如何在TensorFlow 2中获得学习阶段？

Question

K.learning_phase()获取值，而不是张量本身。我需要学习阶段张量反馈到K.function以获得层梯度、输出等。在import keras.backend as K工作正常，但在import tensorflow.keras.backend as K工作失败。 Relevant Git带部分解决方法

如何提取张量本身？你知道吗

---

可复制示例：

import tensorflow.keras.backend as K
from tensorflow.keras.layers import Input, Dense
from tensorflow.keras.models import Model
import numpy as np

ipt = Input((16,))
out = Dense(16)(ipt)
model = Model(ipt, out)
model.compile('adam', 'mse')

x = np.random.randn(32, 16)
model.train_on_batch(x, x)

grads = model.optimizer.get_gradients(model.total_loss, model.layers[-1].output)
grads_fn = K.function(inputs=[model.inputs[0], model._feed_targets[0], K.learning_phase()], 
                      outputs=grads)

完整错误跟踪：

File "<ipython-input-2-7f74922d7492>", line 3, in <module>
  outputs=grads)
File "D:\Anaconda\envs\tf2_env\lib\site-packages\tensorflow_core\python\keras\backend.py", line 3773, in function
  return EagerExecutionFunction(inputs, outputs, updates=updates, name=name)
File "D:\Anaconda\envs\tf2_env\lib\site-packages\tensorflow_core\python\keras\backend.py", line 3670, in __init__
  base_graph=source_graph)
File "D:\Anaconda\envs\tf2_env\lib\site-packages\tensorflow_core\python\eager\lift_to_graph.py", line 249, in lift_to_graph
  visited_ops = set([x.op for x in sources])
File "D:\Anaconda\envs\tf2_env\lib\site-packages\tensorflow_core\python\eager\lift_to_graph.py", line 249, in <listcomp>
  visited_ops = set([x.op for x in sources])

AttributeError: 'int' object has no attribute 'op'

Answer 1

作为一种（不太好的）解决方法，您可以使用symbolic_learning_phase()from tensorflow.python.keras.backend：

from tensorflow.python.keras import backend

# ...
grads_fn = K.function(inputs=[model.inputs[0],
                              model._feed_targets[0],
                              backend.symbolic_learning_phase()], 
                      outputs=grads)

g_learning = grads_fn([x, x, True])
g_not_learning = grads_fn([x, x, False])

我不知道为什么这个函数不像learning_phase()，没有被导出到tensorflow.keras.backend。也许有一个很好的理由不这样做。你知道吗

此外，请注意，仅当您的模型包含在训练和推理模式中表现不同的层/操作（例如退出）时，在此处使用学习阶段才有意义。否则，函数的输出将是相同的。你知道吗