我重用了TensorFlow的多变量线性回归代码，并尝试降低成本，但问题是经过几次迭代后，成本以及W和b的值变成了inf，并且很快变成了nan。请问有人能告诉我问题出在哪里吗？我有大约100,000个值。我已经将其裁剪到10,000个值用于测试。数据集在这里这里

这是代码

import numpy as npimport tensorflow as tfdef computeX():    all_xs = np.loadtxt("test.csv", delimiter=',', skiprows=1, usecols=range(4,260)) #reads the columns except first one     timestamps = np.loadtxt("test.csv", delimiter=',', skiprows=1, usecols=(0),dtype =str)    symbols = np.loadtxt("test.csv", delimiter=',', skiprows=1, usecols=(1),dtype =float)    categories = np.loadtxt("test.csv", delimiter=',', skiprows=1, usecols=(2),dtype =str)    tempList = []    BOW = {"M1": 1.0, "M5": 2.0, "M15": 3.0, "M30": 4.0, "H1": 5.0, "H4": 6.0, "D1": 7.0}    #explode dates and make them features.. 2016/11/1 01:54 becomes [2016, 11, 1, 01, 54]    for i, v in enumerate(timestamps):        splitted = v.split()        dateVal = splitted[0]        timeVal = splitted[1]        ar = dateVal.split("/")        splittedTime = timeVal.split(":")        ar = ar + splittedTime        Features = np.asarray(ar)        Features = Features.astype(float)        # append symbols        Features = np.append(Features,symbols[i])        #append categories from BOW        Features = np.append(Features, BOW[categories[i]] )        row = np.append(Features,all_xs[i])        row = row.tolist()        tempList.append(row)    all_xs = np.array(tempList)    del tempList[:]    return all_xsif __name__ == "__main__":    print ("Starting....")    learn_rate = 0.5    all_ys = np.loadtxt("test.csv", delimiter=',', skiprows=1, usecols=3) #reads only first column      all_xs = computeX()    datapoint_size= int(all_xs.shape[0])    print(datapoint_size)    x = tf.placeholder(tf.float32, [None, 263], name="x")    W = tf.Variable(tf.ones([263,1]), name="W")    b = tf.Variable(tf.ones([1]), name="b")    product = tf.matmul(x,W)    y = product + b    y_ = tf.placeholder(tf.float32, [datapoint_size])    cost = tf.reduce_mean(tf.square(y_-y))/ (2*datapoint_size)    train_step = tf.train.GradientDescentOptimizer(learn_rate).minimize(cost)    sess = tf.Session()    init = tf.global_variables_initializer()    sess.run(init)    batch_size = 10000    steps =10    for i in range(steps):      print("Entering Loop")      if datapoint_size == batch_size:         batch_start_idx = 0      elif datapoint_size < batch_size:         raise ValueError("datapoint_size: %d, must be greater than batch_size: %d" % (datapoint_size, batch_size))      else:         batch_start_idx = (i * batch_size) % (datapoint_size - batch_size)      batch_end_idx = batch_start_idx + batch_size      batch_xs = all_xs[batch_start_idx:batch_end_idx]      batch_ys = all_ys[batch_start_idx:batch_end_idx]      xs = np.array(batch_xs)      ys = np.array(batch_ys)      feed = { x: xs, y_: ys }      sess.run(train_step, feed_dict=feed)        print("W: %s" % sess.run(W))      print("b: %f" % sess.run(b))      print("cost: %f" % sess.run(cost, feed_dict=feed))

回答：

请查看你的数据：

id8         id9         id10    id11    id121451865600  1451865600  -19.8   87.1    0.57011451865600  1451865600  -1.6    3.6     0.571921451865600  1451865600  -5.3    23.9    0.57155

你还将权重初始化为1，如果你将所有输入数据乘以1，然后将它们相加，所有“重”的列（id8、id9等，包含大数字的列）会将数据从较小的列中推开。你还有充满零的列：

id236   id237   id238   id239   id2400       0       0       0       00       0       0       0       00       0       0       0       0 

这些都是不相容的因素。大值会导致非常高的预测，这些会导致损失爆炸和溢出。即使将学习率缩小十亿倍也几乎没有效果。

因此建议如下：

• 检查你的数据，删除所有无意义的数据（充满零的列）
• 归一化你的输入数据
• 在这一点上检查损失函数的大小，然后尝试调整学习率。