如何使用tensorflow占位符在get_collection中使用

所以，我有一些饲料变量的问题。我想冻结我的模型在时代的权重和偏见。我有下一个变量：如何使用tensorflow占位符在get_collection中使用

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")

例如欲训练[WC1，BC1]在第一个10时期，然后[WC2，BC2]未来历元等。为了这个目的，我创建的变量集合：

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

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

而对于集合名称创建占位符：

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

接下来，我尝试把它在我的优化：

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

饲料数据：

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

而我ge t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

那么，任何方式来改变会话的训练变量？

感谢。

来源

2016-08-02 keeper121

给下面的一个尝试：

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

然后当你喂的数据：

#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)

来源

2016-08-02 13:01:05 friesel

如何使用tensorflow占位符在get_collection中使用

回答

相关问题