代码之家 › 专栏 › 技术社区 › DocDriven

如何在使用输入管道时替换feed\u dict?

tensorflow python-3.x python

2

DocDriven · 技术社区 · 8 年前

假设您有一个与 feed_dict 到目前为止,我们还没有将数据注入到图形中。每隔几个时期,我都会将其中一个数据集中的一批数据输入到我的图表中,以此来评估训练和测试损失。

现在,出于性能原因,我决定使用一个输入管道。看看这个虚拟示例:

import tensorflow as tf
import numpy as np

dataset_size = 200
batch_size= 5
dimension = 4

# create some training dataset
dataset = tf.data.Dataset.\
    from_tensor_slices(np.random.normal(2.0,size=(dataset_size,dimension)).
    astype(np.float32))

dataset = dataset.batch(batch_size) # take batches

iterator = dataset.make_initializable_iterator()
x = tf.cast(iterator.get_next(),tf.float32)
w = tf.Variable(np.random.normal(size=(1,dimension)).astype(np.float32))

loss_func = lambda x,w: tf.reduce_mean(tf.square(x-w)) # notice that the loss function is a mean!
loss = loss_func(x,w) # this is the loss that will be minimized
train_op = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    # train one epoch
    sess.run(iterator.initializer)
    for i in range(dataset_size//batch_size):
        # the training step will update the weights based on ONE batch of examples each step
        loss1,_ = sess.run([loss,train_op])
        print('train step {:d}.  batch loss {:f}.'.format(i,loss1))

        # I want to print the loss from another dataset (test set) here

打印丢失的训练数据是没有问题的,但是如何为另一个数据集执行此操作? 使用时 ,我简单地从所说的集合中得到一批,然后给它一个x值。

1 回复 | 直到 8 年前

1

2

javidcf 8 年前

你可以为此做几件事。一个简单的选择可能是拥有两个数据集和迭代器并使用 tf.cond 在它们之间切换。但是,更强大的方法是使用直接支持它的迭代器。请参见上的指南 how to create iterators 各种迭代器类型的描述。例如,使用一个可重新初始化的迭代器,可以得到如下结果:

import tensorflow as tf
import numpy as np

dataset_size = 200
dataset_test_size = 20
batch_size= 5
dimension = 4

# create some training dataset
dataset = tf.data.Dataset.\
    from_tensor_slices(np.random.normal(2.0,size=(dataset_size,dimension)).
    astype(np.float32))

dataset = dataset.batch(batch_size) # take batches

# create some test dataset
dataset_test = tf.data.Dataset.\
    from_tensor_slices(np.random.normal(2.0,size=(dataset_test_size,dimension)).
    astype(np.float32))

dataset_test = dataset_test.batch(batch_size) # take batches

iterator = tf.data.Iterator.from_structure(dataset.output_types,
                                           dataset.output_shapes)

dataset_init_op = iterator.make_initializer(dataset)
dataset_test_init_op = iterator.make_initializer(dataset_test)

x = tf.cast(iterator.get_next(),tf.float32)
w = tf.Variable(np.random.normal(size=(1,dimension)).astype(np.float32))

loss_func = lambda x,w: tf.reduce_mean(tf.square(x-w)) # notice that the loss function is a mean!
loss = loss_func(x,w) # this is the loss that will be minimized
train_op = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    # train one epoch
    sess.run(dataset_init_op)
    for i in range(dataset_size//batch_size):
        # the training step will update the weights based on ONE batch of examples each step
        loss1,_ = sess.run([loss,train_op])
        print('train step {:d}.  batch loss {:f}.'.format(i,loss1))

    # print test loss
    sess.run(dataset_test_init_op)
    for i in range(dataset_test_size//batch_size):
        loss1 = sess.run(loss)
        print('test step {:d}.  batch loss {:f}.'.format(i,loss1))

你可以用feedable迭代器做一些类似的事情,这取决于你觉得什么更方便,我想甚至可以用一个可初始化的迭代器,例如,生成一个布尔数据集,然后用它映射到一些数据 tf.条件 ,尽管这不是一个很自然的方法。

下面是如何用一个可初始化的迭代器来实现它,实际上比我最初想的更简洁,所以也许你更喜欢这样:

import tensorflow as tf
import numpy as np

dataset_size = 200
dataset_test_size = 20
batch_size= 5
dimension = 4

# create data
data = tf.constant(np.random.normal(2.0,size=(dataset_size,dimension)), tf.float32)
data_test = tf.constant(np.random.normal(2.0,size=(dataset_test_size,dimension)), tf.float32)
# choose data
testing = tf.placeholder_with_default(False, ())
current_data = tf.cond(testing, lambda: data_test, lambda: data)
# create dataset
dataset = tf.data.Dataset.from_tensor_slices(current_data)
dataset = dataset.batch(batch_size)
# create iterator
iterator = dataset.make_initializable_iterator()

x = tf.cast(iterator.get_next(),tf.float32)
w = tf.Variable(np.random.normal(size=(1,dimension)).astype(np.float32))

loss_func = lambda x,w: tf.reduce_mean(tf.square(x-w)) # notice that the loss function is a mean!
loss = loss_func(x,w) # this is the loss that will be minimized
train_op = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    # train one epoch
    sess.run(iterator.initializer)
    for i in range(dataset_size//batch_size):
        # the training step will update the weights based on ONE batch of examples each step
        loss1,_ = sess.run([loss,train_op])
        print('train step {:d}.  batch loss {:f}.'.format(i,loss1))

    # print test loss
    sess.run(iterator.initializer, feed_dict={testing: True})
    for i in range(dataset_test_size//batch_size):
        loss1 = sess.run(loss)
        print('test step {:d}.  batch loss {:f}.'.format(i,loss1))