Python Tensorflow RNN精度和成本：NaN

我为一些信号和它们的一个热编码标签训练了一个RNN。在解决了一些大小和形状不匹配的问题后，网络运行无误。然而，我得到的损失和准确性南

Epoch 1 completed out of 10 loss: nan
Epoch 2 completed out of 10 loss: nan
Epoch 3 completed out of 10 loss: nan
Epoch 4 completed out of 10 loss: nan
Epoch 5 completed out of 10 loss: nan
Epoch 6 completed out of 10 loss: nan
Epoch 7 completed out of 10 loss: nan
Epoch 8 completed out of 10 loss: nan
Epoch 9 completed out of 10 loss: nan
Epoch 10 completed out of 10 loss: nan
Accuracy: nan

下面是我如何设置输入数据和标签的-

"""Input signals"""
for X in range(no_tau):

    random.seed()
    tau = np.array([int(math.ceil(np.random.uniform(lorange, hirange)))])
    X= amplitude * np.exp(-t / tau)
    X = np.reshape(X, [-1, 1,1])
    #print(X)
"""Output labels"""
cn = 0
class1 = [0]
class2 = [1]
while (cn <no_tau):
    tau = np.array([int(math.ceil(np.random.uniform(lorange, hirange)))])
    if tau<500:
        label = one_hot(class1, num_labels=2)
    else:
        label = one_hot(class2, num_labels=2)
    cn = cn + 1
    print ('For tau value of', tau, 'label is', label)

“输入信号”
对于范围内的X（无头）：
random.seed（）
tau=np.array（[int（math.ceil（np.random.uniform（lorange，hirange））））
X=振幅*np.exp（-t/tau）
X=np.重塑（X，[-1,1,1]）
#打印（X）
“”“输出标签”“”
cn=0
类别1=[0]
类别2=[1]
虽然你的学习率太高了。我试过使用小型LR 1e-5和1e-10，但仍然发现可能存在更多问题，但你没有正确设置
X
和
标签
hi@rvinas，你认为哪里不对？你能建议一下吗？在调用
训练神经网络（X）之前，试着打印
X
和
label
。
        for epoch in range(hm_epochs):
            epoch_loss = 0
            i = 0
            while i < no_tau:
                start = i
                end = i + batch_size
                batch_x = np.array(X[start:end])
                batch_y = np.array(label[start:end])

                _, c = sess.run([optimizer, cost], feed_dict={x: batch_x, y: batch_y})
                epoch_loss += c
                i += batch_size