Question

请参考下面的tensorflow代码：

#!/usr/bin/env python3
import tensorflow as tf
import numpy as np
from sklearn.datasets import fetch_california_housing
import numpy.random as rnd

housing = fetch_california_housing()
m, n = (50000, 3)

n_epochs = 50000
learning_rate = 0.1

X = tf.placeholder(tf.float32, shape=(None, n + 1), name="X")
y = tf.placeholder(tf.float32, shape=(None, 1), name="y")
theta = tf.Variable(tf.random_uniform([n + 1, 1], -1.0, 1.0, seed=42), name="theta")
y_pred = tf.matmul(X, theta, name="predictions")
error = y_pred - y
mse = tf.reduce_mean(tf.square(error), name="mse")
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
training_op = optimizer.minimize(mse)

init = tf.global_variables_initializer()

ans_theta = np.array([[4],[3],[2],[1]]).astype(np.float32)
X_train = rnd.rand(m, n + 1)
y_train = X_train.dot(ans_theta).reshape(m, 1)
print("ans_theta=%s" % (ans_theta.transpose()))
print("X_train=%s" % (X_train[0]))
print("Expect y=%s"  % (np.sum(X_train[0] * ans_theta.transpose())))
print("y_train=%s" % (y_train[0]))
def fetch_batch(epoch, batch_index, batch_size):
    rnd.seed(epoch * n_batches + batch_index)
    indices = rnd.randint(m, size=batch_size)
    X_batch = X_train[indices]
    y_batch = y_train[indices]
    return X_batch, y_batch

n_epochs = 500
batch_size = 2000
n_batches = int(np.ceil(m / batch_size))

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

    for epoch in range(n_epochs):
    #    for batch_index in range(n_batches):
    #        X_batch, y_batch = fetch_batch(epoch, batch_index, batch_size)
            #print("X_batch(%s):\n%s\n" % (X_batch.shape, X_batch[:1]))
            #print("y_batch(%s):\n%s\n" % (y_batch.shape, y_batch[:1]))
    #        sess.run(training_op, feed_dict={X: X_batch, y: y_batch})
        sess.run(training_op, feed_dict={X:X_train, y:y_train})
    best_theta = theta.eval()
    print("MSE=%s" % (mse.eval()))
print("Best theta:")
print(best_theta)

它会导致异常，如下所示：

由op'X'引起，定义于：文件“./ch9_t00.py”，第19行，in          X = tf.placeholder（tf.float32，shape =（None，n + 1），name =“X”）File   “/usr/local/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py”   第1507行，占位符       name = name）文件“/usr/local/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py”，   1997年，在_placeholder       name = name）文件“/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py”，   第768行，在apply_op中       op_def = op_def）文件“/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”，   第2336行，在create_op中       original_op = self._default_original_op，op_def = op_def）文件“/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”，   第1228行，在 init 中       self._traceback = _extract_stack（）

InvalidArgumentError（请参阅上面的回溯）：您必须提供值   对于占位符张量'X'与dtype float            [[Node：X = Placeholderdtype = DT_FLOAT，shape = []，_ device =“/ job：localhost / replica：0 / task：0 / cpu：0”]]

我不知道为什么。如果我删除行“print（”MSE =％s“％（mse.eval（）））”，那么一切都会好的。有什么建议吗？

提前致谢！

Answer 1

如果没有任何数据，您无法评估您的MSE，您必须为占位符x和y提供值，以评估输入{{1}上的网络预测之间的均方误差和x中给出的地面实况标签。

您可以使用

或在训练时这样做：

print("MSE=%s" % sess.run(mse, feed_dict={X:X_train, y:y_train}))

Tensorflow - 您必须使用dtype float

1 个答案: