def load_orca_checkpoint(self, path, version, prefix=None):
"""
Load existing checkpoint
:param path: Path to the existing checkpoint.
:param version: checkpoint version, which is the suffix of model.* file,
i.e., for modle.4 file, the version is 4.
:param prefix: optimMethod prefix, for example 'optimMethod-Sequentialf53bddcc'
:return:
"""
from bigdl.nn.layer import Model, Container
from bigdl.optim.optimizer import OptimMethod
import os
try:
self.model = Model.load(
os.path.join(path, "model.{}".format(version)))
assert isinstance(self.model, Container), \
"The loaded model should be a Container, please check your checkpoint type."
self.optimizer = OptimMethod.load(
os.path.join(path, "{}.{}".format(prefix, version)))
except Exception:
raise ValueError(
"Cannot load BigDL checkpoint, please check your checkpoint path "
"and checkpoint type.")
self.estimator = SparkEstimator(self.model, self.optimizer,
self.model_dir)
self.nn_estimator = NNEstimator(self.model, self.loss,
self.feature_preprocessing,
self.label_preprocessing)
if self.optimizer is not None:
self.nn_estimator.setOptimMethod(self.optimizer)
self.nn_model = NNModel(
self.model, feature_preprocessing=self.feature_preprocessing)
def __init__(self,
*,
model,
loss,
optimizer=None,
metrics=None,
feature_preprocessing=None,
label_preprocessing=None,
model_dir=None):
self.loss = loss
self.optimizer = optimizer
self.metrics = Metrics.convert_metrics_list(metrics)
self.feature_preprocessing = feature_preprocessing
self.label_preprocessing = label_preprocessing
self.model_dir = model_dir
self.model = model
self.nn_model = NNModel(
self.model, feature_preprocessing=self.feature_preprocessing)
self.nn_estimator = NNEstimator(self.model, self.loss,
self.feature_preprocessing,
self.label_preprocessing)
if self.optimizer is None:
from bigdl.optim.optimizer import SGD
self.optimizer = SGD()
self.nn_estimator.setOptimMethod(self.optimizer)
self.estimator = SparkEstimator(self.model, self.optimizer,
self.model_dir)
self.log_dir = None
self.app_name = None
self.is_nnframe_fit = False
def load(self, checkpoint, optimizer=None, loss=None, feature_preprocessing=None,
label_preprocessing=None, model_dir=None, is_checkpoint=False):
if loss is not None:
self.loss = loss
if optimizer is not None:
self.optimizer = optimizer
if feature_preprocessing is not None:
self.feature_preprocessing = feature_preprocessing
if label_preprocessing is not None:
self.label_preprocessing = label_preprocessing
if model_dir is not None:
self.model_dir = model_dir
if is_checkpoint:
self.load_latest_orca_checkpoint(checkpoint)
else:
from zoo.pipeline.api.net import Net
self.model = Net.load_bigdl(checkpoint + ".bigdl", checkpoint + ".bin")
self.nn_estimator = NNEstimator(self.model, self.loss, self.feature_preprocessing,
self.label_preprocessing)
if self.optimizer is None:
from bigdl.optim.optimizer import SGD
self.optimizer = SGD()
self.nn_estimator.setOptimMethod(self.optimizer)
self.estimator = SparkEstimator(self.model, self.optimizer, self.model_dir)
self.nn_model = NNModel(self.model, feature_preprocessing=self.feature_preprocessing)
return self
def load_orca_checkpoint(self, path, version=None, prefix=None):
"""
Load existing checkpoint. To load a specific checkpoint, please provide both `version`
and `perfix`. If `version` is None, then the latest checkpoint under the specified
directory will be loaded.
:param path: Path to the existing checkpoint (or directory containing Orca checkpoint
files).
:param version: checkpoint version, which is the suffix of model.* file, i.e., for
modle.4 file, the version is 4. If it is None, then load the latest checkpoint.
:param prefix: optimMethod prefix, for example 'optimMethod-Sequentialf53bddcc'
:return:
"""
from bigdl.nn.layer import Model, Container
from bigdl.optim.optimizer import OptimMethod
from zoo.orca.learn.utils import find_latest_checkpoint
import os
if version is None:
path, prefix, version = find_latest_checkpoint(path,
model_type="bigdl")
if path is None:
raise ValueError(
"Cannot find BigDL checkpoint, please check your checkpoint"
" path.")
else:
assert prefix is not None, "You should provide optimMethod prefix, " \
"for example 'optimMethod-TorchModelf53bddcc'"
try:
self.model = Model.load(
os.path.join(path, "model.{}".format(version)))
assert isinstance(self.model, Container), \
"The loaded model should be a Container, please check your checkpoint type."
self.optimizer = OptimMethod.load(
os.path.join(path, "{}.{}".format(prefix, version)))
except Exception:
raise ValueError(
"Cannot load BigDL checkpoint, please check your checkpoint path "
"and checkpoint type.")
self.estimator = SparkEstimator(self.model, self.optimizer,
self.model_dir)
self.nn_estimator = NNEstimator(self.model, self.loss,
self.feature_preprocessing,
self.label_preprocessing)
if self.optimizer is not None:
self.nn_estimator.setOptimMethod(self.optimizer)
self.nn_model = NNModel(
self.model, feature_preprocessing=self.feature_preprocessing)
def load_orca_checkpoint(self, path, version, prefix=None):
from bigdl.nn.layer import Model, Container
from bigdl.optim.optimizer import OptimMethod
import os
try:
self.model = Model.load(os.path.join(path, "model.{}".format(version)))
assert isinstance(self.model, Container), \
"The loaded model should be a Container, please check your checkpoint type."
self.optimizer = OptimMethod.load(os.path.join(path,
"{}.{}".format(prefix, version)))
except Exception:
raise ValueError("Cannot load BigDL checkpoint, please check your checkpoint path "
"and checkpoint type.")
self.estimator = SparkEstimator(self.model, self.optimizer, self.model_dir)
self.nn_estimator = NNEstimator(self.model, self.loss, self.feature_preprocessing,
self.label_preprocessing)
if self.optimizer is not None:
self.nn_estimator.setOptimMethod(self.optimizer)
self.nn_model = NNModel(self.model, feature_preprocessing=self.feature_preprocessing)
def load(self,
checkpoint,
optimizer=None,
loss=None,
feature_preprocessing=None,
label_preprocessing=None,
model_dir=None,
is_checkpoint=False):
"""
Load existing BigDL model or checkpoint
:param checkpoint: Path to the existing model or checkpoint.
:param optimizer: BigDL optimizer.
:param loss: BigDL criterion.
:param feature_preprocessing: Used when data in `fit` and `predict` is a Spark DataFrame.
The param converts the data in feature column to a Tensor or to a Sample directly.
It expects a List of Int as the size of the converted Tensor, or a Preprocessing[F,
Tensor[T]]
If a List of Int is set as feature_preprocessing, it can only handle the case that
feature column contains the following data types:
Float, Double, Int, Array[Float], Array[Double], Array[Int] and MLlib Vector. The
feature data are converted to Tensors with the specified sizes before
sending to the model. Internally, a SeqToTensor is generated according to the
size, and used as the feature_preprocessing.
Alternatively, user can set feature_preprocessing as Preprocessing[F, Tensor[T]]
that transforms the feature data to a Tensor[T]. Some pre-defined Preprocessing are
provided in package zoo.feature. Multiple Preprocessing can be combined as a
ChainedPreprocessing.
The feature_preprocessing will also be copied to the generated NNModel and applied
to feature column during transform.
:param label_preprocessing: Used when data in `fit` and `predict` is a Spark DataFrame.
similar to feature_preprocessing, but applies to Label data.
:param model_dir: The path to save model. During the training, if checkpoint_trigger is
defined and triggered, the model will be saved to model_dir.
:param is_checkpoint: Whether the path is a checkpoint or a saved BigDL model.
Default: False.
:return: The loaded estimator object.
"""
if loss is not None:
self.loss = loss
if optimizer is not None:
self.optimizer = optimizer
if feature_preprocessing is not None:
self.feature_preprocessing = feature_preprocessing
if label_preprocessing is not None:
self.label_preprocessing = label_preprocessing
if model_dir is not None:
self.model_dir = model_dir
if is_checkpoint:
self.load_latest_orca_checkpoint(checkpoint)
else:
from zoo.pipeline.api.net import Net
self.model = Net.load_bigdl(checkpoint + ".bigdl",
checkpoint + ".bin")
self.nn_estimator = NNEstimator(self.model, self.loss,
self.feature_preprocessing,
self.label_preprocessing)
if self.optimizer is None:
from bigdl.optim.optimizer import SGD
self.optimizer = SGD()
self.nn_estimator.setOptimMethod(self.optimizer)
self.estimator = SparkEstimator(self.model, self.optimizer,
self.model_dir)
self.nn_model = NNModel(
self.model, feature_preprocessing=self.feature_preprocessing)
return self
def load(self,
checkpoint,
optimizer=None,
loss=None,
feature_preprocessing=None,
label_preprocessing=None,
model_dir=None,
is_checkpoint=False):
if loss is not None:
self.loss = loss
if optimizer is not None:
self.optimizer = optimizer
if feature_preprocessing is not None:
self.feature_preprocessing = feature_preprocessing
if label_preprocessing is not None:
self.label_preprocessing = label_preprocessing
if model_dir is not None:
self.model_dir = model_dir
if is_checkpoint:
from zoo.orca.learn.utils import find_latest_checkpoint
from zoo.pipeline.api.net import Net
from bigdl.nn.layer import Model, Container
from bigdl.optim.optimizer import OptimMethod
import os
path, prefix, version = find_latest_checkpoint(checkpoint,
model_type="bigdl")
if path is None:
raise ValueError(
"Cannot find BigDL checkpoint, please check your checkpoint path."
)
try:
self.model = Model.load(
os.path.join(path, "model.{}".format(version)))
assert isinstance(self.model, Container), \
"The loaded model should be a Container, please check your checkpoint type."
self.optimizer = OptimMethod.load(
os.path.join(path, "{}.{}".format(prefix, version)))
except Exception:
raise ValueError(
"Cannot load BigDL checkpoint, please check your checkpoint path "
"and checkpoint type.")
self.estimator = SparkEstimator(self.model, self.optimizer,
self.model_dir)
self.nn_estimator = NNEstimator(self.model, self.loss,
self.feature_preprocessing,
self.label_preprocessing)
if self.optimizer is not None:
self.nn_estimator.setOptimMethod(self.optimizer)
self.nn_model = NNModel(
self.model, feature_preprocessing=self.feature_preprocessing)
else:
from zoo.pipeline.api.net import Net
self.model = Net.load_bigdl(checkpoint + ".bigdl",
checkpoint + ".bin")
self.nn_estimator = NNEstimator(self.model, self.loss,
self.feature_preprocessing,
self.label_preprocessing)
if self.optimizer is None:
from bigdl.optim.optimizer import SGD
self.optimizer = SGD()
self.nn_estimator.setOptimMethod(self.optimizer)
self.estimator = SparkEstimator(self.model, self.optimizer,
self.model_dir)
self.nn_model = NNModel(
self.model, feature_preprocessing=self.feature_preprocessing)
return self