.load_metadata(metadata)
else:
data_handler.init_metadata()
metadata = data_handler.metadata
exporters = {
name: (
create_exporter(
task.exporter,
task.features,
task.labels,
data_handler.data_handlers[name].metadata,
task.model,
)
if task.exporter
else None
)
for name, task in task_config.tasks.items()
}
task_weights = {
task_name: task_config.task_weights.get(task_name, 1)
for task_name in task_config.tasks.keys()
}
metric_reporter = DisjointMultitaskMetricReporter(
OrderedDict(
(name, create_metric_reporter(task.metric_reporter, metadata[name]))
for name, task in task_config.tasks.items()
),
loss_weights=task_weights,
target_task_name=task_config.target_task_name,
use_subtask_select_metric=(
task_config.metric_reporter.use_subtask_select_metric
),
)
model = DisjointMultitaskModel(
OrderedDict(
(name, create_model(task.model, task.features, metadata[name]))
for name, task in task_config.tasks.items()
),
loss_weights=task_weights,
)
if model_state:
model.load_state_dict(model_state)
if cuda.CUDA_ENABLED:
model = model.cuda()
return cls(
target_task_name=task_config.target_task_name,
exporters=exporters,
trainer=create_trainer(task_config.trainer, model),
data_handler=data_handler,
model=model,
metric_reporter=metric_reporter,
)