tf.group,tf.tuple,tf.control

tf.group

tf.group( *inputs, **kwargs )

该函数就是把参数中的操作作为一个组和，把这些操作作为为一个操作 group的参数是一个一个operation,而不是一个list(这就是input前面加 * 的原因,注意一定是一个个的) return: 返回是一个op

tf.tuple

tf.tuple( tensors, name=None, control_inputs=None )

参数说明: tensors: 是一个list name: (可选) 为这个操作声明一个名字 control_inputs: 在返回之前需要完成的操作 return: 其返回的是tensors里面各个tensor组合的一个list,

tf.group 和 tf.tuple的代码例子

import tensorflow as tf w = tf.Variable(1) mul = tf.multiply(w, 2) add = tf.add(w, 2) group = tf.group(mul, add) #注意这里是一个一个的哈 tuple = tf.tuple([mul, add])#注意这里是一个list哈 sess=tf.Session() sess.run(tf.global_variables_initializer()) print(sess.run([mul,add,group,w])) print(sess.run(tuple))

输出的是:

[2, 3, None, 1] [2, 3]

tf.identity()

这是一个赋值操作, 注意这是一个op(操作) 。y=tf.identity(x) 效果等价于y=x 但是前者是一个操作,在graph中是一个op 后者在不是

tf.control_dependencies():

tf.control_dependencies()设计是用来控制计算流图的，给图中的某些计算指定顺序。 比如：我们想要获取参数更新后的值，那么我们可以这么组织我们的代码。

说一下:

control_dependencies的意义是: 在执行with包含的操作前,注意一定是操作,否则不woker:(在这里就是 updated_weight = tf.identity(weight) )前,先执行control_dependencies中的操作（在这里就是 opt）

opt = tf.train.Optimizer().minize(loss) with tf.control_dependencies([opt]):#注意书写格式 updated_weight = tf.identity(weight) with tf.Session() as sess: tf.global_variables_initializer().run()#这种书写格式只能在with里面 因为会默认找到sess sess.run(updated_weight, feed_dict={...}) # 这样每次得到的都是更新后的weight

with tf.control_dependencies()所包含的不是op时:

x = tf.Variable(0.0) x_plus_1 = tf.assign_add(x, 1) #返回一个op，表示给变量x加1的操作,这里是一个op 不是返回一个tensor with tf.control_dependencies([x_plus_1]): y = x#这仅仅是一个 赋值,不是op init = tf.global_variables_initializer() with tf.Session() as session: init.run() for i in range(5): print(y.eval())

输出:

0.0 0.0 0.0 0.0 0.0

with tf.control_dependencies()所包含的是op时:

x = tf.Variable(0.0) x_plus_1 = tf.assign_add(x, 1) #返回一个op，表示给变量x加1的操作,这里是一个op 不是返回一个tensor with tf.control_dependencies([x_plus_1]): y = x op1=tf.group(y) init = tf.global_variables_initializer() with tf.Session() as session: init.run() for i in range(5): session.run(op1) #这是一个操作,所以会执行x_plus_1将x加1 print(y.eval()) #因为x已经加1 所以y会获取x加1后的值,注意:执行这句话的时候,x_plus_1还是没执行

输出:

1.0 2.0 3.0 4.0 5.0

tensorflow实现RandomForest

# -*- encoding:utf-8 -*- import tensorflow as tf from tensorflow.python.ops import resources from tensorflow.contrib.tensor_forest.python import tensor_forest import os from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("../../mnist_data/", one_hot=False) num_steps=500 batch_size=1024 num_features=784 num_trees=10 num_classes = 10 max_nodes = 1000 X=tf.placeholder(tf.float32,shape=[None,784]) Y=tf.placeholder(tf.int32,shape=[None]) # Random Forest Parameters 随机树的参数 hparams = tensor_forest.ForestHParams(num_classes=num_classes, num_features=num_features, num_trees=num_trees, max_nodes=max_nodes).fill() forest_graph = tensor_forest.RandomForestGraphs(hparams) train_op = forest_graph.training_graph(X,Y) loss_op=forest_graph.training_loss(X,Y) infer_op,_,_ = forest_graph.inference_graph(X) correct_prediction = tf.equal(tf.argmax(infer_op,1),tf.cast(Y,tf.int64)) accuracy_op=tf.reduce_mean(tf.cast(correct_prediction,tf.float32)) init_vars=tf.group(tf.global_variables_initializer(),resources.initialize_resources(resources.shared_resources())) sess=tf.Session() sess.run(init_vars) # Training for i in range(1, num_steps + 1): # Prepare Data # Get the next batch of MNIST data (only images are needed, not labels) batch_x, batch_y = mnist.train.next_batch(batch_size) _, l = sess.run([train_op, loss_op], feed_dict={X: batch_x, Y: batch_y}) if i % 50 == 0 or i == 1: acc = sess.run(accuracy_op, feed_dict={X: batch_x, Y: batch_y}) print('Step %i, Loss: %f, Acc: %f' % (i, l, acc)) # Test Model test_x, test_y = mnist.test.images, mnist.test.labels print("Test Accuracy:", sess.run(accuracy_op, feed_dict={X: test_x, Y: test_y}))

输出:

Step 1, Loss: -1.000000, Acc: 0.431641 Step 50, Loss: -254.800003, Acc: 0.870117 Step 100, Loss: -539.599976, Acc: 0.881836 Step 150, Loss: -829.599976, Acc: 0.911133 Step 200, Loss: -1001.000000, Acc: 0.921875 Step 250, Loss: -1001.000000, Acc: 0.922852 Step 300, Loss: -1001.000000, Acc: 0.928711 Step 350, Loss: -1001.000000, Acc: 0.924805 Step 400, Loss: -1001.000000, Acc: 0.911133 Step 450, Loss: -1001.000000, Acc: 0.900391 Step 500, Loss: -1001.000000, Acc: 0.921875 Test Accuracy: 0.9204

参照博客: tensorflow学习笔记（四十一）：control dependencies 随机森林实现