def _create_rdd_x_y(x, y, input_names, output_names, sc):
x = training_utils.standardize_input_data(x,
input_names,
check_batch_axis=False,
exception_prefix='input')
y = training_utils.standardize_input_data(y,
output_names,
shapes=None,
check_batch_axis=False,
exception_prefix='target')
num_samples = x[0].shape[0]
num_inputs = len(x)
num_targets = len(y)
input_data = []
for i in range(num_samples):
inputs = []
for j in range(num_inputs):
inputs.append(x[j][i])
targets = []
for j in range(num_targets):
if y[j][i].ndim == 0:
targets.append(np.expand_dims(y[j][i], axis=1))
else:
targets.append(y[j][i])
input_data.append(inputs + targets)
types = [x.dtype for x in input_data[0]]
shapes = [x.shape for x in input_data[0]]
rdd = sc.parallelize(input_data)
return rdd, types, shapes
def _create_rdd_x_y(x, y, input_names, output_names, sc):
from tensorflow.python.keras.engine import training_utils
x = training_utils.standardize_input_data(x,
input_names,
check_batch_axis=False,
exception_prefix='input')
y = training_utils.standardize_input_data(y,
output_names,
shapes=None,
check_batch_axis=False,
exception_prefix='target')
num_samples = x[0].shape[0]
num_inputs = len(x)
num_targets = len(y)
input_data = []
for i in range(num_samples):
inputs = []
for j in range(num_inputs):
inputs.append(x[j][i])
targets = []
for j in range(num_targets):
if y[j][i].ndim == 0:
targets.append(np.expand_dims(y[j][i], axis=1))
else:
targets.append(y[j][i])
input_data.append((inputs, targets))
x_meta = dict([(input_names[i], (input_data[0][0][i].dtype,
input_data[0][0][i].shape))
for i in range(len(input_names))])
y_meta = dict([(output_names[i], (input_data[0][1][i].dtype,
input_data[0][1][i].shape))
for i in range(len(input_names))])
rdd = sc.parallelize(input_data)
return rdd, x_meta, y_meta
def _create_rdd_x(x, input_names, sc):
x = training_utils.standardize_input_data(x, input_names,
check_batch_axis=False,
exception_prefix='input')
num_samples = x[0].shape[0]
num_inputs = len(x)
input_data = []
for i in range(num_samples):
sample = []
for j in range(num_inputs):
sample.append(x[j][i])
input_data.append(sample)
types = [x.dtype for x in input_data[0]]
shapes = [x.shape for x in input_data[0]]
rdd = sc.parallelize(input_data)
return rdd, types, shapes
def set_model(self, model):
"""Sets Keras model and creates summary ops."""
self.model = model
self._init_writer(model)
# histogram summaries only enabled in graph mode
if not context.executing_eagerly():
self._make_histogram_ops(model)
self.merged = tf_summary.merge_all()
# If both embedding_freq and embeddings_data are available, we will
# visualize embeddings.
if self.embeddings_freq and self.embeddings_data is not None:
# Avoid circular dependency.
from tensorflow.python.keras.engine import training_utils # pylint: disable=g-import-not-at-top
self.embeddings_data = training_utils.standardize_input_data(
self.embeddings_data, model.input_names)
# If embedding_layer_names are not provided, get all of the embedding
# layers from the model.
embeddings_layer_names = self.embeddings_layer_names
if not embeddings_layer_names:
embeddings_layer_names = [
layer.name
for layer in self.model.layers
if type(layer).__name__ == 'Embedding'
]
self.assign_embeddings = []
embeddings_vars = {}
self.batch_id = batch_id = array_ops.placeholder(dtypes.int32)
self.step = step = array_ops.placeholder(dtypes.int32)
for layer in self.model.layers:
if layer.name in embeddings_layer_names:
embedding_input = self.model.get_layer(layer.name).output
embedding_size = np.prod(embedding_input.shape[1:])
embedding_input = array_ops.reshape(embedding_input,
(step, int(embedding_size)))
shape = (self.embeddings_data[0].shape[0], int(embedding_size))
embedding = variables.Variable(
array_ops.zeros(shape), name=layer.name + '_embedding')
embeddings_vars[layer.name] = embedding
batch = state_ops.assign(embedding[batch_id:batch_id + step],
embedding_input)
self.assign_embeddings.append(batch)
self.saver = saver.Saver(list(embeddings_vars.values()))
# Create embeddings_metadata dictionary
if isinstance(self.embeddings_metadata, str):
embeddings_metadata = {
layer_name: self.embeddings_metadata
for layer_name in embeddings_vars.keys()
}
else:
# If embedding_metadata is already a dictionary
embeddings_metadata = self.embeddings_metadata
try:
from tensorboard.plugins import projector
except ImportError:
raise ImportError('Failed to import TensorBoard. Please make sure that '
'TensorBoard integration is complete."')
# TODO(psv): Add integration tests to test embedding visualization
# with TensorBoard callback. We are unable to write a unit test for this
# because TensorBoard dependency assumes TensorFlow package is installed.
config = projector.ProjectorConfig()
for layer_name, tensor in embeddings_vars.items():
embedding = config.embeddings.add()
embedding.tensor_name = tensor.name
if (embeddings_metadata is not None and
layer_name in embeddings_metadata):
embedding.metadata_path = embeddings_metadata[layer_name]
projector.visualize_embeddings(self.writer, config)
def set_model(self, model):
"""Sets Keras model and creates summary ops."""
self.model = model
self._init_writer(model)
# histogram summaries only enabled in graph mode
if not context.executing_eagerly():
self._make_histogram_ops(model)
self.merged = tf_summary.merge_all()
# If both embedding_freq and embeddings_data are available, we will
# visualize embeddings.
if self.embeddings_freq and self.embeddings_data is not None:
# Avoid circular dependency.
from tensorflow.python.keras.engine import training_utils # pylint: disable=g-import-not-at-top
self.embeddings_data = training_utils.standardize_input_data(
self.embeddings_data, model.input_names)
# If embedding_layer_names are not provided, get all of the embedding
# layers from the model.
embeddings_layer_names = self.embeddings_layer_names
if not embeddings_layer_names:
embeddings_layer_names = [
layer.name for layer in self.model.layers
if type(layer).__name__ == 'Embedding'
]
self.assign_embeddings = []
embeddings_vars = {}
self.batch_id = batch_id = array_ops.placeholder(dtypes.int32)
self.step = step = array_ops.placeholder(dtypes.int32)
for layer in self.model.layers:
if layer.name in embeddings_layer_names:
embedding_input = self.model.get_layer(layer.name).output
embedding_size = np.prod(embedding_input.shape[1:])
embedding_input = array_ops.reshape(
embedding_input, (step, int(embedding_size)))
shape = (self.embeddings_data[0].shape[0],
int(embedding_size))
embedding = variables.Variable(array_ops.zeros(shape),
name=layer.name +
'_embedding')
embeddings_vars[layer.name] = embedding
batch = state_ops.assign(
embedding[batch_id:batch_id + step], embedding_input)
self.assign_embeddings.append(batch)
self.saver = saver.Saver(list(embeddings_vars.values()))
# Create embeddings_metadata dictionary
if isinstance(self.embeddings_metadata, str):
embeddings_metadata = {
layer_name: self.embeddings_metadata
for layer_name in embeddings_vars.keys()
}
else:
# If embedding_metadata is already a dictionary
embeddings_metadata = self.embeddings_metadata
try:
from tensorboard.plugins import projector
except ImportError:
raise ImportError(
'Failed to import TensorBoard. Please make sure that '
'TensorBoard integration is complete."')
# TODO(psv): Add integration tests to test embedding visualization
# with TensorBoard callback. We are unable to write a unit test for this
# because TensorBoard dependency assumes TensorFlow package is installed.
config = projector.ProjectorConfig()
for layer_name, tensor in embeddings_vars.items():
embedding = config.embeddings.add()
embedding.tensor_name = tensor.name
if (embeddings_metadata is not None
and layer_name in embeddings_metadata):
embedding.metadata_path = embeddings_metadata[layer_name]
projector.visualize_embeddings(self.writer, config)
def set_model(self, model):
"""Sets Keras model and creates summary ops."""
self.model = model
self.sess = K.get_session()
# only make histogram summary op if it hasn't already been made
if self.histogram_freq and self.merged is None:
for layer in self.model.layers:
for weight in layer.weights:
mapped_weight_name = weight.name.replace(':', '_')
tf_summary.histogram(mapped_weight_name, weight)
if self.write_images:
w_img = array_ops.squeeze(weight)
shape = K.int_shape(w_img)
if len(shape) == 2: # dense layer kernel case
if shape[0] > shape[1]:
w_img = array_ops.transpose(w_img)
shape = K.int_shape(w_img)
w_img = array_ops.reshape(
w_img, [1, shape[0], shape[1], 1])
elif len(shape) == 3: # convnet case
if K.image_data_format() == 'channels_last':
# switch to channels_first to display
# every kernel as a separate image
w_img = array_ops.transpose(w_img,
perm=[2, 0, 1])
shape = K.int_shape(w_img)
w_img = array_ops.reshape(
w_img, [shape[0], shape[1], shape[2], 1])
elif len(shape) == 1: # bias case
w_img = array_ops.reshape(w_img,
[1, shape[0], 1, 1])
else:
# not possible to handle 3D convnets etc.
continue
shape = K.int_shape(w_img)
assert len(shape) == 4 and shape[-1] in [1, 3, 4]
tf_summary.image(mapped_weight_name, w_img)
if self.write_grads:
for weight in layer.trainable_weights:
mapped_weight_name = weight.name.replace(':', '_')
grads = model.optimizer.get_gradients(
model.total_loss, weight)
def is_indexed_slices(grad):
return type(grad).__name__ == 'IndexedSlices'
grads = [
grad.values if is_indexed_slices(grad) else grad
for grad in grads
]
tf_summary.histogram(
'{}_grad'.format(mapped_weight_name), grads)
if hasattr(layer, 'output'):
if isinstance(layer.output, list):
for i, output in enumerate(layer.output):
tf_summary.histogram(
'{}_out_{}'.format(layer.name, i), output)
else:
tf_summary.histogram('{}_out'.format(layer.name),
layer.output)
self.merged = tf_summary.merge_all()
if self.write_graph:
self.writer = self._writer_class(self.log_dir, self.sess.graph)
else:
self.writer = self._writer_class(self.log_dir)
# If both embedding_freq and embeddings_data are available, we will
# visualize embeddings.
if self.embeddings_freq and self.embeddings_data is not None:
self.embeddings_data = standardize_input_data(
self.embeddings_data, model.input_names)
# If embedding_layer_names are not provided, get all of the embedding
# layers from the model.
embeddings_layer_names = self.embeddings_layer_names
if not embeddings_layer_names:
embeddings_layer_names = [
layer.name for layer in self.model.layers
if type(layer).__name__ == 'Embedding'
]
self.assign_embeddings = []
embeddings_vars = {}
self.batch_id = batch_id = array_ops.placeholder(dtypes.int32)
self.step = step = array_ops.placeholder(dtypes.int32)
for layer in self.model.layers:
if layer.name in embeddings_layer_names:
embedding_input = self.model.get_layer(layer.name).output
embedding_size = np.prod(embedding_input.shape[1:])
embedding_input = array_ops.reshape(
embedding_input, (step, int(embedding_size)))
shape = (self.embeddings_data[0].shape[0],
int(embedding_size))
embedding = variables.Variable(array_ops.zeros(shape),
name=layer.name +
'_embedding')
embeddings_vars[layer.name] = embedding
batch = state_ops.assign(
embedding[batch_id:batch_id + step], embedding_input)
self.assign_embeddings.append(batch)
self.saver = saver.Saver(list(embeddings_vars.values()))
# Create embeddings_metadata dictionary
if isinstance(self.embeddings_metadata, str):
embeddings_metadata = {
layer_name: self.embeddings_metadata
for layer_name in embeddings_vars.keys()
}
else:
# If embedding_metadata is already a dictionary
embeddings_metadata = self.embeddings_metadata
try:
from tensorboard.plugins import projector
except ImportError:
raise ImportError(
'Failed to import TensorBoard. Please make sure that '
'TensorBoard integration is complete."')
# TODO(psv): Add integration tests to test embedding visualization
# with TensorBoard callback. We are unable to write a unit test for this
# because TensorBoard dependency assumes TensorFlow package is installed.
config = projector.ProjectorConfig()
for layer_name, tensor in embeddings_vars.items():
embedding = config.embeddings.add()
embedding.tensor_name = tensor.name
if (embeddings_metadata is not None
and layer_name in embeddings_metadata):
embedding.metadata_path = embeddings_metadata[layer_name]
projector.visualize_embeddings(self.writer, config)
def set_model(self, model):
"""Sets Keras model and creates summary ops."""
self.model = model
self.sess = K.get_session()
# only make histogram summary op if it hasn't already been made
if self.histogram_freq and self.merged is None:
for layer in self.model.layers:
for weight in layer.weights:
mapped_weight_name = weight.name.replace(':', '_')
tf_summary.histogram(mapped_weight_name, weight)
if self.write_images:
w_img = array_ops.squeeze(weight)
shape = K.int_shape(w_img)
if len(shape) == 2: # dense layer kernel case
if shape[0] > shape[1]:
w_img = array_ops.transpose(w_img)
shape = K.int_shape(w_img)
w_img = array_ops.reshape(w_img, [1, shape[0], shape[1], 1])
elif len(shape) == 3: # convnet case
if K.image_data_format() == 'channels_last':
# switch to channels_first to display
# every kernel as a separate image
w_img = array_ops.transpose(w_img, perm=[2, 0, 1])
shape = K.int_shape(w_img)
w_img = array_ops.reshape(w_img,
[shape[0], shape[1], shape[2], 1])
elif len(shape) == 1: # bias case
w_img = array_ops.reshape(w_img, [1, shape[0], 1, 1])
else:
# not possible to handle 3D convnets etc.
continue
shape = K.int_shape(w_img)
assert len(shape) == 4 and shape[-1] in [1, 3, 4]
tf_summary.image(mapped_weight_name, w_img)
if self.write_grads:
for weight in layer.trainable_weights:
mapped_weight_name = weight.name.replace(':', '_')
grads = model.optimizer.get_gradients(model.total_loss, weight)
def is_indexed_slices(grad):
return type(grad).__name__ == 'IndexedSlices'
grads = [grad.values if is_indexed_slices(grad) else grad
for grad in grads]
tf_summary.histogram('{}_grad'.format(mapped_weight_name), grads)
if hasattr(layer, 'output'):
if isinstance(layer.output, list):
for i, output in enumerate(layer.output):
tf_summary.histogram('{}_out_{}'.format(layer.name, i), output)
else:
tf_summary.histogram('{}_out'.format(layer.name), layer.output)
self.merged = tf_summary.merge_all()
if self.write_graph:
self.writer = self._writer_class(self.log_dir, self.sess.graph)
else:
self.writer = self._writer_class(self.log_dir)
# If both embedding_freq and embeddings_data are available, we will
# visualize embeddings.
if self.embeddings_freq and self.embeddings_data is not None:
self.embeddings_data = standardize_input_data(self.embeddings_data,
model.input_names)
# If embedding_layer_names are not provided, get all of the embedding
# layers from the model.
embeddings_layer_names = self.embeddings_layer_names
if not embeddings_layer_names:
embeddings_layer_names = [
layer.name
for layer in self.model.layers
if type(layer).__name__ == 'Embedding'
]
self.assign_embeddings = []
embeddings_vars = {}
self.batch_id = batch_id = array_ops.placeholder(dtypes.int32)
self.step = step = array_ops.placeholder(dtypes.int32)
for layer in self.model.layers:
if layer.name in embeddings_layer_names:
embedding_input = self.model.get_layer(layer.name).output
embedding_size = np.prod(embedding_input.shape[1:])
embedding_input = array_ops.reshape(embedding_input,
(step, int(embedding_size)))
shape = (self.embeddings_data[0].shape[0], int(embedding_size))
embedding = variables.Variable(
array_ops.zeros(shape), name=layer.name + '_embedding')
embeddings_vars[layer.name] = embedding
batch = state_ops.assign(embedding[batch_id:batch_id + step],
embedding_input)
self.assign_embeddings.append(batch)
self.saver = saver.Saver(list(embeddings_vars.values()))
# Create embeddings_metadata dictionary
if isinstance(self.embeddings_metadata, str):
embeddings_metadata = {
layer_name: self.embeddings_metadata
for layer_name in embeddings_vars.keys()
}
else:
# If embedding_metadata is already a dictionary
embeddings_metadata = self.embeddings_metadata
try:
from tensorboard.plugins import projector
except ImportError:
raise ImportError('Failed to import TensorBoard. Please make sure that '
'TensorBoard integration is complete."')
# TODO(psv): Add integration tests to test embedding visualization
# with TensorBoard callback. We are unable to write a unit test for this
# because TensorBoard dependency assumes TensorFlow package is installed.
config = projector.ProjectorConfig()
for layer_name, tensor in embeddings_vars.items():
embedding = config.embeddings.add()
embedding.tensor_name = tensor.name
if (embeddings_metadata is not None and
layer_name in embeddings_metadata):
embedding.metadata_path = embeddings_metadata[layer_name]
projector.visualize_embeddings(self.writer, config)
def set_model(self, model):
self.model = model
if K.backend() == 'tensorflow':
self.sess = K.get_session()
if self.histogram_freq and self.merged is None:
for layer in self.model.layers:
for weight in layer.weights:
mapped_weight_name = weight.name.replace(':', '_')
tf.summary.histogram(mapped_weight_name, weight)
if self.write_grads and weight in layer.trainable_weights:
grads = model.optimizer.get_gradients(
model.total_loss, weight)
def is_indexed_slices(grad):
return type(grad).__name__ == 'IndexedSlices'
grads = [
grad.values if is_indexed_slices(grad) else grad
for grad in grads
]
tf.summary.histogram(
'{}_grad'.format(mapped_weight_name), grads)
if self.write_images:
w_img = tf.squeeze(weight)
shape = K.int_shape(w_img)
if len(shape) == 2: # dense layer kernel case
if shape[0] > shape[1]:
w_img = tf.transpose(w_img)
shape = K.int_shape(w_img)
w_img = tf.reshape(w_img,
[1, shape[0], shape[1], 1])
elif len(shape) == 3: # convnet case
if K.image_data_format() == 'channels_last':
# switch to channels_first to display
# every kernel as a separate image
w_img = tf.transpose(w_img, perm=[2, 0, 1])
shape = K.int_shape(w_img)
w_img = tf.reshape(
w_img, [shape[0], shape[1], shape[2], 1])
elif len(shape) == 1: # bias case
w_img = tf.reshape(w_img, [1, shape[0], 1, 1])
else:
# not possible to handle 3D convnets etc.
continue
shape = K.int_shape(w_img)
assert len(shape) == 4 and shape[-1] in [1, 3, 4]
tf.summary.image(mapped_weight_name, w_img)
if hasattr(layer, 'output') and self.write_output:
if isinstance(layer.output, list):
for i, output in enumerate(layer.output):
if output.dtype.is_complex:
print(
'skip output histogram because complex dtype'
)
else:
tf.summary.histogram(
'{}_out_{}'.format(layer.name, i), output)
else:
if layer.output.dtype.is_complex:
print(
'skip output histogram because complex dtype')
else:
tf.summary.histogram('{}_out'.format(layer.name),
layer.output)
self.merged = tf.summary.merge_all()
if self.write_graph:
self.writer = tf.summary.FileWriter(self.log_dir, self.sess.graph)
else:
self.writer = tf.summary.FileWriter(self.log_dir)
if self.embeddings_freq and self.embeddings_data is not None:
self.embeddings_data = standardize_input_data(
self.embeddings_data, model.input_names)
embeddings_layer_names = self.embeddings_layer_names
if not embeddings_layer_names:
embeddings_layer_names = [
layer.name for layer in self.model.layers
if type(layer).__name__ == 'Embedding'
]
self.assign_embeddings = []
embeddings_vars = {}
self.batch_id = batch_id = tf.placeholder(tf.int32)
self.step = step = tf.placeholder(tf.int32)
for layer in self.model.layers:
if layer.name in embeddings_layer_names:
embedding_input = self.model.get_layer(layer.name).output
embedding_size = np.prod(embedding_input.shape[1:])
embedding_input = tf.reshape(embedding_input,
(step, int(embedding_size)))
shape = (self.embeddings_data[0].shape[0],
int(embedding_size))
embedding = tf.Variable(tf.zeros(shape),
name=layer.name + '_embedding')
embeddings_vars[layer.name] = embedding
batch = tf.assign(embedding[batch_id:batch_id + step],
embedding_input)
self.assign_embeddings.append(batch)
self.saver = tf.train.Saver(list(embeddings_vars.values()))
if not isinstance(self.embeddings_metadata, str):
embeddings_metadata = self.embeddings_metadata
else:
embeddings_metadata = {
layer_name: self.embeddings_metadata
for layer_name in embeddings_vars.keys()
}
config = projector.ProjectorConfig()
for layer_name, tensor in embeddings_vars.items():
embedding = config.embeddings.add()
embedding.tensor_name = tensor.name
if layer_name in embeddings_metadata:
embedding.metadata_path = embeddings_metadata[layer_name]
projector.visualize_embeddings(self.writer, config)
