AttributeError: 'tuple' object has no attribute 'layer' when using ActivationsVisualizationCallback

Hi, I am getting the same error.
**print(tf.__version__)**:

2.0

**print(tf.keras.__version__)**

2.2.4-tf

I have tensorflow-gpu installed. I am getting this error when I run the following code:

import tf_explain
from tf_explain.callbacks.activations_visualization import ActivationsVisualizationCallback

callbacks = [
    ActivationsVisualizationCallback(validation_data=(x_val, y_val),
                                     layers_name=["hidden_layer_1"],
        output_dir="/home/raov/Desktop/Share/uni_freiburg/Datasets",
    ),
]


model.fit(x= x_train, y = y_train, batch_size=2, epochs=2, verbose= 1, callbacks=callbacks, validation_data= (x_val, y_val))

I guess it has something to do with the callback function. The source of the above code is https://github.com/sicara/tf-explain

Please note, that I tried model.fit with and without the validation data. Both the times I get the same error, so it has nothing to do with the validation data I guess

I did see the answer from the similar post "AttributeError: 'tuple' object has no attribute 'layer' #478". It didn't help me

Any idea how to solve this problem?

Output

Train on 40000 samples, validate on 10000 samples
Epoch 1/2
40000/40000 [==============================] - 245s 6ms/step - loss: 0.7130 - accuracy: 0.8195 - val_loss: 0.6355 - val_accuracy: 0.8540

Traceback

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-49-9049e3b5856c> in <module>
     36 
     37 
---> 38 model.fit(x= x_train, y = y_train, batch_size=2, epochs=2, verbose= 1, callbacks=callbacks, validation_data= (x_val, y_val))

~/.virtualenvs/deep_learning/lib/python3.6/site-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
   1237                                         steps_per_epoch=steps_per_epoch,
   1238                                         validation_steps=validation_steps,
-> 1239                                         validation_freq=validation_freq)
   1240 
   1241     def evaluate(self,

~/.virtualenvs/deep_learning/lib/python3.6/site-packages/keras/engine/training_arrays.py in fit_loop(model, fit_function, fit_inputs, out_labels, batch_size, epochs, verbose, callbacks, val_function, val_inputs, shuffle, initial_epoch, steps_per_epoch, validation_steps, validation_freq)
    214                         epoch_logs['val_' + l] = o
    215 
--> 216         callbacks.on_epoch_end(epoch, epoch_logs)
    217         if callbacks.model.stop_training:
    218             break

~/.virtualenvs/deep_learning/lib/python3.6/site-packages/keras/callbacks/callbacks.py in on_epoch_end(self, epoch, logs)
    150         logs = logs or {}
    151         for callback in self.callbacks:
--> 152             callback.on_epoch_end(epoch, logs)
    153 
    154     def on_train_batch_begin(self, batch, logs=None):

~/.virtualenvs/deep_learning/lib/python3.6/site-packages/tf_explain/callbacks/activations_visualization.py in on_epoch_end(self, epoch, logs)
     48         """
     49         explainer = ExtractActivations()
---> 50         grid = explainer.explain(self.validation_data, self.model, self.layers_name)
     51 
     52         # Using the file writer, log the reshaped image.

~/.virtualenvs/deep_learning/lib/python3.6/site-packages/tf_explain/core/activations.py in explain(self, validation_data, model, layers_name)
     29             np.ndarray: Grid of all the activations
     30         """
---> 31         activations_model = self.generate_activations_graph(model, layers_name)
     32 
     33         predictions = activations_model.predict(

~/.virtualenvs/deep_learning/lib/python3.6/site-packages/tf_explain/core/activations.py in generate_activations_graph(model, layers_name)
     53         """
     54         outputs = [layer.output for layer in model.layers if layer.name in layers_name]
---> 55         activations_model = tf.keras.models.Model(model.inputs, outputs=outputs)
     56         activations_model.compile(optimizer="sgd", loss="categorical_crossentropy")
     57 

~/.virtualenvs/deep_learning/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training.py in __init__(self, *args, **kwargs)
    144 
    145   def __init__(self, *args, **kwargs):
--> 146     super(Model, self).__init__(*args, **kwargs)
    147     _keras_api_gauge.get_cell('model').set(True)
    148     # initializing _distribution_strategy here since it is possible to call

~/.virtualenvs/deep_learning/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/network.py in __init__(self, *args, **kwargs)
    165         'inputs' in kwargs and 'outputs' in kwargs):
    166       # Graph network
--> 167       self._init_graph_network(*args, **kwargs)
    168     else:
    169       # Subclassed network

~/.virtualenvs/deep_learning/lib/python3.6/site-packages/tensorflow_core/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
    455     self._self_setattr_tracking = False  # pylint: disable=protected-access
    456     try:
--> 457       result = method(self, *args, **kwargs)
    458     finally:
    459       self._self_setattr_tracking = previous_value  # pylint: disable=protected-access

~/.virtualenvs/deep_learning/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/network.py in _init_graph_network(self, inputs, outputs, name, **kwargs)
    271 
    272     self._base_init(name=name, **kwargs)
--> 273     self._validate_graph_inputs_and_outputs()
    274 
    275     # A Network does not create weights of its own, thus it is already

~/.virtualenvs/deep_learning/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/network.py in _validate_graph_inputs_and_outputs(self)
   1284       # Check that x is an input tensor.
   1285       # pylint: disable=protected-access
-> 1286       layer = x._keras_history.layer
   1287       if len(layer._inbound_nodes) > 1 or (
   1288           layer._inbound_nodes and layer._inbound_nodes[0].inbound_layers):

AttributeError: 'tuple' object has no attribute 'layer'

Start with the traceback entries in tf_explain/callbacks/activations_visualization.py and tf_explain/core/activations.py, especially generate_activations_graph and its model.inputs and layer.output handling. Reproduce the failure with TensorFlow 2.0 and the shown ActivationsVisualizationCallback configuration, then determine the compatibility change needed and add a regression check demonstrating that the callback completes.