TypeError: Can not convert a NoneType into a Tensor or Operation -- Error believe related to converting to graph - tensorflow

Question

Below find my model:
class CustomModel(tf.keras.Model):
def __init__(self, model1, model2, model3, model4):
super(deep_and_wide, self).__init__()
self.model1 = model1
self.model2 = model2
self.model3 = model3
self.model4 = model4
def call(self, inputs):
x1 = self.mode1([inputs["a"], inputs["b"]])
x2 = self.model2([inputs["a"], inputs["b"]])
x3 = self.model3([inputs["a"], inputs["b"]])
x4 = self.model4([inputs["a"], inputs["b"]])
x = Concatenate()([x1, x2, x3])
x = TimeDistributed(Dense(2))(x)
x = Add()([x, x4])
x_fc = Dense(1)(x)
x_ec = Dense(1)(x)
return x_fc, x_ec
def train_step(self, data):
with tf.GradientTape() as tape:
data = data_adapter.expand_1d(data)
batch_inputs, batch_outputs, sample_weight= data_adapter.unpack_x_y_sample_weight(data)
y_true_fc, y_true_ec = batch_outputs["y_fc"], batch_outputs["y_ec"]
y_pred_fc, y_pred_ec = self(batch_inputs, training=True)
loss_fc = self.compiled_loss(y_true_fc, y_pred_fc)
loss_ec = self.compiled_loss(y_true_ec, y_pred_ec)
print("here")
trainable_variables = self.trainable_variables
print("here")
gradients = tape.gradient([loss_fc, loss_ec], trainable_variables)
print("here")
self.optimizer.apply_gradients(zip(gradients, trainable_variables))
print("here")
And below is my custom loss
class CustomLoss(tf.keras.losses.Loss):
def __init__(self, mask=True, alpha=1, beta=1, gamma=1, dtype=tf.float64):
super(CustomLoss, self).__init__(reduction=tf.keras.losses.Reduction.NONE)
self.mask = mask
self.alpha = alpha
self.beta = beta
self.gamma = gamma
self.dtype = dtype
def call(self, y_true, y_pred):
def loss_fn(y_true, y_pred, mask):
y_true = tf.boolean_mask(y_true, mask)
y_pred = tf.boolean_mask(y_pred, mask)
return tf.keras.losses.MSE(y_true, y_pred)
self.mask = tf.not_equal(y_true, 0.)
y_true = tf.cast(y_true, self.dtype)
y_pred = tf.cast(y_pred, self.dtype)
y_pred = tf.multiply(y_pred, tf.cast(self.mask, dtype=self.dtype))
y_pred_cum = tf.math.cumsum(y_pred, axis=1)
y_pred_cum = tf.multiply(y_pred_cum, tf.cast(self.mask, dtype=self.dtype))
y_true_cum = tf.math.cumsum(y_true, axis=1)
y_true_cum = tf.multiply(y_true_cum, tf.cast(self.mask, dtype=self.dtype))
loss_value = self.alpha * loss_fn(y_true, y_pred, self.mask) + \
self.gamma * loss_fn(y_true_cum, y_pred_cum, self.mask)
return loss_value
And then finally:
optimizer = tf.keras.optimizers.Adam()
loss = CustomLoss()
model.compile(optimizer, loss)
model.fit(train_data, epochs=5, validation_data=val_data)
My data inputs are of size (sequence length, feature length) where sequence length is variable hence I am using tf.data.experimental.bucket_by_sequence_length to pad to max sequence length of the batch (as opposed to batch to max sequence length). All in all, my train and val data are tf.data.Datasets each created using tf.data.experimental.bucket_by_sequence_length where each batch is of size (None, None, feature length).
When I run the above code, I get the following errors and cannot seem to understand where I am going wrong:
Traceback (most recent call last):
File "<input>", line 75, in <module>
File "C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1100, in fit
tmp_logs = self.train_function(iterator)
File "C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\eager\def_function.py", line 828, in __call__
result = self._call(*args, **kwds)
File "C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\eager\def_function.py", line 871, in _call
self._initialize(args, kwds, add_initializers_to=initializers)
File "C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\eager\def_function.py", line 725, in _initialize
self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
File "C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\eager\function.py", line 2969, in _get_concrete_function_internal_garbage_collected
graph_function, _ = self._maybe_define_function(args, kwargs)
File "C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\eager\function.py", line 3361, in _maybe_define_function
graph_function = self._create_graph_function(args, kwargs)
File "C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\eager\function.py", line 3196, in _create_graph_function
func_graph_module.func_graph_from_py_func(
File "C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\framework\func_graph.py", line 990, in func_graph_from_py_func
func_outputs = python_func(*func_args, **func_kwargs)
File "C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\eager\def_function.py", line 634, in wrapped_fn
out = weak_wrapped_fn().__wrapped__(*args, **kwds)
File "C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\framework\func_graph.py", line 977, in wrapper
raise e.ag_error_metadata.to_exception(e)
TypeError: in user code:
C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\keras\engine\training.py:805 train_function *
return step_function(self, iterator)
C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\keras\engine\training.py:795 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1259 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2730 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:3417 _call_for_each_replica
return fn(*args, **kwargs)
C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\keras\engine\training.py:790 run_step **
with ops.control_dependencies(_minimum_control_deps(outputs)):
C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\framework\ops.py:5359 control_dependencies
return get_default_graph().control_dependencies(control_inputs)
C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\framework\func_graph.py:362 control_dependencies
return super(FuncGraph, self).control_dependencies(filtered_control_inputs)
C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\framework\ops.py:4815 control_dependencies
c = self.as_graph_element(c)
C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\framework\ops.py:3726 as_graph_element
return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
C:\Users\\Anaconda3\envs\tf_recsys\lib\site-packages\tensorflow\python\framework\ops.py:3814 _as_graph_element_locked
raise TypeError("Can not convert a %s into a %s." %
TypeError: Can not convert a NoneType into a Tensor or Operation.
The four print statements inserted in the train_step function above are printed.

Answer 1

This NoneType refers to the returned value of the custom train_step, when using a custom train_step you should return something that can be converted into a tensor so that the minimum control dependencies can process it, typically, the loss value as {"loss": loss_value} and potentially some other metrics, or at least an empty dict {}.