def test_tf_optimizer_with_sparse_gradient_using_keras(self):
import tensorflow as tf
ids = np.random.randint(0, 10, size=[40])
labels = np.random.randint(0, 5, size=[40])
id_rdd = self.sc.parallelize(ids)
label_rdd = self.sc.parallelize(labels)
training_rdd = id_rdd.zip(label_rdd).map(lambda x: [x[0], x[1]])
dataset = TFDataset.from_rdd(training_rdd,
features=(tf.int32, []),
labels=(tf.int32, []),
batch_size=8)
words_input = tf.keras.layers.Input(shape=(), name='words_input')
embedding_layer = tf.keras.layers.Embedding(input_dim=10,
output_dim=5,
name='word_embedding')
word_embeddings = embedding_layer(words_input)
embedding = tf.keras.layers.Flatten()(word_embeddings)
output = tf.keras.layers.Dense(5, activation="softmax")(embedding)
model = tf.keras.models.Model(inputs=[words_input], outputs=[output])
model.compile(optimizer="sgd", loss="sparse_categorical_crossentropy")
optimizer = TFOptimizer.from_keras(model, dataset)
optimizer.optimize()
def fit(self, data,
epochs=1,
batch_size=32,
feature_cols=None,
labels_cols=None,
validation_data=None,
hard_code_batch_size=False,
session_config=None,
checkpoint_trigger=None
):
"""
Train this keras model with train data.
:param data: train data. It can be XShards, Spark DataFrame, tf.data.Dataset.
If data is XShards, each element needs to be {'x': a feature numpy array
or a tuple of feature numpy arrays, 'y': a label numpy array or a tuple of
label numpy arrays}
If data is tf.data.Dataset, each element is [feature tensor tuple, label tensor tuple]
:param epochs: number of epochs to train.
:param batch_size: total batch size for each iteration.
:param feature_cols: feature column names if train data is Spark DataFrame.
:param labels_cols: label column names if train data is Spark DataFrame.
:param validation_data: validation data. Validation data type should be the same
as train data.
:param hard_code_batch_size: whether hard code batch size for training. Default is False.
:param session_config: tensorflow session configuration for training.
Should be object of tf.ConfigProto
:param checkpoint_trigger: when to trigger checkpoint during training.
Should be bigdl optimzer trigger, like EveryEpoch(), SeveralIteration(num_iterations),etc.
"""
if isinstance(data, DataFrame):
assert feature_cols is not None, \
"feature columns is None; it should not be None in training"
assert labels_cols is not None, \
"label columns is None; it should not be None in training"
dataset = to_dataset(data, batch_size=batch_size, batch_per_thread=-1,
validation_data=validation_data,
feature_cols=feature_cols, labels_cols=labels_cols,
hard_code_batch_size=hard_code_batch_size,
sequential_order=False, shuffle=True
)
self.tf_optimizer = TFOptimizer.from_keras(self.model.model, dataset,
model_dir=self.model.model_dir,
session_config=session_config,
metrics=self.metrics)
if self.load_checkpoint:
self.tf_optimizer.load_checkpoint(self.checkpoint_path, self.checkpoint_version)
if self.log_dir and self.app_name:
self.tf_optimizer.estimator.set_tensorboad(self.log_dir, self.app_name)
self.tf_optimizer.optimize(MaxEpoch(epochs), checkpoint_trigger=checkpoint_trigger)
return self
def main(max_epoch, data_num):
sc = init_nncontext()
# get data, pre-process and create TFDataset
def get_data_rdd(dataset):
(images_data,
labels_data) = mnist.read_data_sets("/tmp/mnist", dataset)
image_rdd = sc.parallelize(images_data[:data_num])
labels_rdd = sc.parallelize(labels_data[:data_num])
rdd = image_rdd.zip(labels_rdd) \
.map(lambda rec_tuple: [normalizer(rec_tuple[0], mnist.TRAIN_MEAN, mnist.TRAIN_STD),
np.array(rec_tuple[1])])
return rdd
training_rdd = get_data_rdd("train")
testing_rdd = get_data_rdd("test")
dataset = TFDataset.from_rdd(training_rdd,
names=["features", "labels"],
shapes=[[28, 28, 1], []],
types=[tf.float32, tf.int32],
batch_size=280,
val_rdd=testing_rdd)
data = Input(shape=[28, 28, 1])
x = Flatten()(data)
x = Dense(64, activation='relu')(x)
x = Dense(64, activation='relu')(x)
predictions = Dense(10, activation='softmax')(x)
model = Model(inputs=data, outputs=predictions)
model.compile(optimizer='rmsprop',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
optimizer = TFOptimizer.from_keras(model,
dataset,
model_dir="/tmp/mnist_keras")
# kick off training
optimizer.optimize(end_trigger=MaxEpoch(max_epoch))
model.save_weights("/tmp/mnist_keras/mnist_keras.h5")
def fit(self,
data,
epochs=1,
batch_size=32,
feature_cols=None,
label_cols=None,
validation_data=None,
session_config=None,
checkpoint_trigger=None,
auto_shard_files=True):
"""
Train this keras model with train data.
:param data: train data. It can be XShards, Spark DataFrame, tf.data.Dataset.
If data is XShards, each partition can be Pandas Dataframe or a dictionary of
{'x': feature, 'y': label}, where feature(label) is a numpy array or a tuple of
numpy arrays.
If data is tf.data.Dataset, each element is [feature tensor tuple, label tensor
tuple]
:param epochs: number of epochs to train.
:param batch_size: total batch size for each iteration.
:param feature_cols: feature column names if train data is Spark DataFrame or XShards
of Pandas DataFrame.
:param label_cols: label column names if train data is Spark DataFrame or XShards of
Pandas DataFrame.
:param validation_data: validation data. Validation data type should be the same
as train data.
:param session_config: tensorflow session configuration for training.
Should be object of tf.ConfigProto
:param checkpoint_trigger: when to trigger checkpoint during training.
Should be a zoo.orca.learn.trigger, like EveryEpoch(), SeveralIteration(
num_iterations),etc.
:param auto_shard_files: whether to automatically detect if the dataset is file-based and
and apply sharding on files, otherwise sharding on records. Default is False.
"""
if isinstance(data, DataFrame):
assert feature_cols is not None, \
"feature columns is None; it should not be None in training"
assert label_cols is not None, \
"label columns is None; it should not be None in training"
if isinstance(data, tf.data.Dataset):
assert isinstance(data.element_spec, tuple), \
"If data is tf.data.Dataset, each element should be " \
"(feature tensors, label tensor), where each feature/label tensor can be " \
"either a single tensor or a tuple of tensors"
if validation_data is not None:
assert isinstance(validation_data, tf.data.Dataset), \
"train data and validation data should be both tf.data.Dataset"
assert isinstance(validation_data.element_spec, tuple), \
"If validation_data is tf.data.Dataset, each element should be " \
"(feature tensors, label tensor), where each feature/label tensor can be " \
"either a single tensor or a tuple of tensors"
if isinstance(data, SparkXShards):
if data._get_class_name() == 'pandas.core.frame.DataFrame':
assert feature_cols is not None, \
"feature columns is None; it should not be None in training"
assert label_cols is not None, \
"label columns is None; it should not be None in training"
data, validation_data = process_xshards_of_pandas_dataframe(
data, feature_cols, label_cols, validation_data, "fit")
if checkpoint_trigger is not None:
checkpoint_trigger = Trigger.convert_trigger(checkpoint_trigger)
if is_tf_data_dataset(data):
data = data.map(_standardize_keras_target_data)
validation_data = validation_data.map(
_standardize_keras_target_data)
memory_type = OrcaContext.train_data_store
dataset = to_dataset(data,
batch_size=batch_size,
batch_per_thread=-1,
validation_data=validation_data,
feature_cols=feature_cols,
label_cols=label_cols,
hard_code_batch_size=False,
sequential_order=False,
shuffle=True,
auto_shard_files=auto_shard_files,
memory_type=memory_type)
self.tf_optimizer = TFOptimizer.from_keras(
self.model.model,
dataset,
model_dir=self.model.model_dir,
session_config=session_config,
metrics=self.metrics,
optimizer=self.optimizer)
if self.clip_norm:
self.tf_optimizer.set_gradient_clipping_by_l2_norm(
clip_norm=self.clip_norm)
if self.clip_min and self.clip_max:
self.tf_optimizer.set_constant_gradient_clipping(
self.clip_min, self.clip_max)
if self.load_checkpoint:
self.tf_optimizer.load_checkpoint(self.checkpoint_path,
self.checkpoint_version)
if self.log_dir and self.app_name:
self.tf_optimizer.estimator.set_tensorboard(
self.log_dir, self.app_name)
self.tf_optimizer.optimize(MaxEpoch(epochs),
checkpoint_trigger=checkpoint_trigger)
return self
def fit(
self,
data,
epochs=1,
batch_size=32,
feature_cols=None,
labels_cols=None,
validation_data=None,
hard_code_batch_size=False,
session_config=None,
checkpoint_trigger=None,
auto_shard_files=True,
):
"""
Train this keras model with train data.
:param data: train data. It can be XShards, Spark DataFrame, tf.data.Dataset.
If data is XShards, each element needs to be {'x': a feature numpy array
or a tuple of feature numpy arrays, 'y': a label numpy array or a tuple of
label numpy arrays}
If data is tf.data.Dataset, each element is [feature tensor tuple, label tensor tuple]
:param epochs: number of epochs to train.
:param batch_size: total batch size for each iteration.
:param feature_cols: feature column names if train data is Spark DataFrame.
:param labels_cols: label column names if train data is Spark DataFrame.
:param validation_data: validation data. Validation data type should be the same
as train data.
:param hard_code_batch_size: whether hard code batch size for training. Default is False.
:param session_config: tensorflow session configuration for training.
Should be object of tf.ConfigProto
:param checkpoint_trigger: when to trigger checkpoint during training.
Should be a zoo.orca.learn.trigger, like EveryEpoch(), SeveralIteration(num_iterations),etc.
"""
if isinstance(data, DataFrame):
assert feature_cols is not None, \
"feature columns is None; it should not be None in training"
assert labels_cols is not None, \
"label columns is None; it should not be None in training"
if isinstance(data, tf.data.Dataset):
assert isinstance(data.element_spec, tuple), \
"If data is tf.data.Dataset, each element should be " \
"(feature tensors, label tensor), where each feature/label tensor can be " \
"either a single tensor or a tuple of tensors"
if validation_data is not None:
assert isinstance(validation_data, tf.data.Dataset), \
"train data and validation data should be both tf.data.Dataset"
assert isinstance(validation_data.element_spec, tuple), \
"If validation_data is tf.data.Dataset, each element should be " \
"(feature tensors, label tensor), where each feature/label tensor can be " \
"either a single tensor or a tuple of tensors"
if checkpoint_trigger is not None:
checkpoint_trigger = Trigger.convert_trigger(checkpoint_trigger)
if is_tf_data_dataset(data):
data = data.map(_standardize_keras_target_data)
validation_data = validation_data.map(
_standardize_keras_target_data)
dataset = to_dataset(data,
batch_size=batch_size,
batch_per_thread=-1,
validation_data=validation_data,
feature_cols=feature_cols,
labels_cols=labels_cols,
hard_code_batch_size=hard_code_batch_size,
sequential_order=False,
shuffle=True,
auto_shard_files=auto_shard_files)
if isinstance(dataset, TFNdarrayDataset):
dataset = _standarize_feature_label_dataset(
dataset, self.model.model)
self.tf_optimizer = TFOptimizer.from_keras(
self.model.model,
dataset,
model_dir=self.model.model_dir,
session_config=session_config,
metrics=self.metrics,
optimizer=self.optimizer)
if self.clip_norm:
self.tf_optimizer.set_gradient_clipping_by_l2_norm(
clip_norm=self.clip_norm)
if self.clip_min and self.clip_max:
self.tf_optimizer.set_constant_gradient_clipping(
self.clip_min, self.clip_max)
if self.load_checkpoint:
self.tf_optimizer.load_checkpoint(self.checkpoint_path,
self.checkpoint_version)
if self.log_dir and self.app_name:
self.tf_optimizer.estimator.set_tensorboard(
self.log_dir, self.app_name)
self.tf_optimizer.optimize(MaxEpoch(epochs),
checkpoint_trigger=checkpoint_trigger)
return self