Machine learning 没有为任何变量提供梯度

我有一个小问题：

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

Nclass = 500
D = 2
M = 3
K = 3

X1 = np.random.randn(Nclass, D) + np.array([0, -2])
X2 = np.random.randn(Nclass, D) + np.array([2, 2])
X3 = np.random.randn(Nclass, D) + np.array([-2, 2])
X = np.vstack ([X1, X2, X3]).astype(np.float32)

Y = np.array([0]*Nclass + [1]*Nclass + [2]*Nclass)

plt.scatter(X[:,0], X[:,1], c=Y, s=100, alpha=0.5)
plt.show()

N = len(Y)

T = np.zeros((N, K))
for i in range(N):
    T[i, Y[i]] = 1

def init_weights(shape):
    return tf.Variable(tf.random_normal(shape, stddev=0.01))

def forward(X, W1, b1, W2, b2):
    Z = tf.nn.sigmoid(tf.matmul(X, W1) + b1)
    return tf.matmul(Z, W2) + b2

tfX = tf.placeholder(tf.float32, [None, D])
tfY = tf.placeholder(tf.float32, [None, K])

W1 = init_weights([D, M])
b1 = init_weights([M])
W2 = init_weights([M, K])
b2 = init_weights([K])

py_x = forward(tfX, W1, b1, W2, b2)

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=py_x, logits=T))

train_op = tf.train.GradientDescentOptimizer(0.05).minimize(cost)
predict_op = tf.argmax(py_x, 1)

sess = tf.Session()
inti = tf.initizalize_all_variables()

for i in range(1000):
    sess.run(train_op, feed_dict={tfX: X, tfY: T})
    pred = sess.run(predict_op, feed_dict={tfX: X, tfY: T})
    if i % 10 == 0:
        print(np.mean(Y == pred))

回溯（最近一次呼叫最后一次）：
文件“test.py”，第45行，在
列车运行=tf.列车梯度降尘器（0.05）.最小化（成本）
文件“/usr/local/lib/python3.5/dist packages/tensorflow/python/training/optimizer.py”，第322行
（[str（v）代表v，在梯度和变量中为v]，损失））
ValueError：没有为任何变量提供渐变，请检查图形中是否有不支持渐变的操作，在变量[“”、“”、“”、“”、“”]和损失张量（“平均值：0”，形状=（），数据类型=浮点64）之间。

---

不清楚我在这里要做什么。在这一点上，有人能帮我吗？

如果

T

是真正的标签，而

py_x

是网络输出，则必须切换交叉熵函数中的参数：

Traceback (most recent call last):
  File "test.py", line 45, in <module>
    train_op = tf.train.GradientDescentOptimizer(0.05).minimize(cost)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/optimizer.py", line 322, in minimize
    ([str(v) for _, v in grads_and_vars], loss))
ValueError: No gradients provided for any variable, check your graph for ops that do not support gradients, between variables ["<tf.Variable 'Variable:0' shape=(2, 3) dtype=float32_ref>", "<tf.Variable 'Variable_1:0' shape=(3,) dtype=float32_ref>", "<tf.Variable 'Variable_2:0' shape=(3, 3) dtype=float32_ref>", "<tf.Variable 'Variable_3:0' shape=(3,) dtype=float32_ref>"] and loss Tensor("Mean:0", shape=(), dtype=float64).

登录必须是网络输出，标签必须是真实标签。如果混淆参数，优化器将无法反向传播，因为没有梯度。 您还必须在培训前初始化变量；您的代码缺少sess.run（init）语句（您的

initialize\u all_variables（）

中也有一个输入错误）。 我还洗牌了你的数据；也许这会导致更快地向标签靠拢

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=T, logits=py_x))

---

它发现你应该运行

inti

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

Nclass = 500
D = 2
M = 3
K = 3

X1 = np.random.randn(Nclass, D) + np.array([0, -2])
X2 = np.random.randn(Nclass, D) + np.array([2, 2])
X3 = np.random.randn(Nclass, D) + np.array([-2, 2])
X = np.vstack ([X1, X2, X3]).astype(np.float32)
Y = np.array([0]*Nclass + [1]*Nclass + [2]*Nclass)
perm = np.random.permutation(len(X))
X = X[perm]
Y = Y[perm]


# plt.scatter(X[:,0], X[:,1], c=Y, s=100, alpha=0.5)
# plt.show()

N = len(Y)

T = np.zeros((N, K))
for i in range(N):
    T[i, Y[i]] = 1
print(T)

def init_weights(shape):
    return tf.Variable(tf.random_normal(shape, stddev=0.01))

def forward(X, W1, b1, W2, b2):
    Z = tf.nn.sigmoid(tf.matmul(X, W1) + b1)
    return tf.matmul(Z, W2) + b2

tfX = tf.placeholder(tf.float32, [None, D])
tfY = tf.placeholder(tf.float32, [None, K])

W1 = init_weights([D, M])
b1 = init_weights([M])
W2 = init_weights([M, K])
b2 = init_weights([K])

py_x = forward(tfX, W1, b1, W2, b2)

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=T, logits=py_x))

train_op = tf.train.GradientDescentOptimizer(0.1).minimize(cost)
predict_op = tf.argmax(py_x, 1)

sess = tf.Session()
init = tf.initialize_all_variables()

sess.run(init)
for i in range(1000):
    sess.run(train_op, feed_dict={tfX: X, tfY: T})
    pred = sess.run(predict_op, feed_dict={tfX: X, tfY: T})
    if i % 10 == 0:
        print(np.mean(Y == pred))

在运行

GradientDescentOptimizer

inti = tf.initialize_all_variables()
sess.run(inti)