![](/img/trans.png)
[英]Getting the gradients of multiple outputs in TensorFlow and not their addition
[英]Getting the opposite outputs from Tensorflow learn with OR gate
给定DNN(多层感知器的简单情况),分别具有5个和3个维度的2个隐藏层,我正在训练一个模型来识别“或”门。
使用张量流学习,似乎给了我反向输出,我不知道为什么:
from tensorflow.contrib import learn
classifier = learn.DNNClassifier(hidden_units=[5, 3], n_classes=2)
or_input = np.array([[0.,0.], [0.,1.], [1.,0.]])
or_output = np.array([[0,1,1]]).T
classifier.fit(or_input, or_output, steps=0.05, batch_size=3)
classifier.predict(np.array([ [1., 1.], [1., 0.] , [0., 0.] , [0., 1.]]))
[OUT]:
array([0, 0, 1, 0])
如果我是“老派”,没有tensorflow.learn
按照以下说明进行操作。
import tensorflow as tf
# Parameters
learning_rate = 1.0
num_epochs = 1000
# Network Parameters
input_dim = 2 # Input dimensions.
hidden_dim_1 = 5 # 1st layer number of features
hidden_dim_2 = 3 # 2nd layer number of features
output_dim = 1 # Output dimensions.
# tf Graph input
x = tf.placeholder("float", [None, input_dim])
y = tf.placeholder("float", [hidden_dim_2, output_dim])
# With biases.
weights = {
'syn0': tf.Variable(tf.random_normal([input_dim, hidden_dim_1])),
'syn1': tf.Variable(tf.random_normal([hidden_dim_1, hidden_dim_2])),
'syn2': tf.Variable(tf.random_normal([hidden_dim_2, output_dim]))
}
biases = {
'b0': tf.Variable(tf.random_normal([hidden_dim_1])),
'b1': tf.Variable(tf.random_normal([hidden_dim_2])),
'b2': tf.Variable(tf.random_normal([output_dim]))
}
# Create a model
def multilayer_perceptron(X, weights, biases):
# Hidden layer 1 + sigmoid activation function
layer_1 = tf.add(tf.matmul(X, weights['syn0']), biases['b0'])
layer_1 = tf.nn.sigmoid(layer_1)
# Hidden layer 2 + sigmoid activation function
layer_2 = tf.add(tf.matmul(layer_1, weights['syn1']), biases['b1'])
layer_2 = tf.nn.sigmoid(layer_2)
# Output layer
out_layer = tf.matmul(layer_2, weights['syn2']) + biases['b2']
out_layer = tf.nn.sigmoid(out_layer)
return out_layer
# Construct model
pred = multilayer_perceptron(x, weights, biases)
# Define loss and optimizer
cost = tf.sub(y, pred)
# Or you can use fancy cost like:
##tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
init = tf.initialize_all_variables()
or_input = np.array([[0.,0.], [0.,1.], [1.,0.]])
or_output = np.array([[0.,1.,1.]]).T
# Launch the graph
with tf.Session() as sess:
sess.run(init)
# Training cycle
for epoch in range(num_epochs):
batch_x, batch_y = or_input, or_output # Loop over all data points.
# Run optimization op (backprop) and cost op (to get loss value)
_, c = sess.run([optimizer, cost], feed_dict={x: batch_x, y: batch_y})
#print (c)
# Now let's test it on the unknown dataset.
new_inputs = np.array([[1.,1.], [1.,0.]])
feed_dict = {x: new_inputs}
predictions = sess.run(pred, feed_dict)
print (predictions)
[OUT]:
[[ 0.99998868]
[ 0.99998868]]
为什么我使用tensorflow.learn
得到反向输出? 我使用tensorflow.learn
什么吗?
如何获取tensorflow.learn
代码以产生与“老式” tensorflow框架相同的输出?
如果为steps
指定正确的参数,则会得到良好的结果:
classifier.fit(or_input, or_output, steps=1000, batch_size=3)
结果:
array([1, 1, 0, 1])
steps
如何运作 steps
参数指定您运行训练操作的次数。 让我给你举一些例子:
batch_size = 16
和steps = 10
,您将看到总共160
示例 batch_size = 3
而steps = 1000
,该算法将看到3000
示例。 实际上,它将看到与您提供的3个示例相同的1000倍 因此, steps
数不是纪元数,而是您运行训练操作的次数或看到新批次的次数。
steps = 0.05
? 在tf.learn
代码中,它们不检查steps
是否为整数。 他们只是运行一会儿循环检查(在此行 ):
last_step < max_steps
因此,如果max_steps = 0.05
,则其行为将与max_steps = 1
(在循环last_step
递增)相同。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.