C5 W3 A1 Neural Machine Translation ValueError: The two structures don't have the same sequence length. Input structure has length 10, while shallow structure has length 1


I’m receiving an error I’m not understanding in the Week 3 Neural machine translation with attention coding problem:

model.fit([Xoh, s0, c0], outputs, epochs=1, batch_size=100)
ValueError: The two structures don't have the same sequence length. Input structure has length 10, while shallow structure has length 1.

all previous output looks OK. I wonder what the ‘shallow structure’ is and how can I make it length 10?

The complete output:

model.fit([Xoh, s0, c0], outputs, epochs=1, batch_size=100)

ValueError                                Traceback (most recent call last)
<ipython-input-21-1a1812141e7e> in <module>
----> 1 model.fit([Xoh, s0, c0], outputs, epochs=1, batch_size=100)

/opt/conda/lib/python3.7/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)
    110     # Running inside `run_distribute_coordinator` already.

/opt/conda/lib/python3.7/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()

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

/opt/conda/lib/python3.7/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)
--> 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/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)

/opt/conda/lib/python3.7/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

ValueError: in user code:

    /opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py:806 train_function  *
        return step_function(self, iterator)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py:796 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/distribute/distribute_lib.py:1211 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/distribute/distribute_lib.py:2585 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/distribute/distribute_lib.py:2945 _call_for_each_replica
        return fn(*args, **kwargs)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py:789 run_step  **
        outputs = model.train_step(data)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py:759 train_step
        self.compiled_metrics.update_state(y, y_pred, sample_weight)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/compile_utils.py:388 update_state
        self.build(y_pred, y_true)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/compile_utils.py:319 build
        self._metrics, y_true, y_pred)
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/util/nest.py:1139 map_structure_up_to
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/util/nest.py:1221 map_structure_with_tuple_paths_up_to
    /opt/conda/lib/python3.7/site-packages/tensorflow/python/util/nest.py:854 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.


Hi @Akos_Maroy,

After looking at your code of Ex 2, which is causing the issue, 3 things that I observed:

  • For “Step 1”, you are not specifying the “input shape” - (X is the input, it doesn’t specify the input shape)
  • For “Step 2.B”, you are passing the same “initial” cell state over and over again. The code cell comment for Step 2.B gives a reminder about what the states need to be.
  • For model, you are passing the outputs as a list.

Fixing these should make the code run.


P.S it is hard to design unit tests for the exercises in this assignment, so some cases are not captured. We apologise for the inconvenience.

I get a similar error:“ValueError: The two structures don’t have the same sequence length. Input structure has length 10, while shallow structure has length 2”
But my Ex. 2 doesn’t have the code errors you have listed. Where else might I have made a mistake?

Hi @Sundar_Sundareswaran ,

This thread is 2 months old. The problem you encountered may not be the same. Please post a fresh query with error traceback to help with the diagnosis.

Thanks, and Done!