我正在尝试学习TensorFlow，并试图对初学者示例进行一些修改。
我正在尝试将从头开始实现神经网络与深度MNIST专家教程结合起来。
我使用X, y = sklearn.datasets.make_moons(50, noise=0.20)获取数据。基本上，这行代码会生成2D的X(,)和2类别的Y(0/1)。
x = tf.placeholder(tf.float32, shape=[50,2])y_ = tf.placeholder(tf.float32, shape=[50,2])网络的结构与《深度MNIST专家教程》相同。不同之处在于会话运行函数。
sess.run(train_step, feed_dict={x:X, y_:y})但这会导致
_ValueError: setting an array element with a sequence._谁能给我一些关于这个问题的提示？这是代码。
import numpy as npimport matplotlibimport tensorflow as tfimport matplotlib.pyplot as pltimport sklearnimport sklearn.datasetsimport sklearn.linear_modelsess = tf.InteractiveSession()matplotlib.rcParams['figure.figsize'] = (10.0, 8.0)np.random.seed(0)X, y = sklearn.datasets.make_moons(50, noise=0.20)plt.scatter(X[:,0], X[:,1], s=40, c=y, cmap=plt.cm.Spectral)clf = sklearn.linear_model.LogisticRegressionCV()clf.fit(X, y)batch_xs = np.vstack([np.expand_dims(k,0) for k in X])x = tf.placeholder(tf.float32, shape=[50,2])y_ = tf.placeholder(tf.float32, shape=[50,2])W = tf.Variable(tf.zeros([2,2]))b = tf.Variable(tf.zeros([2]))a = np.arange(100).reshape((50, 2))y = tf.nn.softmax(tf.matmul(x,W) + b)cross_entropy = -tf.reduce_sum(y_*tf.log(y))train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)sess.run(tf.initialize_all_variables())for i in range(20000):sess.run(train_step, feed_dict={x:X, y_:y})经过与TensorFlow的斗争后，这是正确的代码：
# 包导入import numpy as npimport matplotlibimport tensorflow as tfimport matplotlib.pyplot as pltimport sklearnimport sklearn.datasetsimport sklearn.linear_modelrng = np.randominput_dim = 2output_dim = 2hidden_dim = 3np.random.seed(0)Train_X, Train_Y = sklearn.datasets.make_moons(200, noise=0.20)Train_X = np.reshape(Train_X, (-1,2))Train_YY = [] for i in Train_Y: # 将Train_Y转换为2-D列表 if i == 1: Train_YY.append([1,0]) else: Train_YY.append([0,1])print Train_YYX = tf.placeholder("float",shape=[None,input_dim])Y = tf.placeholder("float")W1 = tf.Variable(tf.random_normal([input_dim, hidden_dim], stddev=0.35), name="weights")b1 = tf.Variable(tf.zeros([1,hidden_dim]), name="bias1")a1 = tf.tanh(tf.add(tf.matmul(X,W1),b1))W2 = tf.Variable(tf.random_normal([hidden_dim,output_dim]), name="weight2")b2 = tf.Variable(tf.zeros([1,output_dim]), name="bias2")a2 = tf.add(tf.matmul(a1, W2), b2)output=tf.nn.softmax(a2)correct_prediction = tf.equal(tf.argmax(output,1), tf.argmax(Y,1))accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))cross_entropy = -tf.reduce_sum(Y*tf.log(output))optimizer = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)with tf.Session() as sess: sess.run(tf.initialize_all_variables()) for i in range(20000): # for (a,d) in zip(Train_X, Train_Y): training_cost = sess.run(optimizer, feed_dict={X:Train_X, Y:Train_YY}) if i%1000 == 0: # print "Training cost=", training_cost, "W1=", W1.eval(), "b1=", b1.eval(),"W2=", W2.eval(), "b2=", b2.eval() # print output.eval({X:Train_X, Y:Train_YY}) # print cross_entropy.eval({X:Train_X, Y:Train_YY}) print "Accuracy = ", accuracy.eval({X:Train_X, Y:Train_YY}) 回答：
问题出现在你重新定义y的这行代码上：
y = tf.nn.softmax(tf.matmul(x,W) + b)TensorFlow因此会报错，因为在feed_dict中将y_: y传给另一个张量是不可能的（即使可能，这样做也会产生循环依赖！）。
解决方案是重写你的softmax和交叉熵操作：
y_softmax = tf.nn.softmax(tf.matmul(x,W) + b)cross_entropy = -tf.reduce_sum(y_*tf.log(y_softmax))