def load_weights(self, filepath, format=None, in_order=True, skip=False):
"""Load model weights from a given file, which should be previously saved by self.save_weights().
Parameters
----------
filepath : str
Filename from which the model weights will be loaded.
format : str or None
If not specified (None), the postfix of the filepath will be used to decide its format. If specified,
value should be 'hdf5', 'npz', 'npz_dict' or 'ckpt'. Other format is not supported now.
In addition, it should be the same format when you saved the file using self.save_weights().
Default is None.
in_order : bool
Allow loading weights into model in a sequential way or by name. Only useful when 'format' is 'hdf5'.
If 'in_order' is True, weights from the file will be loaded into model in a sequential way.
If 'in_order' is False, weights from the file will be loaded into model by matching the name
with the weights of the model, particularly useful when trying to restore model in eager(graph) mode from
a weights file which is saved in graph(eager) mode.
Default is True.
skip : bool
Allow skipping weights whose name is mismatched between the file and model. Only useful when 'format' is
'hdf5' or 'npz_dict'. If 'skip' is True, 'in_order' argument will be ignored and those loaded weights
whose name is not found in model weights (self.weights) will be skipped. If 'skip' is False, error will
occur when mismatch is found.
Default is False.
Examples
--------
1) load model from a hdf5 file.
>>> net = tl.models.vgg16()
>>> net.load_weights('./model_graph.h5', in_order=False, skip=True) # load weights by name, skipping mismatch
>>> net.load_weights('./model_eager.h5') # load sequentially
2) load model from a npz file
>>> net.load_weights('./model.npz')
2) load model from a npz file, which is saved as npz_dict previously
>>> net.load_weights('./model.npz', format='npz_dict')
Notes
-------
1) 'in_order' is only useful when 'format' is 'hdf5'. If you are trying to load a weights file which is
saved in a different mode, it is recommended to set 'in_order' be True.
2) 'skip' is useful when 'format' is 'hdf5' or 'npz_dict'. If 'skip' is True,
'in_order' argument will be ignored.
Returns
-------
"""
if not os.path.exists(filepath):
raise FileNotFoundError("file {} doesn't exist.".format(filepath))
if format is None:
format = filepath.split('.')[-1]
if format == 'hdf5' or format == 'h5':
if skip == True or in_order == False:
# load by weights name
utils.load_hdf5_to_weights(filepath, self, skip)
else:
# load in order
utils.load_hdf5_to_weights_in_order(filepath, self)
elif format == 'npz':
utils.load_and_assign_npz(filepath, self)
elif format == 'npz_dict':
utils.load_and_assign_npz_dict(filepath, self, skip)
elif format == 'ckpt':
# TODO: enable this when tf save ckpt is enabled
raise NotImplementedError("ckpt load/save is not supported now.")
else:
raise ValueError(
"File format must be 'hdf5', 'npz', 'npz_dict' or 'ckpt'. "
"Other format is not supported now.")
def load_weights(self, filepath, format=None, in_order=True, skip=False):
"""Load model weights from a given file, which should be previously saved by self.save_weights().
Parameters
----------
filepath : str
Filename from which the model weights will be loaded.
format : str or None
If not specified (None), the postfix of the filepath will be used to decide its format. If specified,
value should be 'hdf5', 'npz', 'npz_dict' or 'ckpt'. Other format is not supported now.
In addition, it should be the same format when you saved the file using self.save_weights().
Default is None.
in_order : bool
Allow loading weights into model in a sequential way or by name. Only useful when 'format' is 'hdf5'.
If 'in_order' is True, weights from the file will be loaded into model in a sequential way.
If 'in_order' is False, weights from the file will be loaded into model by matching the name
with the weights of the model, particularly useful when trying to restore model in eager(graph) mode from
a weights file which is saved in graph(eager) mode.
Default is True.
skip : bool
Allow skipping weights whose name is mismatched between the file and model. Only useful when 'format' is
'hdf5' or 'npz_dict'. If 'skip' is True, 'in_order' argument will be ignored and those loaded weights
whose name is not found in model weights (self.weights) will be skipped. If 'skip' is False, error will
occur when mismatch is found.
Default is False.
Examples
--------
1) load model from a hdf5 file.
>>> net = tl.models.vgg16()
>>> net.load_weights('./model_graph.h5', in_order=False, skip=True) # load weights by name, skipping mismatch
>>> net.load_weights('./model_eager.h5') # load sequentially
2) load model from a npz file
>>> net.load_weights('./model.npz')
2) load model from a npz file, which is saved as npz_dict previously
>>> net.load_weights('./model.npz', format='npz_dict')
Notes
-------
1) 'in_order' is only useful when 'format' is 'hdf5'. If you are trying to load a weights file which is
saved in a different mode, it is recommended to set 'in_order' be True.
2) 'skip' is useful when 'format' is 'hdf5' or 'npz_dict'. If 'skip' is True,
'in_order' argument will be ignored.
Returns
-------
"""
if not os.path.exists(filepath):
raise FileNotFoundError("file {} doesn't exist.".format(filepath))
if format is None:
format = filepath.split('.')[-1]
if format == 'hdf5' or format == 'h5':
if skip ==True or in_order == False:
# load by weights name
utils.load_hdf5_to_weights(filepath, self, skip)
else:
# load in order
utils.load_hdf5_to_weights_in_order(filepath, self)
elif format == 'npz':
utils.load_and_assign_npz(filepath, self)
elif format == 'npz_dict':
utils.load_and_assign_npz_dict(filepath, self, skip)
elif format == 'ckpt':
# TODO: enable this when tf save ckpt is enabled
raise NotImplementedError("ckpt load/save is not supported now.")
else:
raise ValueError(
"File format must be 'hdf5', 'npz', 'npz_dict' or 'ckpt'. "
"Other format is not supported now."
)