Question

我需要随着时间的推移获得损失历史记录，以图形方式绘制它。这是我的代码框架：

optimizer = tf.contrib.opt.ScipyOptimizerInterface(loss, method='L-BFGS-B', 
options={'maxiter': args.max_iterations, 'disp': print_iterations})
optimizer.minimize(sess, loss_callback=append_loss_history)

使用append_loss_history定义：

def append_loss_history(**kwargs):
    global step
    if step % 50 == 0:
        loss_history.append(loss.eval())
    step += 1

当我看到ScipyOptimizerInterface的详细输出时，损失实际上随着时间的推移而减少。但是当我打印loss_history时，随着时间的推移损失几乎相同。

参考文档：＆＃34;受优化影响的变量在优化结束时就地更新＆＃34; https://www.tensorflow.org/api_docs/python/tf/contrib/opt/ScipyOptimizerInterface。这是损失不变的原因吗？

Answer 1

我认为你有问题;变量本身在优化结束之前不会被修改（而是being fed to session.run calls），并评估＆＃34;反向通道＆＃34; Tensor获取未修改的变量。相反，使用fetches optimizer.minimize参数来搭载指定了Feed的session.run个调用：

import tensorflow as tf

def print_loss(loss_evaled, vector_evaled):
  print(loss_evaled, vector_evaled)

vector = tf.Variable([7., 7.], 'vector')
loss = tf.reduce_sum(tf.square(vector))

optimizer = tf.contrib.opt.ScipyOptimizerInterface(
    loss, method='L-BFGS-B',
    options={'maxiter': 100})

with tf.Session() as session:
  tf.global_variables_initializer().run()
  optimizer.minimize(session,
                     loss_callback=print_loss,
                     fetches=[loss, vector])
  print(vector.eval())

（从example in the documentation修改）。这将使用更新的值打印Tensors：

98.0 [ 7.  7.]
79.201 [ 6.29289341  6.29289341]
7.14396e-12 [ -1.88996808e-06  -1.88996808e-06]
[ -1.88996808e-06  -1.88996808e-06]

如何使用tf.contrib.opt.ScipyOptimizerInterface获取损失函数历史记录

1 个答案: