SDNE,'NoneType' object is not callable

[orderer0001]

error during training：
model.train(batch_size=1024,epochs=3,verbose=2)
Traceback (most recent call last):
File "/opt/homebrew/Caskroom/miniforge/base/envs/tensorflow24/lib/python3.8/site-packages/IPython/core/interactiveshell.py", line 3457, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "", line 1, in
model.train(batch_size=1024,epochs=3,verbose=2)
File "/opt/homebrew/Caskroom/miniforge/base/envs/tensorflow24/lib/python3.8/site-packages/ge/models/sdne.py", line 129, in train
A_train = self.A[index, :].todense()
File "/opt/homebrew/Caskroom/miniforge/base/envs/tensorflow24/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py", line 1854, in train_on_batch
logs = self.train_function(iterator)
File "/opt/homebrew/Caskroom/miniforge/base/envs/tensorflow24/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 885, in call
result = self._call(*args, **kwds)
File "/opt/homebrew/Caskroom/miniforge/base/envs/tensorflow24/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 917, in _call
return self._stateless_fn(*args, **kwds) # pylint: disable=not-callable
TypeError: 'NoneType' object is not callable

Does anyone have experience with this problem?

[shenweichen]

Fixed by #83.

SDNE training now uses public tensorflow.keras APIs, TensorFlow-native loss operations, explicit array inputs/targets, and updated batch training behavior. Closing this as resolved; please open a new issue if the error still appears in a supported Python/TensorFlow combination.