Question

这是我的第一个效果很好的代码。

输入是2维，输出是2维

第一个代码：

w = tf.Variable(tf.zeros([2,1]))
b = tf.Variable(tf.zeros([1]))


x = tf.placeholder(tf.float32,shape=[None,2])
t = tf.placeholder(tf.float32,shape=[None,1])
y = tf.nn.sigmoid(tf.matmul(x,w) + b)

cross_entropy = - tf.reduce_sum(t * tf.log(y) + (1-t) * 
                                tf.log(1 -y))
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(cross_entropy)
correct_prediction = tf.equal(tf.to_float(tf.greater(y,0.5)),t)


X = np.array([[0,0],[0,1],[1,0],[1,1]])
Y = np.array([[0],[1],[1],[1]])

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

for epoch in range(200):
    sess.run(train_step,feed_dict={
        x:X,
        t:Y
    })

现在我想将其扩展到10维输入和2维输出。

然后我改变如下，但它显示错误。我知道这个错误与占位符的大小有关我应该在哪里改变？为什么???

Traceback (most recent call last):
  File "wisdom2.py", line 57, in <module>
    t: Y
  File "/Users/whitebear/tensorflow/lib/python3.4/site-packages/tensorflow/python/client/session.py", line 789, in run
    run_metadata_ptr)
  File "/Users/whitebear/tensorflow/lib/python3.4/site-packages/tensorflow/python/client/session.py", line 975, in _run
    % (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (5, 1) for Tensor 'Placeholder:0', which has shape '(?, 10)'

第二代码：

w = tf.Variable(tf.zeros([10,1])) ## change dimensions to 2 -> 10
b = tf.Variable(tf.zeros([1]))

x = tf.placeholder(tf.float32,shape=[None,10]) # change dimensions to 2 -> 10
t = tf.placeholder(tf.float32,shape=[None,1])
y = tf.nn.sigmoid(tf.matmul(x,w) + b)

cross_entropy = - tf.reduce_sum(t * tf.log(y) + (1 -t) * tf.log(1 -y))
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(cross_entropy)
correct_prediction = tf.equal(tf.to_float(tf.greater(y,0.5)),t)

##I changed here....
X = np.array([[0],[1],[0],[1],[1]]) #answer
Y = np.array([
[2,-2,3,-4,2,2,3,5,3,6],  
[1,3,-3,2,2,5,1,3,2,3],   
[-2,3,2,-2,2,-2,1,3,4,5],   
[-2,2,-1,-2,2,-2,7,3,9,2],   
[-2,-3,2,-2,2,-4,1,-4,4,5]   
])


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

for epoch in range(200):
    sess.run(train_step,feed_dict={
        x: X,
        t: Y
    })

Answer 1

您正在输入错误的形状作为placeholders的输入。您已在占位符中更改了x的维度，但却输入错误的输入X（您尚未更改），而不是y（您已更改）。因此，要么交换X，要么更改相应的placeholders

只需将输入层的维数从2改为10即可

1 个答案: