TensorFlow 占位符声明

Question

我正在尝试将 tutorial 从 Keras 转换为 TF。 我收到以下错误：

Traceback (most recent call last):
  File "/Users/spicyramen/Documents/Development/google/python/machine_learning/deep_learning/exercise1_tf.py", line 64, in <module>
    sess.run(train_step, feed_dict=train_data)
  File "/Library/Python/2.7/site-packages/tensorflow/python/client/session.py", line 789, in run
    run_metadata_ptr)
  File "/Library/Python/2.7/site-packages/tensorflow/python/client/session.py", line 975, in _run
    % (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (768,) for Tensor u'Placeholder_1:0', which has shape '(?, 1)'

这似乎与我如何传递目标标签以及如何声明占位符值有关。 当我返回标签时，我有这个：

>>> dataset[:, 8].shape
(768,)
>>> dataset[:, 0:8].shape
(768, 8)

代码

import tensorflow as tf
import numpy as np

print("Tensorflow version: " + tf.__version__)
tf.set_random_seed(0)

FILENAME = 'pima-indians-diabetes.csv'
_LEARNING_RATE = 0.003
_NUM_FEATURES = 8
_NUM_LABELS = 1
_NUM_EPOCHS = 150
_BATCH_SIZE = 10


def import_data(filename):
    if filename:
        dataset = np.loadtxt(filename, delimiter=",")
        return dataset[:, 0:8], dataset[:, 8]


# create placeholder. Dataset contains _NUM_FEATURES features:
X = tf.placeholder(tf.float32, [None, _NUM_FEATURES])
Y_ = tf.placeholder(tf.float32,[None, _NUM_LABELS])  # Placeholder for correct answers

# weights and biases
W = tf.Variable(tf.random_normal([_NUM_FEATURES, _NUM_LABELS],
                                 mean=0,
                                 stddev=0.1,
                                 name='weights'))

b = tf.Variable(tf.random_normal([1, _NUM_LABELS],
                                 mean=0,
                                 stddev=0.1,
                                 name='bias'))

# activation function
Y = tf.nn.relu(tf.matmul(X, W) + b, name='activation')

# cost function i.e. sigmoid_cross_entropy_with_logits
cross_entropy = tf.nn.sigmoid_cross_entropy_with_logits(labels=Y_, logits=Y, name='loss_function')
optimizer = tf.train.AdamOptimizer(_LEARNING_RATE)  # Formal derivation
train_step = optimizer.minimize(cross_entropy)

# cost function i.e. RMSE
# cross_entropy = tf.nn.l2_loss(Y - Y_, name="squared_error_cost")
# optimizer = tf.train.GradientDescentOptimizer(_LEARNING_RATE)
# train_step = optimizer.minimize(cross_entropy)

is_correct = tf.equal(tf.argmax(Y, 1), tf.argmax(Y_, 1))
accuracy = tf.reduce_mean(tf.cast(is_correct, tf.float32))

# init
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)

for i in range(_NUM_EPOCHS):
    # data
    batch_X, batch_Y = import_data(FILENAME)
    # train
    train_data = {X: batch_X, Y_: batch_Y}
    sess.run(train_step, feed_dict=train_data)
    a, c = sess.run([accuracy, cross_entropy], feed_dict=train_data)        
    print(str(i) + ": accuracy:" + str(a) + " loss: " + str(c))

Answer 1

这是你的问题：

>>> dataset[:, 8].shape
(768,)

TensorFlow 需要一个形状数组 (768,1) 而不是 (768,) 作为错误引用：

Cannot feed value of shape (768,) for Tensor u'Placeholder_1:0', which has shape '(?, 1)'

这两种形状之间的差异有点小，Numpy 通常会在许多情况下为您广播这些形状，但 TF 不会。看看这两种形状的区别in this question with a great answer。

幸运的是，在您的情况下，解决方案非常简单。您可以使用np.expand_dims() 将您的(768,) 向量转换为(768,1) 向量，如下所示：

>>> np.array([5,5,5]).shape
(3,)
>>> np.expand_dims(np.array([5,5,5]), axis=1).shape
(3, 1)

在您的 import_data 函数中，只需将返回行更改为

return dataset[:, 0:8], np.expand_dims(dataset[:, 8], axis=1)

编辑：我喜欢上面的方法，因为np.expand_dims 更明确一点，但还有另一种同样简单的方法，其他人可能会认为它更清楚——这取决于你的习惯。想我会包括它的完整性。 (N,) 和 (N,1) 数组之间的区别在于，第一个将值保存在 0 维数组 np.array([5, 5, 5]) 中，而第二个将值保存在 1 维数组 np.array([[5],[5],[5]]) 中。您可以通过在其周围添加括号将 0-d 数组转换为 1-d 数组；但它是一行而不是一列，所以它需要转置。所以这是两种建议的方法； B 是新的建议，C 是上面的建议：

>>> A = np.array([5,5,5])
>>> B = np.array([A]).T
>>> C = np.expand_dims(A, axis=1)
>>> A; A.shape
array([5, 5, 5])
(3,)
>>> B; B.shape
array([[5],
       [5],
       [5]])
(3, 1)
>>> C; C.shape
array([[5],
       [5],
       [5]])
(3, 1)

Edit2：TensorFlow 本身也有一个tf.expand_dims() 函数。