Question

请记住，我对tf非常陌生。

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_boston

np.set_printoptions(suppress=True)

boston = load_boston()

m = boston.data.shape[0] - 1

bt_unfixed = np.transpose(boston.data)
bt = np.insert(bt_unfixed, 0, 1)

Y = tf.placeholder(tf.float64)
X = tf.placeholder(tf.float64, [None, 13])
print X.shape
W = tf.Variable(np.transpose(np.array([0.00,0,0,0,0,0,0,0,0,0,0,0,0]).flatten()), name='weights')
b = tf.Variable(0.5, name='bias')

hypothesis = tf.add(tf.matmul(X, W), tf.cast(b, tf.float64))

loss = tf.reduce_sum(tf.square(hypothesis - Y)) / (2 * m)

optimizer = tf.train.GradientDescentOptimizer(0.01)

train_op = optimizer.minimize(loss)

with tf.Session() as sess:
    sess.run(tf.initialize_all_variables())
    for i in range(0, 1200):
        for (x, y) in zip(boston.data, boston.target.data):
            sess.run(train_op, feed_dict={X:x, Y:y})
    print "Done!\n"
    print "Running test...\n"
    t = sess.run(cost, feed_dict={X:boston.data[504], Y:boston.target.data[504]})
    print "loss =" + str(t) + "Real value" + str(boston.target.data[504]) + "Pred " +str(sess.run(hypothesis, feed_dict={X:boston.data[504]}))

请随时更正我的代码中的任何其他错误！

当我定义假设时会抛出错误，我需要转置我的向量以将它们相乘，但它不起作用。

Traceback (most recent call last):
  File "multihouse.py", line 20, in <module>
    hypothesis = tf.add(tf.matmul(X, W), tf.cast(b, tf.float64))
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py", line 1398, in matmul
    name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_math_ops.py", line 1348, in _mat_mul
    transpose_b=transpose_b, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 749, in apply_op
    op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2382, in create_op
    set_shapes_for_outputs(ret)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1783, in set_shapes_for_outputs
    shapes = shape_func(op)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/common_shapes.py", line 596, in call_cpp_shape_fn
    raise ValueError(err.message)

    ValueError: Shape must be rank 2 but is rank 1

Answer 1

问题是没有像numpy中的矢量转置这样的东西。你必须定义一个具有一个平凡维度的矩阵来处理这些事情，例如

np.array([0.00,0,0,0,0,0,0,0,0,0,0,0,0]) # this cannot be transposed
np.array([[0.00,0,0,0,0,0,0,0,0,0,0,0,0]]) # this can

就像在这个例子中一样

>>> import numpy as np
>>> np.transpose(np.array([1,1,1]))
array([1, 1, 1])
>>> np.transpose(np.array([[1,1,1]]))
array([[1],
       [1],
       [1]])

一旦你解决了这个问题，你的假设就会被正确定义（现在你试图将矩阵与一个向量相乘，而这个向量在TF中没有定义）。

张量流形状误差（最新版本）多元线性回归

1 个答案: