Machine Translation task model not fitting

The model is built successfully and all, but when attempting to call the fit method, I get the following error:

**ValueError: The two structures don't have the same sequence length. Input structure has length 10, while shallow structure has length 1.**

Hey @Subigya_Paudel,
Welcome to the community. Have you passed all the test-cases in your assignment? If not, then can you please post the traceback of the error that you receive in your notebook.

P.S. - Posting code publicly is strictly against the community guidelines. So, please make sure to post the traceback only, and not the code.


Yes, all the test cases pass and even the assignment received 100 points, but the actual training is interrupted by this error. The requested feedback is as follows:

ValueError                                Traceback (most recent call last)
<ipython-input-47-1a1812141e7e> in <module>
----> 1[Xoh, s0, c0], outputs, epochs=1, batch_size=100)

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/ 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)
    110     # Running inside `run_distribute_coordinator` already.

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/ 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()

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/ in __call__(self, *args, **kwds)
    778       else:
    779         compiler = "nonXla"
--> 780         result = self._call(*args, **kwds)
    782       new_tracing_count = self._get_tracing_count()

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/ in _call(self, *args, **kwds)
    821       # This is the first call of __call__, so we have to initialize.
    822       initializers = []
--> 823       self._initialize(args, kwds, add_initializers_to=initializers)
    824     finally:
    825       # At this point we know that the initialization is complete (or less

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/ in _initialize(self, args, kwds, add_initializers_to)
    695     self._concrete_stateful_fn = (
    696         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
--> 697             *args, **kwds))
    699     def invalid_creator_scope(*unused_args, **unused_kwds):

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/ in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
   2853       args, kwargs = None, None
   2854     with self._lock:
-> 2855       graph_function, _, _ = self._maybe_define_function(args, kwargs)
   2856     return graph_function

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/ in _maybe_define_function(self, args, kwargs)
   3212       self._function_cache.missed.add(call_context_key)
-> 3213       graph_function = self._create_graph_function(args, kwargs)
   3214       self._function_cache.primary[cache_key] = graph_function
   3215       return graph_function, args, kwargs

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/ 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,

/opt/conda/lib/python3.7/site-packages/tensorflow/python/framework/ 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)
--> 986       func_outputs = python_func(*func_args, **func_kwargs)
    988       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/ 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)

/opt/conda/lib/python3.7/site-packages/tensorflow/python/framework/ 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

ValueError: in user code:

    /opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/ train_function  *
        return step_function(self, iterator)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/ step_function  **
        outputs =, args=(data,))
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/distribute/ run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/distribute/ call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/distribute/ _call_for_each_replica
        return fn(*args, **kwargs)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/ run_step  **
        outputs = model.train_step(data)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/ train_step
        self.compiled_metrics.update_state(y, y_pred, sample_weight)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/ update_state, y_true)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/ build
        self._metrics, y_true, y_pred)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/util/ map_structure_up_to
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/util/ map_structure_with_tuple_paths_up_to
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/util/ assert_shallow_structure
        input_length=len(input_tree), shallow_length=len(shallow_tree)))

    ValueError: The two structures don't have the same sequence length. Input structure has length 10, while shallow structure has length 1.

Are you running in the Coursera Labs environment, or are you using some other platform?

It’s in Coursera labs.

Hey @Subigya_Paudel,
It seems like your code has an error that is not being caught by both, the test-cases and the auto-grader, and as a result, even though your assignment is receiving a full score, you are unable to train the model. This is because, I ran the notebook myself in Coursera labs, and it is running perfectly fine. Can you please DM your notebook as an attachment to me? You can find the instructions to download your notebook here.


I got similar error, what helped me is that I was returning Model(inputs=[X, s0, c0], outputs=[outputs])instead of Model(inputs=[X, s0, c0], outputs=outputs) which solved it for me

Hey @Ankur_Srivastava,
Welcome, and we are glad that you could become a part of our community :partying_face: Thanks a lot for your contribution.