def load(self, model_path):
"""
Load the Estimator state (model and possibly with optimizer) from provided model_path.
The model file should be generated by the save method of this estimator, or by
``torch.save(state_dict, model_path)``, where `state_dict` can be obtained by
the ``state_dict()`` method of a pytorch model.
:param model_path: path to the saved model.
:return:
"""
from zoo.pipeline.api.torch import TorchModel
import os
try:
pytorch_model = self.get_model()
pytorch_model.load_state_dict(torch.load(model_path))
self.model = TorchModel.from_pytorch(pytorch_model)
except Exception:
raise ValueError(
"Cannot load the PyTorch model. Please check your model path.")
optim_path = self._get_optimizer_path(model_path)
if os.path.isfile(optim_path):
try:
self.optimizer = OptimMethod.load(optim_path)
except Exception:
raise ValueError(
"Cannot load the optimizer. Only `bigdl.optim.optimizer."
"OptimMethod` is supported for loading.")
else:
self.optimizer = None
self.estimator = SparkEstimator(self.model, self.optimizer,
self.model_dir)
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 model.4 file, the version is 4.
:param prefix: optimMethod prefix, for example 'optimMethod-TorchModelf53bddcc'
:return:
"""
import os
from bigdl.nn.layer import Model
from bigdl.optim.optimizer import OptimMethod
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)))
optimizer = OptimMethod.load(
os.path.join(path, "{}.{}".format(prefix, version)))
except Exception:
raise ValueError(
"Cannot load PyTorch checkpoint, please check your checkpoint path "
"and checkpoint type.")
self.estimator = SparkEstimator(self.model, optimizer, self.model_dir)
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 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 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-TorchModelf53bddcc'.
:return:
"""
import os
from bigdl.nn.layer import Model
from bigdl.optim.optimizer import OptimMethod
from zoo.orca.learn.utils import find_latest_checkpoint
from zoo.pipeline.api.torch import TorchModel
if version is None:
path, prefix, version = find_latest_checkpoint(path, model_type="pytorch")
if path is None:
raise ValueError("Cannot find PyTorch checkpoint, please check your checkpoint"
" path.")
else:
assert prefix is not None, "You should provide optimMethod prefix, " \
"for example 'optimMethod-TorchModelf53bddcc'"
try:
loaded_model = Model.load(os.path.join(path, "model.{}".format(version)))
self.model = TorchModel.from_value(loaded_model.value)
self.optimizer = OptimMethod.load(os.path.join(path, "{}.{}".format(prefix, version)))
except Exception:
raise ValueError("Cannot load PyTorch checkpoint, please check your checkpoint path "
"and checkpoint type.")
self.estimator = SparkEstimator(self.model, self.optimizer, self.model_dir)
def load_orca_checkpoint(self, path, version, prefix=None):
import os
from bigdl.nn.layer import Model
from bigdl.optim.optimizer import OptimMethod
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)))
optimizer = OptimMethod.load(os.path.join(path, "{}.{}".format(prefix, version)))
except Exception:
raise ValueError("Cannot load PyTorch checkpoint, please check your checkpoint path "
"and checkpoint type.")
self.estimator = SparkEstimator(self.model, optimizer, self.model_dir)
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, loss=None):
from zoo.orca.learn.utils import find_latest_checkpoint
from bigdl.nn.layer import Model
from bigdl.optim.optimizer import OptimMethod
import os
if loss is not None:
from zoo.pipeline.api.torch import TorchLoss
self.loss = TorchLoss.from_pytorch(loss)
path, prefix, version = find_latest_checkpoint(checkpoint,
model_type="pytorch")
if path is None:
raise ValueError(
"Cannot find PyTorch checkpoint, please check your checkpoint path."
)
try:
self.model = Model.load(
os.path.join(path, "model.{}".format(version)))
optimizer = OptimMethod.load(
os.path.join(path, "{}.{}".format(prefix, version)))
except Exception:
raise ValueError(
"Cannot load PyTorch checkpoint, please check your checkpoint path "
"and checkpoint type.")
self.estimator = SparkEstimator(self.model, optimizer, self.model_dir)
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