TypeError：“NoneType”对象在 train_on_batch 中不可调用

Question

我正在 Google Colab 上从事与 GAN 相关的 .ipynb 项目。首先我得到了错误

AttributeError: module 'tensorflow' has no attribute 'log' 我将 tf.log 切换到 tf.math.log 来修复它，但遇到了以下问题。会不会是版本问题？我认为这不是我的代码造成的。

<ipython-input-54-3d3644f6e96d> in <module>()
      1 
----> 2 train(d_model, g_model, gan_model, [blue_sketch, blue_photo], 'Models/Pixel[02]_Context[08]/', n_epochs = 100, n_batch=16)

3 frames
<ipython-input-53-b838163ed04b> in train(d_model, g_model, gan_model, data, target_dir, n_epochs, n_batch)
     33 
     34             # update the generator
---> 35             g_loss, _, _ = gan_model.train_on_batch(X_realA, [y_real, X_realB])
     36 
     37             # summarize performance

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in train_on_batch(self, x, y, sample_weight, class_weight, reset_metrics, return_dict)
   1725                                                     class_weight)
   1726       self.train_function = self.make_train_function()
-> 1727       logs = self.train_function(iterator)
   1728 
   1729     if reset_metrics:

/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
    826     tracing_count = self.experimental_get_tracing_count()
    827     with trace.Trace(self._name) as tm:
--> 828       result = self._call(*args, **kwds)
    829       compiler = "xla" if self._experimental_compile else "nonXla"
    830       new_tracing_count = self.experimental_get_tracing_count()

/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
    853       # In this case we have created variables on the first call, so we run the
    854       # defunned version which is guaranteed to never create variables.
--> 855       return self._stateless_fn(*args, **kwds)  # pylint: disable=not-callable
    856     elif self._stateful_fn is not None:
    857       # Release the lock early so that multiple threads can perform the call

TypeError: 'NoneType' object is not callable

Answer 1

tf.log 已切换为tf.math.log。

我想这可能是避免与 .logging 混淆的一种方式。

再次检查您使用的版本是否正确。