def train(self, checkpoint=None):
self._load_dataset()
baseline.save_vectorizers(self.get_basedir(), self.vectorizers)
model = self._create_model()
conll_output = self.config_params.get("conll_output", None)
train_params = self.config_params['train']
train_params['checkpoint'] = checkpoint
metrics = baseline.train.fit(model, self.train_data, self.valid_data, self.test_data,
conll_output=conll_output,
txts=self.txts, **train_params)
baseline.zip_files(self.get_basedir())
self._close_reporting_hooks()
return model, metrics
def train(self, checkpoint=None):
self._load_dataset()
baseline.save_vectorizers(self.get_basedir(), self.vectorizers)
model = self._create_model()
conll_output = self.config_params.get("conll_output", None)
train_params = self.config_params['train']
train_params['checkpoint'] = checkpoint
metrics = baseline.train.fit(model, self.train_data, self.valid_data, self.test_data,
conll_output=conll_output,
txts=self.txts, **train_params)
baseline.zip_files(self.get_basedir())
self._close_reporting_hooks()
return model, metrics
def train(self, checkpoint=None):
self._reorganize_params()
self._load_dataset()
# Dont do this here! We need to move train_data elsewhere
calc_lr_params(self.config_params['train'], self.train_data.steps)
baseline.save_vectorizers(self.get_basedir(), self.vectorizers)
model_params = self.config_params['model']
model_params['task'] = self.task_name()
model_params['features'] = self._get_features()
train_params = self.config_params['train']
train_params['checkpoint'] = checkpoint
baseline.train.fit(model_params, self.train_data, self.valid_data, self.test_data, **train_params)
baseline.zip_files(self.get_basedir())
self._close_reporting_hooks()
def train(self):
self._load_dataset()
if self.config_params['train'].get('lr_scheduler_type',
None) == 'zaremba':
first_range = int(
self.config_params['train']['start_decay_epoch'] *
self.train_data.steps)
self.config_params['train']['bounds'] = [first_range] + list(
np.arange(self.config_params['train']['start_decay_epoch'] + 1,
self.config_params['train']['epochs'] + 1,
dtype=np.int32) * self.train_data.steps)
baseline.save_vectorizers(self.get_basedir(), self.vectorizers)
model = self._create_model()
baseline.train.fit(model, self.train_data, self.valid_data,
self.test_data, **self.config_params['train'])
baseline.zip_files(self.get_basedir())
self._close_reporting_hooks()
def train(self):
"""This method delegates to several sub-hooks in order to complete training.
1. call `_load_dataset()` which initializes the `DataFeed` fields of this class
2. call `baseline.save_vectorizers()` which write out the bound `vectorizers` fields to a file in the `basedir`
3. call `baseline.train.fit()` which executes the training procedure and yields a saved model
4. call `baseline.zip_files()` which zips all files in the `basedir` with the same `PID` as this process
5. call `_close_reporting_hooks()` which lets the reporting hooks know that the job is finished
:return: Nothing
"""
self._load_dataset()
baseline.save_vectorizers(self.get_basedir(), self.vectorizers)
model = self._create_model()
baseline.train.fit(model, self.train_data, self.valid_data,
self.test_data, **self.config_params['train'])
baseline.zip_files(self.get_basedir())
self._close_reporting_hooks()
def train(self, checkpoint=None):
self._load_dataset()
if self.config_params['train'].get('lr_scheduler_type', None) == 'zaremba':
first_range = int(self.config_params['train']['start_decay_epoch'] * self.train_data.steps)
self.config_params['train']['bounds'] = [first_range] + list(
np.arange(
self.config_params['train']['start_decay_epoch'] + 1,
self.config_params['train']['epochs'] + 1,
dtype=np.int32
) * self.train_data.steps
)
baseline.save_vectorizers(self.get_basedir(), self.vectorizers)
model = self._create_model()
train_params = self.config_params['train']
train_params['checkpoint'] = checkpoint
metrics = baseline.train.fit(model, self.train_data, self.valid_data, self.test_data, **train_params)
baseline.zip_files(self.get_basedir())
self._close_reporting_hooks()
return model, metrics
def train(self, checkpoint=None):
"""This method delegates to several sub-hooks in order to complete training.
1. call `_load_dataset()` which initializes the `DataFeed` fields of this class
2. call `baseline.save_vectorizers()` which write out the bound `vectorizers` fields to a file in the `basedir`
3. call `baseline.train.fit()` which executes the training procedure and yields a saved model
4. call `baseline.zip_files()` which zips all files in the `basedir` with the same `PID` as this process
5. call `_close_reporting_hooks()` which lets the reporting hooks know that the job is finished
:return: Nothing
"""
self._load_dataset()
baseline.save_vectorizers(self.get_basedir(), self.vectorizers)
model = self._create_model()
train_params = self.config_params['train']
train_params['checkpoint'] = checkpoint
metrics = baseline.train.fit(model, self.train_data, self.valid_data, self.test_data, **train_params)
baseline.zip_files(self.get_basedir())
self._close_reporting_hooks()
return model, metrics
def train(self, checkpoint=None):
self._load_dataset()
baseline.save_vectorizers(self.get_basedir(), self.vectorizers)
self._reorganize_params()
conll_output = self.config_params.get("conll_output", None)
model_params = self.config_params['model']
model_params['features'] = self._get_features()
model_params['labels'] = self._get_labels()
model_params['task'] = self.task_name()
train_params = self.config_params['train']
train_params['checkpoint'] = checkpoint
train_params['conll_output'] = conll_output
train_params['txts'] = self.txts
if conll_output is not None:
dir_name = os.path.dirname(conll_output)
if dir_name:
os.makedirs(dir_name, exist_ok=True)
baseline.train.fit(model_params, self.train_data, self.valid_data, self.test_data, **train_params)
baseline.zip_files(self.get_basedir())
self._close_reporting_hooks()
def train(self, checkpoint=None):
"""This method delegates to several sub-hooks in order to complete training.
1. call `_load_dataset()` which initializes the `DataFeed` fields of this class
2. call `baseline.save_vectorizers()` which write out the bound `vectorizers` fields to a file in the `basedir`
3. call `baseline.train.fit()` which executes the training procedure and yields a saved model
4. call `baseline.zip_files()` which zips all files in the `basedir` with the same `PID` as this process
5. call `_close_reporting_hooks()` which lets the reporting hooks know that the job is finished
:return: Nothing
"""
self._reorganize_params()
baseline.save_vectorizers(self.get_basedir(), self.vectorizers)
self._load_dataset()
model_params = self.config_params['model']
model_params['features'] = self._get_features()
model_params['labels'] = self._get_labels()
model_params['task'] = self.task_name()
train_params = self.config_params['train']
train_params['checkpoint'] = checkpoint
baseline.train.fit(model_params, self.train_data, self.valid_data, self.test_data, **train_params)
baseline.zip_files(self.get_basedir())
self._close_reporting_hooks()
