tf.keras get computed gradient during training

Question

Following what is written here I was trying to get the computed gradient during the training using tf.keras, I've end up with the following callback function which is called during the fitting's phase:

The used networks is a very standard one, fully connected and sequential.

r = network.fit(x=trn.X,y=trn.Y,verbose=2,batch_size=50,epochs=50,callbacks=[reporter,])

def on_train_begin(self, logs={}):

    # Functions return weights of each layer
    self.layerweights = []
    for lndx, l in enumerate(self.model.layers):
        if hasattr(l, 'kernel'):
            self.layerweights.append(l.kernel)

    input_tensors = [self.model.inputs[0],
                     self.model.sample_weights[0],
                     self.model.targets[0],
                     K.learning_phase()]

    # Get gradients of all the relevant layers at once
    grads = self.model.optimizer.get_gradients(self.model.total_loss, self.layerweights)
    self.get_gradients = K.function(inputs=input_tensors,outputs=grads) # <-- Error Here

which rise the following Error Message:

~\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\eager\lift_to_graph.py in (.0)
    312   # Check that the initializer does not depend on any placeholders.
    313   sources = set(sources or [])
--> 314   visited_ops = set([x.op for x in sources])
    315   op_outputs = collections.defaultdict(set)
    316 

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

Any idea how to resolve it? Already read this one, and this one, but got no luck

Answer 1

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

means that you have a objects or attributes got None.
To handle it you can use this:

visited_ops = set([x.op for x in sources if x])

Answer 2

Resolved the issue using an older version of keras(v. 2.2.4) and tensorflow (1.13.1) on python 3.6.9.