Question

我读过许多张量流的初学者书并制作了这段代码。这只需要N维数据并输出1维。

它很有魅力!!

现在，我想为此添加隐藏图层，但是我无法创建它并找到简单的教程或示例来了解如何添加隐藏图层。

有良好的做法或想法吗？要么 “为此样本添加隐藏层”是进一步学习的正确方法???

tf.set_random_seed(0)
N = 10

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

x = tf.placeholder(tf.float32,shape=[None,N]) 
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)


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

for epoch in range(2000):
    sess.run(train_step,feed_dict={
        x: X,
        t: Y
    })

classified = correct_prediction.eval(session=sess,feed_dict={
    x:X,
    t:Y
    })

print(classified)

prob = y.eval(session=sess ,feed_dict={
    x:X,
    t:Y
})
print(prob)

print('w:',sess.run(w))
print('b:',sess.run(b))

Answer 1

您的隐藏图层将位于输入和输出图层之间，因此输入隐藏图层将通过尺寸[input_size, hidden_size]的权重连接，隐藏输出图层将通过尺寸[hidden_size, output_size]的权重连接。并且每一层都会有激活。

您的代码应如下所示：

N = 10
n_hidden = 20
# dont initialise weights to zero but to a small number
w_h = tf.Variable(tf.truncated_normal([N,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,N]) 
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

#remove sigmoid from last layer and use the stable implementation:
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)

Answer 2

为什么不使用tf.layers？

N = 10
n_hidden = 20

x = tf.placeholder(tf.float32,shape=[None,N])
t = tf.placeholder(tf.float32,shape=[None,1])

layer1 = tf.layers.dense(x,n_hidden,tf.nn.relu)
y = tf.layers.dense(layer1,1)

添加更多图层会改变上述内容：

N = 10
n_hidden_1 = 20
n_hidden_2 = 25

x = tf.placeholder(tf.float32,shape=[None,N])
t = tf.placeholder(tf.float32,shape=[None,1])

layer1 = tf.layers.dense(x,n_hidden_1,tf.nn.relu)
layer2 = tf.layers.dense(layer1,n_hidden_2,tf.nn.relu)
y = tf.layers.dense(layer1,1)

将隐藏层添加到第一个简单的神经网络

2 个答案: