如何在get_集合中使用tensorflow占位符

所以，我对feed变量有一些问题。我想冻结我的模型的权重和偏差。我有下一个变量：

wc1 = tf.Variable(tf.random_normal([f1, f1, _channel, n1], mean=0, stddev=0.01), name="wc1")
wc2 = tf.Variable(tf.random_normal([f2, f2, n1, n2], mean=0, stddev=0.01), name="wc2")
wc3 = tf.Variable(tf.random_normal([f3, f3, n2, _channel], mean=0, stddev=0.01), name="wc3") 

bc1 = tf.Variable(tf.random_normal(shape=[n1], mean=0, stddev=0.01), name="bc1")
bc2 = tf.Variable(tf.random_normal(shape=[n2], mean=0, stddev=0.01), name="bc2")
bc3 = tf.Variable(tf.random_normal(shape=[_channel], mean=0, stddev=0.01), name="bc3")

例如，我希望在前10个历元上训练[wc1，bc1]，然后在下一个历元上训练[wc2，bc2]，依此类推。为此，我创建了变量集合：

tf.add_to_collection('wc1', wc1)
tf.add_to_collection('wc1', bc1)

tf.add_to_collection('wc2', wc2)
tf.add_to_collection('wc2', bc2)

并为集合名称创建占位符：

trainable_name = tf.placeholder(tf.string, shape=[])

接下来，我尝试在优化器中获取它：

opt = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
train_op = opt.minimize(cost, var_list=tf.get_collection(trainable_name))

提要数据：

sess.run(train_op, feed_dict={ ... , trainable_name: "wc1"})

我得到一个错误：

 Traceback (most recent call last):
  File "/home/keeper121/PycharmProjects/super/sp_train.py", line 292, in <module>
    train(tiles_names, "model.ckpt")
  File "/home/keeper121/PycharmProjects/super/sp_train.py", line 123, in train
    train_op = opt.minimize(cost, var_list=tf.get_collection(trainable_name))
  File "/home/keeper121/anaconda/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/training/optimizer.py", line 193, in minimize
    grad_loss=grad_loss)
  File "/home/keeper121/anaconda/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/training/optimizer.py", line 244, in compute_gradients
    raise ValueError("No variables to optimize")
ValueError: No variables to optimize

回溯（最近一次呼叫最后一次）：
文件“/home/keeper121/PycharmProjects/super/sp_train.py”，第292行，在
列车（瓷砖名称，“model.ckpt”）
文件“/home/keeper121/PycharmProjects/super/sp_train.py”，第123行，列车内
训练操作=选择最小化（成本、变量列表=tf.获取集合（可训练名称））
文件“/home/keeper121/anaconda/envs/tensorflow/lib/python2.7/site packages/tensorflow/python/training/optimizer.py”，第193行
梯度损失=梯度损失）
文件“/home/keeper121/anaconda/envs/tensorflow/lib/python2.7/site packages/tensorflow/python/training/optimizer.py”，第244行，计算梯度
raise VALUERROR（“无需优化的变量”）
ValueError：没有要优化的变量

那么，有什么方法可以在训练期间改变训练变量呢

---

谢谢。

尝试以下方法：

train_op_wc1 = opt.minimize(cost, var_list=tf.get_collection("wc1"))
train_op_wc2 = opt.minimize(cost, var_list=tf.get_collection("wc2"))

然后，当您输入数据时：

#define your samples as you would always do
input_feed = ...
#then use the training op that addresses the correct layers, as you defined above
if first_10_epoch:
  sess.run(train_op_wc1, feed_dict=input_feed)
else:
  sess.run(train_op_wc2, feed_dict=input_feed)