Keras Sequential Model is not fitting after successful compilation

Question

I am trying to create a neural network using keras and tensorflow. After successfully creating a sequential and dense model and compiling it with Adam optimizer, there is an error when I try to fit the model and run it over some epochs.

Here is my code for the model creation and compilation:

ann = tensorflow.keras.models.Sequential([Dense(6, activation="relu", input_shape=X_train.shape[1:]), Dense(6,activation="relu"), Dense(1)])
loss = keras.losses.mean_squared_error
ann.compile(optimizer="Adam",loss=loss,metrics=["mean_squared_error"])

and here is the code where I try to fit and train the model:

history=ann.fit(X_train,y_train,epochs=100)

The error I get is the following:

AttributeError                            Traceback (most recent call last)
<ipython-input-64-8d6faf07db5a> in <module>
----> 1 history=ann.fit(X_train,y_train,epochs=100)

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\keras\engine\training.py in _method_wrapper(self, *args, **kwargs)
    106   def _method_wrapper(self, *args, **kwargs):
    107     if not self._in_multi_worker_mode():  # pylint: disable=protected-access
--> 108       return method(self, *args, **kwargs)
    109 
    110     # Running inside `run_distribute_coordinator` already.

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\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_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1096                 batch_size=batch_size):
   1097               callbacks.on_train_batch_begin(step)
-> 1098               tmp_logs = train_function(iterator)
   1099               if data_handler.should_sync:
   1100                 context.async_wait()

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
    778       else:
    779         compiler = "nonXla"
--> 780         result = self._call(*args, **kwds)
    781 
    782       new_tracing_count = self._get_tracing_count()

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
    812       # In this case we have not created variables on the first call. So we can
    813       # run the first trace but we should fail if variables are created.
--> 814       results = self._stateful_fn(*args, **kwds)
    815       if self._created_variables:
    816         raise ValueError("Creating variables on a non-first call to a function"

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\function.py in __call__(self, *args, **kwargs)
   2826     """Calls a graph function specialized to the inputs."""
   2827     with self._lock:
-> 2828       graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
   2829     return graph_function._filtered_call(args, kwargs)  # pylint: disable=protected-access
   2830 

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
   3208           and self.input_signature is None
   3209           and call_context_key in self._function_cache.missed):
-> 3210         return self._define_function_with_shape_relaxation(args, kwargs)
   3211 
   3212       self._function_cache.missed.add(call_context_key)

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\function.py in _define_function_with_shape_relaxation(self, args, kwargs)
   3140 
   3141     graph_function = self._create_graph_function(
-> 3142         args, kwargs, override_flat_arg_shapes=relaxed_arg_shapes)
   3143     self._function_cache.arg_relaxed[rank_only_cache_key] = graph_function
   3144 

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3073             arg_names=arg_names,
   3074             override_flat_arg_shapes=override_flat_arg_shapes,
-> 3075             capture_by_value=self._capture_by_value),
   3076         self._function_attributes,
   3077         function_spec=self.function_spec,

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\framework\func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
    984         _, original_func = tf_decorator.unwrap(python_func)
    985 
--> 986       func_outputs = python_func(*func_args, **func_kwargs)
    987 
    988       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
    598         # __wrapped__ allows AutoGraph to swap in a converted function. We give
    599         # the function a weak reference to itself to avoid a reference cycle.
--> 600         return weak_wrapped_fn().__wrapped__(*args, **kwds)
    601     weak_wrapped_fn = weakref.ref(wrapped_fn)
    602 

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
    971           except Exception as e:  # pylint:disable=broad-except
    972             if hasattr(e, "ag_error_metadata"):
--> 973               raise e.ag_error_metadata.to_exception(e)
    974             else:
    975               raise

AttributeError: in user code:

    C:\Users\AnamayMayureshDeshpa\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\keras\engine\training.py:806 train_function  *
        return step_function(self, iterator)
    E:\Anaconda\lib\site-packages\keras\losses.py:603 mean_squared_error  *
        if not K.is_tensor(y_pred):
    E:\Anaconda\lib\site-packages\keras\backend\tensorflow_backend.py:703 is_tensor  *
        return isinstance(x, tf_ops._TensorLike) or tf_ops.is_dense_tensor_like(x)

    AttributeError: module 'tensorflow.python.framework.ops' has no attribute '_TensorLike'

I have also imported the following libraries:

import keras
import tensorflow
from tensorflow.keras import models
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Input, Dense, Dropout, Activation, Flatten
from tensorflow.keras.optimizers import Adam, RMSprop

Answer 1

First I would advise you to uniformise between keras and tf.keras (preferably tf.keras).

Then try to replace lossby :

loss = tensorflow.keras.losses.MeanSquaredError()

Finally, the simplest might be :

ann.compile(optimizer="Adam",loss='mse',metrics=['mse'])