def make_input_fns():
train, eval = mnist.load_data()
fns = []
for data in (train, eval):
x, y = data
x = (x.astype(np.float32) * 2. / 255.) - 1.
y = y.astype(np.int64)
fns.append(tf.estimator.inputs.numpy_input_fn(
{'x': x}, y,
batch_size=tf.flags.FLAGS.batch_size,
num_epochs=None,
shuffle=True
))
return fns
def onBeginTraining(self):
ue.log("starting mnist keras cnn training")
model_file_name = "mnistKerasCNN"
model_directory = ue.get_content_dir() + "/Scripts/"
model_sess_path = model_directory + model_file_name + ".tfsess"
model_json_path = model_directory + model_file_name + ".json"
my_file = Path(model_json_path)
#reset the session each time we get training calls
K.clear_session()
#let's train
batch_size = 128
num_classes = 10
epochs = 8
# input image dimensions
img_rows, img_cols = 28, 28
# the data, shuffled and split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
if K.image_data_format() == 'channels_first':
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
ue.log('x_train shape:' + str(x_train.shape))
ue.log(str(x_train.shape[0]) + 'train samples')
ue.log(str(x_test.shape[0]) + 'test samples')
# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
model = Sequential()
model.add(Conv2D(64, kernel_size=(3, 3),
activation='relu',
input_shape=input_shape))
# model.add(Dropout(0.2))
# model.add(Flatten())
# model.add(Dense(512, activation='relu'))
# model.add(Dropout(0.2))
# model.add(Dense(num_classes, activation='softmax'))
#model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test),
callbacks=[self.stopcallback])
score = model.evaluate(x_test, y_test, verbose=0)
ue.log("mnist keras cnn training complete.")
ue.log('Test loss:' + str(score[0]))
ue.log('Test accuracy:' + str(score[1]))
self.session = K.get_session()
self.model = model
stored = {'model':model, 'session': self.session}
#run a test evaluation
ue.log(x_test.shape)
result_test = model.predict(np.reshape(x_test[500],(1,28,28,1)))
ue.log(result_test)
#flush the architecture model data to disk
#with open(model_json_path, "w") as json_file:
# json_file.write(model.to_json())
#flush the whole model and weights to disk
#saver = tf.train.Saver()
#save_path = saver.save(K.get_session(), model_sess_path)
#model.save(model_path)
return stored
from tensorflow.contrib.keras.api.keras.models import Model
from tensorflow.contrib.keras.api.keras.layers import Input, Dense
from tensorflow.contrib.keras.python.keras.layers import TimeDistributed
from tensorflow.contrib.keras.api.keras.layers import LSTM
# Training parameters.
batch_size = 32
num_classes = 10
epochs = 5
# Embedding dimensions.
row_hidden = 128
col_hidden = 128
# The data, shuffled and split between train and test sets.
(x_train, y_train), (x_test, y_test) = mnist.load_data()
# Reshapes data to 4D for Hierarchical RNN.
x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)
x_test = x_test.reshape(x_test.shape[0], 28, 28, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# Converts class vectors to binary class matrices.
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
def make_input_fns():
train, test = mnist.load_data()
return make_input_fn(train), make_input_fn(test)
def main_fun(args, ctx):
import numpy
import os
import tensorflow as tf
import tensorflow.contrib.keras as keras
from tensorflow.contrib.keras.api.keras import backend as K
from tensorflow.contrib.keras.api.keras.models import Sequential, load_model, save_model
from tensorflow.contrib.keras.api.keras.layers import Dense, Dropout
from tensorflow.contrib.keras.api.keras.optimizers import RMSprop
from tensorflow.contrib.keras.python.keras.callbacks import LambdaCallback, TensorBoard
from tensorflow.python.saved_model import builder as saved_model_builder
from tensorflow.python.saved_model import tag_constants
from tensorflow.python.saved_model.signature_def_utils_impl import predict_signature_def
from tensorflowonspark import TFNode
cluster, server = TFNode.start_cluster_server(ctx)
if ctx.job_name == "ps":
server.join()
elif ctx.job_name == "worker":
def generate_rdd_data(tf_feed, batch_size):
print("generate_rdd_data invoked")
while True:
batch = tf_feed.next_batch(batch_size)
imgs = []
lbls = []
for item in batch:
imgs.append(item[0])
lbls.append(item[1])
images = numpy.array(imgs).astype('float32') / 255
labels = numpy.array(lbls).astype('float32')
yield (images, labels)
with tf.device(
tf.train.replica_device_setter(
worker_device="/job:worker/task:%d" % ctx.task_index,
cluster=cluster)):
IMAGE_PIXELS = 28
batch_size = 100
num_classes = 10
# the data, shuffled and split between train and test sets
if args.input_mode == 'tf':
from tensorflow.contrib.keras.api.keras.datasets import mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(60000, 784)
x_test = x_test.reshape(10000, 784)
x_train = x_train.astype('float32') / 255
x_test = x_test.astype('float32') / 255
# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
else: # args.mode == 'spark'
x_train = tf.placeholder(tf.float32,
[None, IMAGE_PIXELS * IMAGE_PIXELS],
name="x_train")
y_train = tf.placeholder(tf.float32, [None, 10],
name="y_train")
model = Sequential()
model.add(Dense(512, activation='relu', input_shape=(784, )))
model.add(Dropout(0.2))
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(10, activation='softmax'))
model.summary()
model.compile(loss='categorical_crossentropy',
optimizer=RMSprop(),
metrics=['accuracy'])
saver = tf.train.Saver()
with tf.Session(server.target) as sess:
K.set_session(sess)
def save_checkpoint(epoch, logs=None):
if epoch == 1:
tf.train.write_graph(sess.graph.as_graph_def(),
args.model_dir, 'graph.pbtxt')
saver.save(sess,
os.path.join(args.model_dir, 'model.ckpt'),
global_step=epoch * args.steps_per_epoch)
ckpt_callback = LambdaCallback(on_epoch_end=save_checkpoint)
tb_callback = TensorBoard(log_dir=args.model_dir,
histogram_freq=1,
write_graph=True,
write_images=True)
# add callbacks to save model checkpoint and tensorboard events (on worker:0 only)
callbacks = [ckpt_callback, tb_callback
] if ctx.task_index == 0 else None
if args.input_mode == 'tf':
# train & validate on in-memory data
history = model.fit(x_train,
y_train,
batch_size=batch_size,
epochs=args.epochs,
verbose=1,
validation_data=(x_test, y_test),
callbacks=callbacks)
else: # args.input_mode == 'spark':
# train on data read from a generator which is producing data from a Spark RDD
tf_feed = TFNode.DataFeed(ctx.mgr)
history = model.fit_generator(
generator=generate_rdd_data(tf_feed, batch_size),
steps_per_epoch=args.steps_per_epoch,
epochs=args.epochs,
verbose=1,
callbacks=callbacks)
if args.export_dir and ctx.job_name == 'worker' and ctx.task_index == 0:
# save a local Keras model, so we can reload it with an inferencing learning_phase
save_model(model, "tmp_model")
# reload the model
K.set_learning_phase(False)
new_model = load_model("tmp_model")
# export a saved_model for inferencing
builder = saved_model_builder.SavedModelBuilder(
args.export_dir)
signature = predict_signature_def(
inputs={'images': new_model.input},
outputs={'scores': new_model.output})
builder.add_meta_graph_and_variables(
sess=sess,
tags=[tag_constants.SERVING],
signature_def_map={'predict': signature},
clear_devices=True)
builder.save()
if args.input_mode == 'spark':
tf_feed.terminate()
from tensorflow.contrib.keras.api.keras.models import Sequential
from tensorflow.contrib.keras.api.keras.layers import Dense, Activation, Convolution2D
# from tensorflow.examples.tutorials.mnist import input_data
from tensorflow.python.keras._impl.keras.utils import np_utils
# mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
batch_size = 128
n_classes = 10
n_epoch = 12 # 训练轮数
img_rows, img_cols = 28, 28
n_filters = 32
poll_size = (2, 2) # 池化大小
kernel_size = (3, 3) # 卷积核大小
(train_x, train_y), (test_x, test_y) = mnist.load_data()
train_x = train_x.reshape(train_x.shape[0], img_rows, img_cols, 1)
test_x = test_x.reshape(test_x.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
train_x = train_x.astype('float32')
test_x = test_x.astype('float32')
train_x /= 255
test_x /= 255
# 将类向量转换成二进制矩阵
train_y = np_utils.to_categorical(train_y, n_classes)
test_y = np_utils.to_categorical(test_y, n_classes)
# 构建训练模型
model = Sequential()
# 添加卷积层
model.add(Convolution2D(n_filters, kernel_size[0],
def load_dataset():
train, test = mnist.load_data()
return train, test