Question

这可能是张量流初学者的问题。

我有一个组合trainX(training)和trainY(answer)，testX和testY以及单furtureX（预测未来Y）

然后我的体重为w_h，b_h，w，b

w_h = tf.Variable(tf.truncated_normal([companys,n_hidden],stddev=0.001))
b_h = tf.Variable(tf.zeros([n_hidden]))

w = tf.Variable(tf.truncated_normal([n_hidden,1],stddev=0.001)) 
b = tf.Variable(tf.zeros([1]))

x = tf.placeholder(tf.float32,shape=[None,companys]) # change dimensions to 2 -> 10
t = tf.placeholder(tf.float32,shape=[None,1])

h = tf.nn.relu(tf.matmul(x,w_h) + b_h)
y = tf.matmul(h,w) + b

cross_entropy = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=y,labels=t))
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(cross_entropy)
correct_prediction = tf.equal(tf.to_float(tf.greater(y,0.5)),t)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

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

for epoch in range(20000):
    sess.run(train_step,feed_dict={
        x: trainX,
        t: trainY
    })
    if epoch % 1000  == 0:
        trainAcc = sess.run(accuracy, feed_dict={x: trainX, t: trainY})
        testAcc = sess.run(accuracy, feed_dict={x: testX, t: testY})
        print ("accuracy at %s   train:%.3f  test:%.3f" % (epoch, trainAcc,testAcc))

#successfully get the final `weight` here

bIn = sess.run(b)
wIn = sess.run(w)
bHide = sess.run(b_h)
wHide = sess.run(w_h)
pprint(bIn)
pprint(wIn)
pprint(bHide)
pprint(wHide)

#I want to get the final data from `futureX`

现在，有了最后的重量＆＃39;，我想从futureX预测未来。

我应该使用什么样的功能？

我为初学者阅读了很多书，并了解如何列出培训和测试数据，但是无法找到预测未来的方法..

从火车/答案获得重量后，我如何预测未来的vaue？

0 个答案: