我正在实现一种交替训练方案。图中包含两个训练操作。训练过程应该在这两个操作之间交替进行。
下面是一个小例子。但似乎每次都更新了这两个操作。我如何明确地在这两个操作之间交替执行？
from tensorflow.examples.tutorials.mnist import input_dataimport tensorflow as tf# 导入数据mnist = input_data.read_data_sets('/tmp/tensorflow/mnist/input_data', one_hot=True)# 创建模型x = tf.placeholder(tf.float32, [None, 784])W = tf.Variable(tf.zeros([784, 10]), name='weights')b = tf.Variable(tf.zeros([10]), name='biases')y = tf.matmul(x, W) + b# 定义损失和优化器y_ = tf.placeholder(tf.float32, [None, 10])cross_entropy = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))global_step = tf.Variable(0, trainable=False)tvars1 = [b]train_step1 = tf.train.GradientDescentOptimizer(0.5).apply_gradients(zip(tf.gradients(cross_entropy, tvars1), tvars1), global_step)tvars2 = [W]train_step2 = tf.train.GradientDescentOptimizer(0.5).apply_gradients(zip(tf.gradients(cross_entropy, tvars2), tvars2), global_step)train_step = tf.cond(tf.equal(tf.mod(global_step,2), 0), true_fn= lambda:train_step1, false_fn=lambda : train_step2)sess = tf.InteractiveSession()tf.global_variables_initializer().run()# 训练for i in range(1000): batch_xs, batch_ys = mnist.train.next_batch(100) sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys}) if i % 100 == 0: print(sess.run([cross_entropy, global_step], feed_dict={x: mnist.test.images, y_: mnist.test.labels}))结果是
[2.0890141, 2][0.38277805, 202][0.33943111, 402][0.32314575, 602][0.3113254, 802][0.3006627, 1002][0.2965056, 1202][0.29858461, 1402][0.29135355, 1602][0.29006076, 1802] 全局步骤迭代到了1802，因此每次调用train_step时都会执行两个训练操作。（例如，当总是为假的条件是tf.equal(global_step,-1)时也会发生这种情况。）
我的问题是如何交替执行train_step1和train_step2？
回答：
我认为最简单的方法是
for i in range(1000): batch_xs, batch_ys = mnist.train.next_batch(100) if i % 2 == 0: sess.run(train_step1, feed_dict={x: batch_xs, y_: batch_ys}) else: sess.run(train_step2, feed_dict={x: batch_xs, y_: batch_ys})但如果需要通过TensorFlow的条件流来进行切换，可以这样做：
optimizer = tf.train.GradientDescentOptimizer(0.5)train_step = tf.cond(tf.equal(tf.mod(global_step, 2), 0), true_fn=lambda: optimizer.apply_gradients(zip(tf.gradients(cross_entropy, tvars1), tvars1), global_step), false_fn=lambda: optimizer.apply_gradients(zip(tf.gradients(cross_entropy, tvars2), tvars2), global_step))