擅长:python、mysql、java
<p>正如您在问题中提到的,实现这一点的最简单方法是使用对<code>opt.minimize(cost, ...)</code>的单独调用创建两个优化器操作。默认情况下,优化器将使用<a href="https://www.tensorflow.org/versions/master/api_docs/python/state_ops.html#trainable_variables">^{<cd2>}</a>中的所有变量。如果要将变量筛选到特定作用域,可以按如下所示对<a href="https://www.tensorflow.org/versions/master/api_docs/python/framework.html#get_collection">^{<cd4>}</a>使用可选的<code>scope</code>参数:</p>
<pre><code>optimizer = tf.train.AdagradOptimzer(0.01)
first_train_vars = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES,
"scope/prefix/for/first/vars")
first_train_op = optimizer.minimize(cost, var_list=first_train_vars)
second_train_vars = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES,
"scope/prefix/for/second/vars")
second_train_op = optimizer.minimize(cost, var_list=second_train_vars)
</code></pre>