TypeError: Tensor is unhashable. Instead, use tensor.ref() as the key. in Keras Surgeon

Question

我在 pruning.I 使用 Kerassurgeon 模块时遇到这个错误，而我在 google 中使用 VGG-16 colab.It 对其他 models.Can 人来说工作正常帮我解决这个问题。

---> 17   model_new = surgeon.operate()<br>
     18   return model_new

>>/usr/local/lib/python3.6/dist-packages/kerassurgeon/surgeon.py in operate(self)
    152             sub_output_nodes = utils.get_node_inbound_nodes(node)
    153             outputs, output_masks = self._rebuild_graph(self.model.inputs,
--> 154                                                         sub_output_nodes)
    155 
    156             # Perform surgery at this node

>>/usr/local/lib/python3.6/dist-packages/kerassurgeon/surgeon.py in _rebuild_graph(self, graph_inputs, output_nodes, graph_input_masks)
    264         # Call the recursive _rebuild_rec method to rebuild the submodel up to
    265         # each output layer
--> 266         outputs, output_masks = zip(*[_rebuild_rec(n) for n in output_nodes])
    267         return outputs, output_masks
    268 

>>/usr/local/lib/python3.6/dist-packages/kerassurgeon/surgeon.py in <listcomp>(.0)
    264         # Call the recursive _rebuild_rec method to rebuild the submodel up to
    265         # each output layer
--> 266         outputs, output_masks = zip(*[_rebuild_rec(n) for n in output_nodes])
    267         return outputs, output_masks
    268 

>>/usr/local/lib/python3.6/dist-packages/kerassurgeon/surgeon.py in _rebuild_rec(node)
    216             # Check for replaced tensors before any other checks:
    217             # these are created by the surgery methods.
--> 218             if node_output in self._replace_tensors.keys():
    219                 logging.debug('bottomed out at replaced output: {0}'.format(
    220                     node_output))

>>/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py in __hash__(self)
    724     if (Tensor._USE_EQUALITY and executing_eagerly_outside_functions() and
    725         (g is None or g.building_function)):
--> 726       raise TypeError("Tensor is unhashable. "
    727                       "Instead, use tensor.ref() as the key.")
    728     else:

**TypeError: Tensor is unhashable. Instead, use tensor.ref() as the key.**

Answer 1

我解决了这个错误。这是由于 versions.Use Kerassurgeon 而不是 tfkerassurgeon 的变化。

使用以下版本

tf 1.x , keras > 2.2 , kerassurgeon

Answer 2

我在尝试Deep learning example with GradientExplainer时解决了类似的问题。这是版本不兼容造成的。
添加以下代码可能会有所帮助：

import tensorflow.compat.v1.keras.backend as K
import tensorflow as tf
tf.compat.v1.disable_eager_execution()

tf 版本为 2.3.1
kerase 版本是 2.4.0
Shap 版本为 0.36

Answer 3

我遇到了类似的问题，我已经使用下一行解决了它：

import tensorflow.compat.v1.keras.backend as K
import tensorflow as tf
tf.compat.v1.disable_eager_execution()

Answer 4

请尝试以下代码：

import tensorflow.compat.v1.keras.backend as K
import tensorflow as tf
tf.compat.v1.disable_eager_execution()

1.compat 允许您编写同时适用于 TensorFlow 1.x 和 2 的代码，并且应该根据 版本导入 .

解决任何错误

2.eager_execution是一调用就可以操作的接口来自 Python。开启它可以让 Tensorflow 更加直观。

3.But 那为什么要禁用 eager_execution？
->eager_execution 比 graph_execution 慢。它逐行运行操作这使得潜在的加速机会变得毫无用处。

4.Run tf.executing_eagerly() 检查 eager_execution 是打开还是关闭。

希望这有助于减轻您的错误。

TypeError: Tensor is unhashable. Instead, use tensor.ref() as the key. in Keras Surgeon

TypeError: Tensor is unhashable. Instead, use tensor.ref() as the key. in Keras Surgeon

keras

tf.keras

vgg-net

pruning