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,
names=["ids", "labels"],
shapes=[[], []],
types=[tf.int32, 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 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,
names=["ids", "labels"],
shapes=[[], []],
types=[tf.int32, tf.int32],
batch_size=8)
from tensorflow.python.ops import variable_scope
def variable_creator(**kwargs):
kwargs["use_resource"] = False
return variable_scope.default_variable_creator(None, **kwargs)
getter = lambda next_creator, **kwargs: variable_creator(**kwargs)
with variable_scope.variable_creator_scope(getter):
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 input_fn(mode):
np.random.seed(20)
x = np.random.rand(20, 10)
y = np.random.randint(0, 10, (20))
rdd_x = self.sc.parallelize(x)
rdd_y = self.sc.parallelize(y)
rdd = rdd_x.zip(rdd_y)
if mode == tf.estimator.ModeKeys.TRAIN or mode == tf.estimator.ModeKeys.EVAL:
dataset = TFDataset.from_rdd(rdd,
features=(tf.float32, [10]),
labels=(tf.int32, []))
else:
dataset = TFDataset.from_rdd(rdd_x,
features=(tf.float32, [10]))
return dataset
def main(max_epoch):
sc = init_nncontext()
training_rdd = get_data_rdd("train", sc)
testing_rdd = get_data_rdd("test", sc)
dataset = TFDataset.from_rdd(training_rdd,
features=(tf.float32, [28, 28, 1]),
labels=(tf.int32, []),
batch_size=320,
val_rdd=testing_rdd)
model = tf.keras.Sequential(
[tf.keras.layers.Flatten(input_shape=(28, 28, 1)),
tf.keras.layers.Dense(64, activation='relu'),
tf.keras.layers.Dense(64, activation='relu'),
tf.keras.layers.Dense(10, activation='softmax'),
]
)
model.compile(optimizer=tf.keras.optimizers.RMSprop(),
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
keras_model = KerasModel(model)
keras_model.fit(dataset,
epochs=max_epoch,
distributed=True)
eval_dataset = TFDataset.from_rdd(
testing_rdd,
features=(tf.float32, [28, 28, 1]),
labels=(tf.int32, []), batch_per_thread=80)
result = keras_model.evaluate(eval_dataset)
print(result)
# >> [0.08865142822265625, 0.9722]
# the following assert is used for internal testing
assert result['acc Top1Accuracy'] > 0.95
model.save_weights("/tmp/mnist_keras.h5")
def input_fn(mode):
if mode == tf.estimator.ModeKeys.TRAIN:
training_rdd = get_data_rdd("train", sc)
dataset = TFDataset.from_rdd(training_rdd,
features=(tf.float32, [28, 28, 1]),
labels=(tf.int32, []),
batch_size=320)
elif mode == tf.estimator.ModeKeys.EVAL:
testing_rdd = get_data_rdd("test", sc)
dataset = TFDataset.from_rdd(testing_rdd,
features=(tf.float32, [28, 28, 1]),
labels=(tf.int32, []),
batch_size=320)
else:
testing_rdd = get_data_rdd("test", sc).map(lambda x: x[0])
dataset = TFDataset.from_rdd(testing_rdd,
features=(tf.float32, [28, 28, 1]),
batch_per_thread=80)
return dataset
def test_dataset_without_batch(self):
x = np.random.rand(20, 10)
y = np.random.randint(0, 2, (20))
rdd_x = self.sc.parallelize(x)
rdd_y = self.sc.parallelize(y)
rdd = rdd_x.zip(rdd_y)
dataset = TFDataset.from_rdd(rdd,
features=(tf.float32, [10]),
labels=(tf.int32, []),
names=["features", "labels"],
val_rdd=rdd)
keras_model = self.create_model()
model = KerasModel(keras_model)
self.intercept(
lambda: model.fit(dataset), "The batch_size of TFDataset must be" +
" specified when used in KerasModel fit.")
dataset = TFDataset.from_rdd(
rdd,
features=(tf.float32, [10]),
labels=(tf.int32, []),
names=["features", "labels"],
)
self.intercept(
lambda: model.evaluate(dataset),
"The batch_per_thread of TFDataset must be " +
"specified when used in KerasModel evaluate.")
dataset = TFDataset.from_rdd(
rdd_x,
features=(tf.float32, [10]),
names=["features", "labels"],
)
self.intercept(
lambda: model.predict(dataset),
"The batch_per_thread of TFDataset must be" +
" specified when used in KerasModel predict.")
def create_predict_dataset(self):
np.random.seed(20)
x = np.random.rand(20, 10)
rdd = self.sc.parallelize(x)
rdd = rdd.map(lambda x: [x])
dataset = TFDataset.from_rdd(rdd,
features=(tf.float32, [10]),
batch_per_thread=1)
return dataset
def create_predict_dataset(self):
np.random.seed(20)
x = np.random.rand(20, 10)
rdd = self.sc.parallelize(x)
rdd = rdd.map(lambda x: [x])
dataset = TFDataset.from_rdd(rdd,
names=["features"],
shapes=[[10]],
types=[tf.float32],
batch_per_thread=1)
return dataset
def create_evaluation_dataset(self):
np.random.seed(20)
x = np.random.rand(20, 10)
y = np.random.randint(0, 2, (20))
rdd_x = self.sc.parallelize(x)
rdd_y = self.sc.parallelize(y)
rdd = rdd_x.zip(rdd_y)
dataset = TFDataset.from_rdd(rdd,
features=(tf.float32, [10]),
labels=(tf.int32, []),
batch_per_thread=1)
return dataset
def create_training_dataset(self):
np.random.seed(20)
x = np.random.rand(20, 10)
y = np.random.randint(0, 2, (20))
rdd_x = self.sc.parallelize(x)
rdd_y = self.sc.parallelize(y)
rdd = rdd_x.zip(rdd_y)
dataset = TFDataset.from_rdd(rdd,
features=(tf.float32, [10]),
labels=(tf.int32, []),
batch_size=4,
val_rdd=rdd)
return dataset
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)
# construct the model from TFDataset
images, labels = dataset.tensors
with slim.arg_scope(lenet.lenet_arg_scope()):
logits, end_points = lenet.lenet(images,
num_classes=10,
is_training=True)
loss = tf.reduce_mean(
tf.losses.sparse_softmax_cross_entropy(logits=logits, labels=labels))
# create a optimizer
optimizer = TFOptimizer(loss,
Adam(1e-3),
val_outputs=[logits],
val_labels=[labels],
val_method=Top1Accuracy())
optimizer.set_train_summary(TrainSummary("/tmp/az_lenet", "lenet"))
optimizer.set_val_summary(ValidationSummary("/tmp/az_lenet", "lenet"))
# kick off training
optimizer.optimize(end_trigger=MaxEpoch(max_epoch))
saver = tf.train.Saver()
saver.save(optimizer.sess, "/tmp/lenet/model")
def main(data_num):
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.load_weights("/tmp/mnist_keras.h5")
if DISTRIBUTED:
# using RDD api to do distributed evaluation
sc = init_nncontext()
# get data, pre-process and create TFDataset
(images_data, labels_data) = mnist.read_data_sets("/tmp/mnist", "test")
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)])
dataset = TFDataset.from_rdd(rdd,
names=["features"],
shapes=[[28, 28, 1]],
types=[tf.float32],
batch_per_thread=20)
predictor = TFPredictor.from_keras(model, dataset)
accuracy = predictor.predict().zip(labels_rdd).map(
lambda x: np.argmax(x[0]) == x[1]).mean()
print("predict accuracy is %s" % accuracy)
else:
# using keras api for local evaluation
model.compile(optimizer='rmsprop',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
(images_data, labels_data) = mnist.read_data_sets("/tmp/mnist", "test")
images_data = normalizer(images_data, mnist.TRAIN_MEAN,
mnist.TRAIN_STD)
result = model.evaluate(images_data, labels_data)
print(model.metrics_names)
print(result)
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 test_tf_dataset_with_list_feature(self):
np.random.seed(20)
x = np.random.rand(20, 10)
y = np.random.randint(0, 2, (20))
rdd_x = self.sc.parallelize(x)
rdd_y = self.sc.parallelize(y)
rdd = rdd_x.zip(rdd_y)
dataset = TFDataset.from_rdd(rdd,
features=[(tf.float32, [10]), (tf.float32, [10])],
labels=(tf.int32, []),
batch_size=4,
val_rdd=rdd
)
for idx, tensor in enumerate(dataset.feature_tensors):
assert tensor.name == "list_input_" + str(idx) + ":0"
def main(data_num):
sc = init_nncontext()
# get data, pre-process and create TFDataset
(images_data, labels_data) = mnist.read_data_sets("/tmp/mnist", "test")
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])])
dataset = TFDataset.from_rdd(rdd,
names=["features", "labels"],
shapes=[[28, 28, 1], [1]],
types=[tf.float32, tf.int32],
batch_per_thread=20)
# construct the model from TFDataset
images, labels = dataset.tensors
labels = tf.squeeze(labels)
with slim.arg_scope(lenet.lenet_arg_scope()):
logits, end_points = lenet.lenet(images,
num_classes=10,
is_training=False)
predictions = tf.to_int32(tf.argmax(logits, axis=1))
correct = tf.expand_dims(tf.to_int32(tf.equal(predictions, labels)),
axis=1)
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.restore(sess, "/tmp/lenet/model")
predictor = TFPredictor(sess, [correct])
accuracy = predictor.predict().mean()
print("predict accuracy is %s" % accuracy)
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,
features=(tf.float32, [28, 28, 1]),
labels=(tf.int32, []),
batch_size=280,
val_rdd=testing_rdd)
# construct the model from TFDataset
images, labels = dataset.tensors
with slim.arg_scope(lenet.lenet_arg_scope()):
logits, end_points = lenet.lenet(images, num_classes=10, is_training=True)
loss = tf.reduce_mean(tf.losses.sparse_softmax_cross_entropy(logits=logits, labels=labels))
acc = accuracy(logits, labels)
# create a optimizer
optimizer = TFOptimizer.from_loss(loss, Adam(1e-3),
metrics={"acc": acc},
model_dir="/tmp/lenet/")
# kick off training
optimizer.optimize(end_trigger=MaxEpoch(max_epoch))
saver = tf.train.Saver()
saver.save(optimizer.sess, "/tmp/lenet/model")
def test_tf_optimizer_with_sparse_gradient(self):
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]])
with tf.Graph().as_default():
dataset = TFDataset.from_rdd(training_rdd,
names=["ids", "labels"],
shapes=[[], []],
types=[tf.int32, tf.int32],
batch_size=8)
id_tensor, label_tensor = dataset.tensors
embedding_table = tf.get_variable(name="word_embedding",
shape=[10, 5])
embedding = tf.nn.embedding_lookup(embedding_table, id_tensor)
loss = tf.reduce_mean(
tf.losses.sparse_softmax_cross_entropy(logits=embedding,
labels=label_tensor))
optimizer = TFOptimizer(loss, Adam(1e-3))
optimizer.optimize(end_trigger=MaxEpoch(1))
optimizer.sess.close()
from bigdl.dataset import mnist
from tensorflow_gan.examples.mnist.networks import *
from tensorflow_gan.python.losses.losses_impl import *
def get_data_rdd(dataset):
(images_data, labels_data) = mnist.read_data_sets("/tmp/mnist", dataset)
image_rdd = sc.parallelize(images_data).map(lambda img: [((img / 255) - 0.5) * 2])
return image_rdd
if __name__ == "__main__":
sc = init_nncontext()
training_rdd = get_data_rdd("train")
dataset = TFDataset.from_rdd(training_rdd,
features=(tf.float32, (28, 28, 1)),
batch_size=32)
def noise_fn(batch_size):
return tf.random.normal(mean=0.0, stddev=1.0, shape=(batch_size, 10))
dataset = dataset.map(lambda tensors: (noise_fn(tf.shape(tensors[0])[0]), tensors[0]))
opt = GANEstimator(
generator_fn=unconditional_generator,
discriminator_fn=unconditional_discriminator,
generator_loss_fn=wasserstein_generator_loss,
discriminator_loss_fn=wasserstein_discriminator_loss,
generator_optimizer=Adam(1e-3, beta1=0.5),
discriminator_optimizer=Adam(1e-4, beta1=0.5),
model_dir="/tmp/gan_model/model"
