def convert_all_kernels_in_model(model):
"""Converts all convolution kernels in a model from Theano to TensorFlow.
Also works from TensorFlow to Theano.
Arguments:
model: target model for the conversion.
"""
# Note: SeparableConvolution not included
# since only supported by TF.
conv_classes = {
'Conv1D',
'Conv2D',
'Conv3D',
'Conv2DTranspose',
}
to_assign = []
for layer in model.layers:
if layer.__class__.__name__ in conv_classes:
original_kernel = K.get_value(layer.kernel)
converted_kernel = convert_kernel(original_kernel)
to_assign.append((layer.kernel, converted_kernel))
K.batch_set_value(to_assign)
def convert_all_kernels_in_model(model):
"""Converts all convolution kernels in a model from Theano to TensorFlow.
Also works from TensorFlow to Theano.
Arguments:
model: target model for the conversion.
"""
# Note: SeparableConvolution not included
# since only supported by TF.
conv_classes = {
'Conv1D',
'Conv2D',
'Conv3D',
'Conv2DTranspose',
}
to_assign = []
for layer in model.layers:
if layer.__class__.__name__ in conv_classes:
original_kernel = K.get_value(layer.kernel)
converted_kernel = convert_kernel(original_kernel)
to_assign.append((layer.kernel, converted_kernel))
K.batch_set_value(to_assign)
def preprocess_weights_for_loading(layer,
weights,
original_keras_version=None,
original_backend=None):
"""Converts layers weights from Keras 1 format to Keras 2.
Arguments:
layer: Layer instance.
weights: List of weights values (Numpy arrays).
original_keras_version: Keras version for the weights, as a string.
original_backend: Keras backend the weights were trained with,
as a string.
Returns:
A list of weights values (Numpy arrays).
"""
if layer.__class__.__name__ == 'Bidirectional':
num_weights_per_layer = len(weights) // 2
forward_weights = preprocess_weights_for_loading(
layer.forward_layer, weights[:num_weights_per_layer],
original_keras_version, original_backend)
backward_weights = preprocess_weights_for_loading(
layer.backward_layer, weights[num_weights_per_layer:],
original_keras_version, original_backend)
weights = forward_weights + backward_weights
if original_keras_version == '1':
if layer.__class__.__name__ == 'TimeDistributed':
weights = preprocess_weights_for_loading(
layer.layer, weights, original_keras_version, original_backend)
if layer.__class__.__name__ == 'Conv1D':
shape = weights[0].shape
# Handle Keras 1.1 format
if shape[:2] != (layer.kernel_size[0], 1) or shape[3] != layer.filters:
# Legacy shape:
# (filters, input_dim, filter_length, 1)
assert shape[0] == layer.filters and shape[2:] == (layer.kernel_size[0],
1)
weights[0] = np.transpose(weights[0], (2, 3, 1, 0))
weights[0] = weights[0][:, 0, :, :]
if layer.__class__.__name__ == 'Conv2D':
if layer.data_format == 'channels_first':
# old: (filters, stack_size, kernel_rows, kernel_cols)
# new: (kernel_rows, kernel_cols, stack_size, filters)
weights[0] = np.transpose(weights[0], (2, 3, 1, 0))
if layer.__class__.__name__ == 'Conv2DTranspose':
if layer.data_format == 'channels_last':
# old: (kernel_rows, kernel_cols, stack_size, filters)
# new: (kernel_rows, kernel_cols, filters, stack_size)
weights[0] = np.transpose(weights[0], (0, 1, 3, 2))
if layer.data_format == 'channels_first':
# old: (filters, stack_size, kernel_rows, kernel_cols)
# new: (kernel_rows, kernel_cols, filters, stack_size)
weights[0] = np.transpose(weights[0], (2, 3, 0, 1))
if layer.__class__.__name__ == 'Conv3D':
if layer.data_format == 'channels_first':
# old: (filters, stack_size, ...)
# new: (..., stack_size, filters)
weights[0] = np.transpose(weights[0], (2, 3, 4, 1, 0))
if layer.__class__.__name__ == 'GRU':
if len(weights) == 9:
kernel = np.concatenate([weights[0], weights[3], weights[6]], axis=-1)
recurrent_kernel = np.concatenate(
[weights[1], weights[4], weights[7]], axis=-1)
bias = np.concatenate([weights[2], weights[5], weights[8]], axis=-1)
weights = [kernel, recurrent_kernel, bias]
if layer.__class__.__name__ == 'LSTM':
if len(weights) == 12:
# old: i, c, f, o
# new: i, f, c, o
kernel = np.concatenate(
[weights[0], weights[6], weights[3], weights[9]], axis=-1)
recurrent_kernel = np.concatenate(
[weights[1], weights[7], weights[4], weights[10]], axis=-1)
bias = np.concatenate(
[weights[2], weights[8], weights[5], weights[11]], axis=-1)
weights = [kernel, recurrent_kernel, bias]
if layer.__class__.__name__ == 'ConvLSTM2D':
if len(weights) == 12:
kernel = np.concatenate(
[weights[0], weights[6], weights[3], weights[9]], axis=-1)
recurrent_kernel = np.concatenate(
[weights[1], weights[7], weights[4], weights[10]], axis=-1)
bias = np.concatenate(
[weights[2], weights[8], weights[5], weights[11]], axis=-1)
if layer.data_format == 'channels_first':
# old: (filters, stack_size, kernel_rows, kernel_cols)
# new: (kernel_rows, kernel_cols, stack_size, filters)
kernel = np.transpose(kernel, (2, 3, 1, 0))
recurrent_kernel = np.transpose(recurrent_kernel, (2, 3, 1, 0))
weights = [kernel, recurrent_kernel, bias]
if layer.__class__.__name__ in ['Model', 'Sequential']:
new_weights = []
# trainable weights
for sublayer in layer.layers:
num_weights = len(sublayer.trainable_weights)
if num_weights > 0:
new_weights.extend(
preprocess_weights_for_loading(
layer=sublayer,
weights=weights[:num_weights],
original_keras_version=original_keras_version,
original_backend=original_backend))
weights = weights[num_weights:]
# non-trainable weights
for sublayer in layer.layers:
num_weights = len([
l for l in sublayer.weights if l not in sublayer.trainable_weights
])
if num_weights > 0:
new_weights.extend(
preprocess_weights_for_loading(
layer=sublayer,
weights=weights[:num_weights],
original_keras_version=original_keras_version,
original_backend=original_backend))
weights = weights[num_weights:]
weights = new_weights
conv_layers = ['Conv1D', 'Conv2D', 'Conv3D', 'Conv2DTranspose', 'ConvLSTM2D']
if layer.__class__.__name__ in conv_layers:
if original_backend == 'theano':
weights[0] = conv_utils.convert_kernel(weights[0])
if layer.__class__.__name__ == 'ConvLSTM2D':
weights[1] = conv_utils.convert_kernel(weights[1])
if K.int_shape(layer.weights[0]) != weights[0].shape:
weights[0] = np.transpose(weights[0], (3, 2, 0, 1))
if layer.__class__.__name__ == 'ConvLSTM2D':
weights[1] = np.transpose(weights[1], (3, 2, 0, 1))
return _convert_rnn_weights(layer, weights)
def preprocess_weights_for_loading(layer,
weights,
original_keras_version=None,
original_backend=None):
"""Converts layers weights from Keras 1 format to Keras 2.
Arguments:
layer: Layer instance.
weights: List of weights values (Numpy arrays).
original_keras_version: Keras version for the weights, as a string.
original_backend: Keras backend the weights were trained with,
as a string.
Returns:
A list of weights values (Numpy arrays).
"""
if layer.__class__.__name__ == 'Bidirectional':
num_weights_per_layer = len(weights) // 2
forward_weights = preprocess_weights_for_loading(
layer.forward_layer, weights[:num_weights_per_layer],
original_keras_version, original_backend)
backward_weights = preprocess_weights_for_loading(
layer.backward_layer, weights[num_weights_per_layer:],
original_keras_version, original_backend)
weights = forward_weights + backward_weights
if original_keras_version == '1':
if layer.__class__.__name__ == 'TimeDistributed':
weights = preprocess_weights_for_loading(layer.layer, weights,
original_keras_version,
original_backend)
if layer.__class__.__name__ == 'Conv1D':
shape = weights[0].shape
# Handle Keras 1.1 format
if shape[:2] != (layer.kernel_size[0],
1) or shape[3] != layer.filters:
# Legacy shape:
# (filters, input_dim, filter_length, 1)
assert shape[0] == layer.filters and shape[2:] == (
layer.kernel_size[0], 1)
weights[0] = np.transpose(weights[0], (2, 3, 1, 0))
weights[0] = weights[0][:, 0, :, :]
if layer.__class__.__name__ == 'Conv2D':
if layer.data_format == 'channels_first':
# old: (filters, stack_size, kernel_rows, kernel_cols)
# new: (kernel_rows, kernel_cols, stack_size, filters)
weights[0] = np.transpose(weights[0], (2, 3, 1, 0))
if layer.__class__.__name__ == 'Conv2DTranspose':
if layer.data_format == 'channels_last':
# old: (kernel_rows, kernel_cols, stack_size, filters)
# new: (kernel_rows, kernel_cols, filters, stack_size)
weights[0] = np.transpose(weights[0], (0, 1, 3, 2))
if layer.data_format == 'channels_first':
# old: (filters, stack_size, kernel_rows, kernel_cols)
# new: (kernel_rows, kernel_cols, filters, stack_size)
weights[0] = np.transpose(weights[0], (2, 3, 0, 1))
if layer.__class__.__name__ == 'Conv3D':
if layer.data_format == 'channels_first':
# old: (filters, stack_size, ...)
# new: (..., stack_size, filters)
weights[0] = np.transpose(weights[0], (2, 3, 4, 1, 0))
if layer.__class__.__name__ == 'GRU':
if len(weights) == 9:
kernel = np.concatenate([weights[0], weights[3], weights[6]],
axis=-1)
recurrent_kernel = np.concatenate(
[weights[1], weights[4], weights[7]], axis=-1)
bias = np.concatenate([weights[2], weights[5], weights[8]],
axis=-1)
weights = [kernel, recurrent_kernel, bias]
if layer.__class__.__name__ == 'LSTM':
if len(weights) == 12:
# old: i, c, f, o
# new: i, f, c, o
kernel = np.concatenate(
[weights[0], weights[6], weights[3], weights[9]], axis=-1)
recurrent_kernel = np.concatenate(
[weights[1], weights[7], weights[4], weights[10]], axis=-1)
bias = np.concatenate(
[weights[2], weights[8], weights[5], weights[11]], axis=-1)
weights = [kernel, recurrent_kernel, bias]
if layer.__class__.__name__ == 'ConvLSTM2D':
if len(weights) == 12:
kernel = np.concatenate(
[weights[0], weights[6], weights[3], weights[9]], axis=-1)
recurrent_kernel = np.concatenate(
[weights[1], weights[7], weights[4], weights[10]], axis=-1)
bias = np.concatenate(
[weights[2], weights[8], weights[5], weights[11]], axis=-1)
if layer.data_format == 'channels_first':
# old: (filters, stack_size, kernel_rows, kernel_cols)
# new: (kernel_rows, kernel_cols, stack_size, filters)
kernel = np.transpose(kernel, (2, 3, 1, 0))
recurrent_kernel = np.transpose(recurrent_kernel,
(2, 3, 1, 0))
weights = [kernel, recurrent_kernel, bias]
if layer.__class__.__name__ in ['Model', 'Sequential']:
new_weights = []
# trainable weights
for sublayer in layer.layers:
num_weights = len(sublayer.trainable_weights)
if num_weights > 0:
new_weights.extend(
preprocess_weights_for_loading(
layer=sublayer,
weights=weights[:num_weights],
original_keras_version=original_keras_version,
original_backend=original_backend))
weights = weights[num_weights:]
# non-trainable weights
for sublayer in layer.layers:
num_weights = len([
l for l in sublayer.weights
if l not in sublayer.trainable_weights
])
if num_weights > 0:
new_weights.extend(
preprocess_weights_for_loading(
layer=sublayer,
weights=weights[:num_weights],
original_keras_version=original_keras_version,
original_backend=original_backend))
weights = weights[num_weights:]
weights = new_weights
conv_layers = [
'Conv1D', 'Conv2D', 'Conv3D', 'Conv2DTranspose', 'ConvLSTM2D'
]
if layer.__class__.__name__ in conv_layers:
if original_backend == 'theano':
weights[0] = conv_utils.convert_kernel(weights[0])
if layer.__class__.__name__ == 'ConvLSTM2D':
weights[1] = conv_utils.convert_kernel(weights[1])
if K.int_shape(layer.weights[0]) != weights[0].shape:
weights[0] = np.transpose(weights[0], (3, 2, 0, 1))
if layer.__class__.__name__ == 'ConvLSTM2D':
weights[1] = np.transpose(weights[1], (3, 2, 0, 1))
# Convert the weights of CuDNNLSTM so that they could be loaded into LSTM
if layer.__class__.__name__ == 'LSTM' and len(weights) == 3:
# Determine if loading a CuDNNLSTM layer from the number of bias weights:
# CuDNNLSTM has (units * 8) weights; while LSTM has (units * 4)
# if there's no bias weight in the file, skip this conversion
units = weights[1].shape[0]
bias = weights[2]
if len(bias) == units * 8:
# reshape the kernels
kernels = np.split(weights[0], 4, axis=1)
kernels = [
kernel.reshape(-1).reshape(kernel.shape, order='F')
for kernel in kernels
]
weights[0] = np.concatenate(kernels, axis=1)
# transpose the recurrent kernels
recurrent_kernels = np.split(weights[1], 4, axis=1)
recurrent_kernels = [kernel.T for kernel in recurrent_kernels]
weights[1] = np.concatenate(recurrent_kernels, axis=1)
# split the bias into half and merge
weights[2] = bias[:units * 4] + bias[units * 4:]
return convert_rnn_weights(layer, weights)
def preprocess_weights_for_loading(layer,
weights,
original_keras_version=None,
original_backend=None):
"""Converts layers weights from Keras 1 format to Keras 2.
Arguments:
layer: Layer instance.
weights: List of weights values (Numpy arrays).
original_keras_version: Keras version for the weights, as a string.
original_backend: Keras backend the weights were trained with,
as a string.
Returns:
A list of weights values (Numpy arrays).
"""
if layer.__class__.__name__ == 'Bidirectional':
num_weights_per_layer = len(weights) // 2
forward_weights = preprocess_weights_for_loading(
layer.forward_layer, weights[:num_weights_per_layer],
original_keras_version, original_backend)
backward_weights = preprocess_weights_for_loading(
layer.backward_layer, weights[num_weights_per_layer:],
original_keras_version, original_backend)
weights = forward_weights + backward_weights
if original_keras_version == '1':
if layer.__class__.__name__ == 'TimeDistributed':
weights = preprocess_weights_for_loading(
layer.layer, weights, original_keras_version, original_backend)
if layer.__class__.__name__ == 'Conv1D':
shape = weights[0].shape
# Handle Keras 1.1 format
if shape[:2] != (layer.kernel_size[0], 1) or shape[3] != layer.filters:
# Legacy shape:
# (filters, input_dim, filter_length, 1)
assert shape[0] == layer.filters and shape[2:] == (layer.kernel_size[0],
1)
weights[0] = np.transpose(weights[0], (2, 3, 1, 0))
weights[0] = weights[0][:, 0, :, :]
if layer.__class__.__name__ == 'Conv2D':
if layer.data_format == 'channels_first':
# old: (filters, stack_size, kernel_rows, kernel_cols)
# new: (kernel_rows, kernel_cols, stack_size, filters)
weights[0] = np.transpose(weights[0], (2, 3, 1, 0))
if layer.__class__.__name__ == 'Conv2DTranspose':
if layer.data_format == 'channels_last':
# old: (kernel_rows, kernel_cols, stack_size, filters)
# new: (kernel_rows, kernel_cols, filters, stack_size)
weights[0] = np.transpose(weights[0], (0, 1, 3, 2))
if layer.data_format == 'channels_first':
# old: (filters, stack_size, kernel_rows, kernel_cols)
# new: (kernel_rows, kernel_cols, filters, stack_size)
weights[0] = np.transpose(weights[0], (2, 3, 0, 1))
if layer.__class__.__name__ == 'Conv3D':
if layer.data_format == 'channels_first':
# old: (filters, stack_size, ...)
# new: (..., stack_size, filters)
weights[0] = np.transpose(weights[0], (2, 3, 4, 1, 0))
if layer.__class__.__name__ == 'GRU':
if len(weights) == 9:
kernel = np.concatenate([weights[0], weights[3], weights[6]], axis=-1)
recurrent_kernel = np.concatenate(
[weights[1], weights[4], weights[7]], axis=-1)
bias = np.concatenate([weights[2], weights[5], weights[8]], axis=-1)
weights = [kernel, recurrent_kernel, bias]
if layer.__class__.__name__ == 'LSTM':
if len(weights) == 12:
# old: i, c, f, o
# new: i, f, c, o
kernel = np.concatenate(
[weights[0], weights[6], weights[3], weights[9]], axis=-1)
recurrent_kernel = np.concatenate(
[weights[1], weights[7], weights[4], weights[10]], axis=-1)
bias = np.concatenate(
[weights[2], weights[8], weights[5], weights[11]], axis=-1)
weights = [kernel, recurrent_kernel, bias]
if layer.__class__.__name__ == 'ConvLSTM2D':
if len(weights) == 12:
kernel = np.concatenate(
[weights[0], weights[6], weights[3], weights[9]], axis=-1)
recurrent_kernel = np.concatenate(
[weights[1], weights[7], weights[4], weights[10]], axis=-1)
bias = np.concatenate(
[weights[2], weights[8], weights[5], weights[11]], axis=-1)
if layer.data_format == 'channels_first':
# old: (filters, stack_size, kernel_rows, kernel_cols)
# new: (kernel_rows, kernel_cols, stack_size, filters)
kernel = np.transpose(kernel, (2, 3, 1, 0))
recurrent_kernel = np.transpose(recurrent_kernel, (2, 3, 1, 0))
weights = [kernel, recurrent_kernel, bias]
if layer.__class__.__name__ in ['Model', 'Sequential']:
new_weights = []
# trainable weights
for sublayer in layer.layers:
num_weights = len(sublayer.trainable_weights)
if num_weights > 0:
new_weights.extend(
preprocess_weights_for_loading(
layer=sublayer,
weights=weights[:num_weights],
original_keras_version=original_keras_version,
original_backend=original_backend))
weights = weights[num_weights:]
# non-trainable weights
for sublayer in layer.layers:
num_weights = len([
l for l in sublayer.weights if l not in sublayer.trainable_weights
])
if num_weights > 0:
new_weights.extend(
preprocess_weights_for_loading(
layer=sublayer,
weights=weights[:num_weights],
original_keras_version=original_keras_version,
original_backend=original_backend))
weights = weights[num_weights:]
weights = new_weights
conv_layers = ['Conv1D', 'Conv2D', 'Conv3D', 'Conv2DTranspose', 'ConvLSTM2D']
if layer.__class__.__name__ in conv_layers:
if original_backend == 'theano':
weights[0] = conv_utils.convert_kernel(weights[0])
if layer.__class__.__name__ == 'ConvLSTM2D':
weights[1] = conv_utils.convert_kernel(weights[1])
if K.int_shape(layer.weights[0]) != weights[0].shape:
weights[0] = np.transpose(weights[0], (3, 2, 0, 1))
if layer.__class__.__name__ == 'ConvLSTM2D':
weights[1] = np.transpose(weights[1], (3, 2, 0, 1))
# Convert the weights of CuDNNLSTM so that they could be loaded into LSTM
if layer.__class__.__name__ == 'LSTM' and len(weights) == 3:
# Determine if loading a CuDNNLSTM layer from the number of bias weights:
# CuDNNLSTM has (units * 8) weights; while LSTM has (units * 4)
# if there's no bias weight in the file, skip this conversion
units = weights[1].shape[0]
bias = weights[2]
if len(bias) == units * 8:
# reshape the kernels
kernels = np.split(weights[0], 4, axis=1)
kernels = [
kernel.reshape(-1).reshape(kernel.shape, order='F')
for kernel in kernels
]
weights[0] = np.concatenate(kernels, axis=1)
# transpose the recurrent kernels
recurrent_kernels = np.split(weights[1], 4, axis=1)
recurrent_kernels = [kernel.T for kernel in recurrent_kernels]
weights[1] = np.concatenate(recurrent_kernels, axis=1)
# split the bias into half and merge
weights[2] = bias[:units * 4] + bias[units * 4:]
return weights
def preprocess_weights_for_loading(layer,
weights,
original_keras_version=None,
original_backend=None):
"""Converts layers weights from Keras 1 format to Keras 2.
Arguments:
layer: Layer instance.
weights: List of weights values (Numpy arrays).
original_keras_version: Keras version for the weights, as a string.
original_backend: Keras backend the weights were trained with,
as a string.
Returns:
A list of weights values (Numpy arrays).
"""
if layer.__class__.__name__ == 'Bidirectional':
num_weights_per_layer = len(weights) // 2
forward_weights = preprocess_weights_for_loading(
layer.forward_layer, weights[:num_weights_per_layer],
original_keras_version, original_backend)
backward_weights = preprocess_weights_for_loading(
layer.backward_layer, weights[num_weights_per_layer:],
original_keras_version, original_backend)
weights = forward_weights + backward_weights
if original_keras_version == '1':
if layer.__class__.__name__ == 'TimeDistributed':
weights = preprocess_weights_for_loading(
layer.layer, weights, original_keras_version, original_backend)
if layer.__class__.__name__ == 'Conv1D':
shape = weights[0].shape
# Handle Keras 1.1 format
if shape[:2] != (layer.kernel_size[0], 1) or shape[3] != layer.filters:
# Legacy shape:
# (filters, input_dim, filter_length, 1)
assert shape[0] == layer.filters and shape[2:] == (layer.kernel_size[0],
1)
weights[0] = np.transpose(weights[0], (2, 3, 1, 0))
weights[0] = weights[0][:, 0, :, :]
if layer.__class__.__name__ == 'Conv2D':
if layer.data_format == 'channels_first':
# old: (filters, stack_size, kernel_rows, kernel_cols)
# new: (kernel_rows, kernel_cols, stack_size, filters)
weights[0] = np.transpose(weights[0], (2, 3, 1, 0))
if layer.__class__.__name__ == 'Conv2DTranspose':
if layer.data_format == 'channels_last':
# old: (kernel_rows, kernel_cols, stack_size, filters)
# new: (kernel_rows, kernel_cols, filters, stack_size)
weights[0] = np.transpose(weights[0], (0, 1, 3, 2))
if layer.data_format == 'channels_first':
# old: (filters, stack_size, kernel_rows, kernel_cols)
# new: (kernel_rows, kernel_cols, filters, stack_size)
weights[0] = np.transpose(weights[0], (2, 3, 0, 1))
if layer.__class__.__name__ == 'Conv3D':
if layer.data_format == 'channels_first':
# old: (filters, stack_size, ...)
# new: (..., stack_size, filters)
weights[0] = np.transpose(weights[0], (2, 3, 4, 1, 0))
if layer.__class__.__name__ == 'GRU':
if len(weights) == 9:
kernel = np.concatenate([weights[0], weights[3], weights[6]], axis=-1)
recurrent_kernel = np.concatenate(
[weights[1], weights[4], weights[7]], axis=-1)
bias = np.concatenate([weights[2], weights[5], weights[8]], axis=-1)
weights = [kernel, recurrent_kernel, bias]
if layer.__class__.__name__ == 'LSTM':
if len(weights) == 12:
# old: i, c, f, o
# new: i, f, c, o
kernel = np.concatenate(
[weights[0], weights[6], weights[3], weights[9]], axis=-1)
recurrent_kernel = np.concatenate(
[weights[1], weights[7], weights[4], weights[10]], axis=-1)
bias = np.concatenate(
[weights[2], weights[8], weights[5], weights[11]], axis=-1)
weights = [kernel, recurrent_kernel, bias]
if layer.__class__.__name__ == 'ConvLSTM2D':
if len(weights) == 12:
kernel = np.concatenate(
[weights[0], weights[6], weights[3], weights[9]], axis=-1)
recurrent_kernel = np.concatenate(
[weights[1], weights[7], weights[4], weights[10]], axis=-1)
bias = np.concatenate(
[weights[2], weights[8], weights[5], weights[11]], axis=-1)
if layer.data_format == 'channels_first':
# old: (filters, stack_size, kernel_rows, kernel_cols)
# new: (kernel_rows, kernel_cols, stack_size, filters)
kernel = np.transpose(kernel, (2, 3, 1, 0))
recurrent_kernel = np.transpose(recurrent_kernel, (2, 3, 1, 0))
weights = [kernel, recurrent_kernel, bias]
if layer.__class__.__name__ in ['Model', 'Sequential']:
new_weights = []
# trainable weights
for sublayer in layer.layers:
num_weights = len(sublayer.trainable_weights)
if num_weights > 0:
new_weights.extend(
preprocess_weights_for_loading(
layer=sublayer,
weights=weights[:num_weights],
original_keras_version=original_keras_version,
original_backend=original_backend))
weights = weights[num_weights:]
# non-trainable weights
for sublayer in layer.layers:
num_weights = len([
l for l in sublayer.weights if l not in sublayer.trainable_weights
])
if num_weights > 0:
new_weights.extend(
preprocess_weights_for_loading(
layer=sublayer,
weights=weights[:num_weights],
original_keras_version=original_keras_version,
original_backend=original_backend))
weights = weights[num_weights:]
weights = new_weights
conv_layers = ['Conv1D', 'Conv2D', 'Conv3D', 'Conv2DTranspose', 'ConvLSTM2D']
if layer.__class__.__name__ in conv_layers:
if original_backend == 'theano':
weights[0] = conv_utils.convert_kernel(weights[0])
if layer.__class__.__name__ == 'ConvLSTM2D':
weights[1] = conv_utils.convert_kernel(weights[1])
if K.int_shape(layer.weights[0]) != weights[0].shape:
weights[0] = np.transpose(weights[0], (3, 2, 0, 1))
if layer.__class__.__name__ == 'ConvLSTM2D':
weights[1] = np.transpose(weights[1], (3, 2, 0, 1))
return _convert_rnn_weights(layer, weights)
