Question

我已经用文件.meta，.index，checkpoint和.data-0001存储了一个Tensorflow模型。我使用以下方法恢复图形和模型：

model = tf.train.import_meta_graph("models/model.meta")
model.restore(sess, tf.train.latest_checkpoint("models/"))

我恢复了一些变量，如权重和偏差，但我还需要恢复损失函数。我的模型正在使用nce_loss。本质上，在给定特定输入的情况下，我想获取损失函数的梯度，而不必重新定义损失变量，只需从还原版本调用操作即可。所以：

loss = graph.get_operation_by_name("loss")
grads = tf.gradients(loss,loss.inputs)

在这里，我收到以下错误消息：

File "/tmp/fgsm.py", line 114, in main
    grads = tf.gradients(loss,loss.inputs)
  File "/tmp/venv/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py", line 630, in gradients
    gate_gradients, aggregation_method, stop_gradients)
  File "/tmp/venv/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py", line 675, in _GradientsHelper
    ys = ops.convert_n_to_tensor_or_indexed_slices(ys, name="y")
  File "/tmp/venv/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1377, in convert_n_to_tensor_or_indexed_slices
    values=values, dtype=dtype, name=name, as_ref=False)
  File "/tmp/venv/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1348, in internal_convert_n_to_tensor_or_indexed_slices
    value, dtype=dtype, name=n, as_ref=as_ref))
  File "/tmp/venv/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1307, in internal_convert_to_tensor_or_indexed_slices
    value, dtype=dtype, name=name, as_ref=as_ref)
  File "/tmp/venv/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1146, in internal_convert_to_tensor
    ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
  File "/tmp/venv/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 6168, in _operation_conversion_error
    name, as_ref))
TypeError: Can't convert Operation 'loss' to Tensor (target dtype=None, name='y_0', as_ref=False)

我在这里做什么错了？

编辑：

所以切换到

loss = graph.get_tensor_by_name("loss:0")

我可以成功获得损失张量。现在，在给定恢复损失函数的情况下，如何获得输入的梯度？ nce_loss有一个“输入”参数，我想给定损失函数和输入参数来计算梯度。我该如何使用tf.gradients？我tf.gradients(loss,loss.inputs)遇到错误

AttributeError: 'Tensor' object has no attribute 'inputs'

Answer 1

从tensorflow检索张量时，必须对其进行索引。在您的代码中：

loss = graph.get_operation_by_name("loss")
grads = tf.gradients(loss,loss.inputs)

由于错误状态，您正在获取损失而不是其输出张量的运算。要检索其张量，您可以像这样对操作进行索引：

loss = graph.get_operation_by_name("loss:0")
grads = tf.gradients(loss,loss.inputs)

从恢复的张量流模型中获取“损失”功能

1 个答案: