Python TensorFlow：如何重用Adam优化器变量？

最近升级了TensorFlow版本后，我遇到了无法解决的错误：

Traceback (most recent call last):
  File "cross_train.py", line 177, in <module>
    train_network(use_gpu=True)
  File "cross_train.py", line 46, in train_network
    with tf.control_dependencies([s_opt.apply_gradients(s_grads), s_increment_step]):

...

ValueError: Variable image-conv1-layer/weights/Adam/ already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at:

  File "cross_train.py", line 34, in train_network
    with tf.control_dependencies([e_opt.apply_gradients(e_grads), e_increment_step]):
  File "cross_train.py", line 177, in <module>
    train_network(use_gpu=True)

---

但我不确定我是否能为亚当做同样的事。有什么想法吗？非常感谢您的帮助。

事实证明，我不需要实例化两个不同的Adam优化器。我只创建了一个实例，没有名称冲突或试图共享变量的问题。无论更新哪个网络分支，我都使用相同的优化器：

    e_grads = opt.compute_gradients(e_loss)
with tf.control_dependencies([opt.apply_gradients(e_grads), e_increment_step]):
    e_train = tf.no_op(name='english_train') 

而且

    s_grads = opt.compute_gradients(s_loss)
with tf.control_dependencies([opt.apply_gradients(s_grads), s_increment_step]):
    s_train = tf.no_op(name='spanish_train')

---

有趣的是，对于旧版本的Tensorflow，使用两个Adam实例没有问题，即使M分支名称冲突…

您为优化操作设置了名称吗<代码>优化器=tf.train.AdamOptimizer（学习率=0.0001，name='first''优化器'）。最小化（损失）

    s_grads = opt.compute_gradients(s_loss)
with tf.control_dependencies([opt.apply_gradients(s_grads), s_increment_step]):
    s_train = tf.no_op(name='spanish_train')