def load_weights(self, filepath, by_name=False, exclude=None):
"""
exclude: list of layer names to exclude
"""
import h5py
from tensorflow.python.keras.saving import hdf5_format
if exclude:
by_name = True
if h5py is None:
raise ImportError('`load_weights` requires h5py.')
with h5py.File(filepath, mode='r') as f:
if 'layer_names' not in f.attrs and 'model_weights' in f:
f = f['model_weights']
keras_model = self.keras_model
layers = keras_model.inner_model.layers if hasattr(keras_model, "inner_model")\
else keras_model.layers
# Exclude some layers
if exclude:
layers = filter(lambda l: l.name not in exclude, layers)
if by_name:
hdf5_format.load_weights_from_hdf5_group_by_name(f, layers)
else:
hdf5_format.load_weights_from_hdf5_group(f, layers)
# Update the log directory
self.set_log_dir(filepath)
def load_weights(model: Model, filepath, by_name=False, skip_mismatch=False):
layers = []
for layer in model.layers:
if isinstance(layer, Component):
layers.extend(layer.layers)
else:
layers.append(layer)
with h5py.File(filepath, 'r') as f:
if 'layer_names' not in f.attrs and 'model_weights' in f:
f = f['model_weights']
hdf5_format.load_weights_from_hdf5_group(f, layers)
hdf5_format.load_weights_from_hdf5_group_by_name(f, layers, skip_mismatch=skip_mismatch)
def test_sequential_weight_loading_group_name_with_incorrect_shape(self):
if h5py is None:
return
temp_dir = self.get_temp_dir()
self.addCleanup(shutil.rmtree, temp_dir)
h5_path = os.path.join(temp_dir, 'test.h5')
num_hidden = 5
input_dim = 3
num_classes = 2
with ops.Graph().as_default(), self.cached_session():
ref_model = keras.models.Sequential()
ref_model.add(
keras.layers.Dense(num_hidden, input_dim=input_dim, name='d1'))
ref_model.add(keras.layers.Dense(num_classes, name='d2'))
ref_model.compile(loss=keras.losses.MSE,
optimizer=optimizer_v1.RMSprop(lr=0.0001),
metrics=[keras.metrics.categorical_accuracy])
f_ref_model = h5py.File(h5_path, 'w')
keras.backend.set_value(ref_model.layers[1].bias,
[3.5] * num_classes)
hdf5_format.save_weights_to_hdf5_group(f_ref_model,
ref_model.layers)
f_model = h5py.File(h5_path, 'r')
model = keras.models.Sequential()
model.add(
keras.layers.Dense(num_hidden + 5,
input_dim=input_dim,
name='d1'))
model.add(keras.layers.Dense(num_classes, name='d2'))
model.compile(loss=keras.losses.MSE,
optimizer=optimizer_v1.RMSprop(lr=0.0001),
metrics=[keras.metrics.categorical_accuracy])
with self.assertRaisesRegex(
ValueError, r'Layer #0 \(named "d1"\), weight '
r'<tf\.Variable \'d1_1\/kernel:0\' '
r'shape=\(3, 10\) dtype=float32> has '
r'shape \(3, 10\), but the saved weight has '
r'shape \(3, 5\)\.'):
hdf5_format.load_weights_from_hdf5_group_by_name(
f_model, model.layers)
hdf5_format.load_weights_from_hdf5_group_by_name(
f_model, model.layers, skip_mismatch=True)
self.assertAllClose([3.5] * num_classes,
keras.backend.get_value(model.layers[1].bias))
def test_sequential_weight_loading_group_name_with_incorrect_length(self):
if h5py is None:
return
temp_dir = self.get_temp_dir()
self.addCleanup(shutil.rmtree, temp_dir)
h5_path = os.path.join(temp_dir, 'test.h5')
num_hidden = 5
input_dim = 3
num_classes = 2
with self.cached_session():
ref_model = keras.models.Sequential()
ref_model.add(
keras.layers.Dense(num_hidden, input_dim=input_dim, name='d1'))
ref_model.add(keras.layers.Dense(num_classes, name='d2'))
ref_model.compile(loss=keras.losses.MSE,
optimizer='rmsprop',
metrics=[keras.metrics.categorical_accuracy])
f_ref_model = h5py.File(h5_path, 'w')
hdf5_format.save_weights_to_hdf5_group(f_ref_model,
ref_model.layers)
f_model = h5py.File(h5_path, 'r')
model = keras.models.Sequential()
model.add(
keras.layers.Dense(num_hidden,
use_bias=False,
input_dim=input_dim,
name='d1'))
model.add(keras.layers.Dense(num_classes, name='d2'))
model.compile(loss=keras.losses.MSE,
optimizer='rmsprop',
metrics=[keras.metrics.categorical_accuracy])
with self.assertRaisesRegex(
ValueError, r'Layer #0 \(named \"d1\"\) expects 1 '
r'weight\(s\), but the saved weights have 2 '
r'element\(s\)\.'):
hdf5_format.load_weights_from_hdf5_group_by_name(
f_model, model.layers)
hdf5_format.load_weights_from_hdf5_group_by_name(
f_model, model.layers, skip_mismatch=True)
self.assertAllClose(
keras.backend.get_value(ref_model.layers[1].kernel),
keras.backend.get_value(model.layers[1].kernel))
def test_sequential_weight_loading_group_name_with_incorrect_shape(self):
if h5py is None:
return
temp_dir = self.get_temp_dir()
self.addCleanup(shutil.rmtree, temp_dir)
h5_path = os.path.join(temp_dir, 'test.h5')
num_hidden = 5
input_dim = 3
num_classes = 2
with self.cached_session():
ref_model = keras.models.Sequential()
ref_model.add(keras.layers.Dense(num_hidden, input_dim=input_dim,
name='d1'))
ref_model.add(keras.layers.Dense(num_classes, name='d2'))
ref_model.compile(loss=keras.losses.MSE,
optimizer=keras.optimizers.RMSprop(lr=0.0001),
metrics=[keras.metrics.categorical_accuracy])
f_ref_model = h5py.File(h5_path, 'w')
hdf5_format.save_weights_to_hdf5_group(f_ref_model, ref_model.layers)
f_model = h5py.File(h5_path, 'r')
model = keras.models.Sequential()
model.add(keras.layers.Dense(num_hidden + 5, input_dim=input_dim,
name='d1'))
model.add(keras.layers.Dense(num_classes, name='d2'))
model.compile(loss=keras.losses.MSE,
optimizer=keras.optimizers.RMSprop(lr=0.0001),
metrics=[keras.metrics.categorical_accuracy])
with self.assertRaisesRegexp(ValueError,
r'Layer #0 \(named "d1"\), weight '
r'<tf\.Variable \'d1_1\/kernel:0\' '
r'shape=\(3, 10\) dtype=float32> has '
r'shape \(3, 10\), but the saved weight has '
r'shape \(3, 5\)\.'):
hdf5_format.load_weights_from_hdf5_group_by_name(f_model, model.layers)
def test_sequential_weight_loading_group_name_with_incorrect_length(self):
if h5py is None:
return
temp_dir = self.get_temp_dir()
self.addCleanup(shutil.rmtree, temp_dir)
h5_path = os.path.join(temp_dir, 'test.h5')
num_hidden = 5
input_dim = 3
num_classes = 2
with self.cached_session():
ref_model = keras.models.Sequential()
ref_model.add(keras.layers.Dense(num_hidden, input_dim=input_dim,
name='d1'))
ref_model.add(keras.layers.Dense(num_classes, name='d2'))
ref_model.compile(loss=keras.losses.MSE,
optimizer=keras.optimizers.RMSprop(lr=0.0001),
metrics=[keras.metrics.categorical_accuracy])
f_ref_model = h5py.File(h5_path, 'w')
hdf5_format.save_weights_to_hdf5_group(f_ref_model, ref_model.layers)
f_model = h5py.File(h5_path, 'r')
model = keras.models.Sequential()
model.add(keras.layers.Dense(num_hidden, use_bias=False,
input_dim=input_dim, name='d1'))
model.add(keras.layers.Dense(num_classes, name='d2'))
model.compile(loss=keras.losses.MSE,
optimizer=keras.optimizers.RMSprop(lr=0.0001),
metrics=[keras.metrics.categorical_accuracy])
with self.assertRaisesRegexp(ValueError,
r'Layer #0 \(named \"d1\"\) expects 1 '
r'weight\(s\), but the saved weights have 2 '
r'element\(s\)\.'):
hdf5_format.load_weights_from_hdf5_group_by_name(f_model, model.layers)
