Question

我在TensorFlow中成功实现了一个前馈算法，如下所示......

mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)

# tf Graph Input
x = tf.placeholder(tf.float32, [None, 784])  # mnist data image of shape 28*28=784
y = tf.placeholder(tf.float32, [None, 10])  # 0-9 digits recognition => 10 classes

# set model weights
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

# construct model
logits = tf.matmul(x, W) + b
pred = tf.nn.softmax(logits)  # Softmax

# minimize error using cross entropy
cost = tf.reduce_mean(-tf.reduce_sum(y * tf.log(pred), reduction_indices=1))
# Gradient Descent
optimizer = tf.train.GradientDescentOptimizer(FLAGS.learning_rate).minimize(cost)

# initializing the variables
init = tf.global_variables_initializer()

......培训周期如下......

# launch the graph
with tf.Session() as sess:

    sess.run(init)

    # training cycle
    for epoch in range(FLAGS.training_epochs):
        avg_cost = 0
        total_batch = int(mnist.train.num_examples/FLAGS.batch_size)
        # loop over all batches
        for i in range(total_batch):
            batch_xs, batch_ys = mnist.train.next_batch(FLAGS.batch_size)

            _, c = sess.run([optimizer, cost], feed_dict={x: batch_xs, y: batch_ys})

......其余代码不是必需的。到目前为止，代码完美无缺。请务必注意，我的batch_size为100.问题是我使用tf.placeholder表示我的值，但实际上我需要将其更改为使用tf.get_variable。我做的第一件事是更改以下内容......

# tf Graph Input
x = tf.get_variable("input_image", shape=[100,784], dtype=tf.float32)
y = tf.placeholder(shape=[100,10], name='input_label', dtype=tf.float32)  # 0-9 digits recognition => 10 classes


# set model weights
W = tf.get_variable("weights", shape=[784, 10], dtype=tf.float32, initializer=tf.random_normal_initializer())
b = tf.get_variable("biases", shape=[1, 10], dtype=tf.float32, initializer=tf.zeros_initializer())

# construct model
logits = tf.matmul(x, W) + b
pred = tf.nn.softmax(logits)  # Softmax

# minimize error using cross entropy
cost = tf.reduce_mean(-tf.reduce_sum(y * tf.log(pred), reduction_indices=1))
# Gradient Descent
optimizer = tf.train.GradientDescentOptimizer(FLAGS.learning_rate).minimize(cost)

# initializing the variables
init = tf.global_variables_initializer()

......到目前为止一切顺利。但现在我正在尝试实施培训周期，这是我遇到问题的地方。我使用batch_size = 100运行与上述完全相同的训练周期，我得到以下错误......

tensorflow.python.framework.errors_impl.InvalidArgumentError：节点GradientDescent / update_input_image / ApplyGradientDescent的输入0是从_recv_input_image_0传递的浮点数：0与预期的float_ref不兼容。

如何解决此问题？错误来自以下行...

_, c = sess.run([optimizer, cost], feed_dict={x: batch_xs, y: batch_ys})

Answer 1

我不清楚为什么当您继续为其提供值时，需要将x更改为tf.Variable。有两种解决方法（不包括您可以将x恢复为tf.placeholder()的情况，如工作代码中所示）：

由于optimizer正在尝试将SGD更新应用于您正在提供的值（这会导致令人困惑的运行时类型错误），因此引发了错误。您可以在构建optimizer时传递trainable=False来阻止x执行此操作：
```
x = tf.get_variable("input_image", shape=[100, 784], dtype=tf.float32,
                    trainable=False)
```

由于x是一个变量，因此您可以在运行optimizer之前，在单独的步骤中将图像分配给变量。

x = tf.get_variable("input_image", shape=[100, 784], dtype=tf.float32)
x_placeholder = tf.placeholder(tf.float32, shape=[100, 784])
assign_x_op = x.assign(x_placeholder).op

# ...

for i in range(total_batch):
    batch_xs, batch_ys = mnist.train.next_batch(FLAGS.batch_size)

    # Assign the contents of `batch_xs` to variable `x`.
    sess.run(assign_x_op, feed_dict={x_placeholder: batch_xs})

    # N.B. Now you do not need to feed `x`.
    _, c = sess.run([optimizer, cost], feed_dict={y: batch_ys})

后一版本允许您对图像内容执行渐变下降（这可能是您首先要将其存储在变量中的原因）。

TensorFlow变量配置

1 个答案: