Error in "Transfer_learning_with_MobileNet_v1"

[menezesluiz]

Please, upon reaching the code snippet below, the notebook is displaying the following error. What could be happening?

initial_epochs = 5
history = model2.fit(train_dataset, validation_data=validation_dataset, epochs=initial_epochs)

Epoch 1/5

ValueError Traceback (most recent call last)
in
1 initial_epochs = 5
----> 2 history = model2.fit(train_dataset, validation_data=validation_dataset, epochs=initial_epochs)

/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)
109
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)
781
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))
698
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
2857

/opt/conda/lib/python3.7/site-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
3211
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)
985
→ 986 func_outputs = python_func(*func_args, **func_kwargs)
987
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)
602

/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:749 train_step
    y, y_pred, sample_weight, regularization_losses=self.losses)
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/compile_utils.py:204 __call__
    loss_value = loss_obj(y_t, y_p, sample_weight=sw)
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/losses.py:149 __call__
    losses = ag_call(y_true, y_pred)
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/losses.py:253 call  **
    return ag_fn(y_true, y_pred, **self._fn_kwargs)
/opt/conda/lib/python3.7/site-packages/tensorflow/python/util/dispatch.py:201 wrapper
    return target(*args, **kwargs)
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/losses.py:1605 binary_crossentropy
    K.binary_crossentropy(y_true, y_pred, from_logits=from_logits), axis=-1)
/opt/conda/lib/python3.7/site-packages/tensorflow/python/util/dispatch.py:201 wrapper
    return target(*args, **kwargs)
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/backend.py:4814 binary_crossentropy
    return nn.sigmoid_cross_entropy_with_logits(labels=target, logits=output)
/opt/conda/lib/python3.7/site-packages/tensorflow/python/util/dispatch.py:201 wrapper
    return target(*args, **kwargs)
/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/nn_impl.py:174 sigmoid_cross_entropy_with_logits
    (logits.get_shape(), labels.get_shape()))

ValueError: logits and labels must have the same shape ((None, 1280) vs (None, 1))

[menezesluiz]

Until I get to that part, the code seems to work correctly, but below it, it’s giving this error.

[TMosh]

I apologize, but I have no idea what would cause that to happen.

[menezesluiz]

I also can’t even imagine what could be causing this error. If we look at the last print, we can see that the tests complete successfully. This activity will be on “stand-by” while I advance in the course so as not to miss deadlines, until it is possible to solve it.

[TMosh]

{edited my own reply}

[menezesluiz]

Ok. I’ll arrange it right now.

[paulinpaloalto]

It’s not a good idea to assume that the tests in the notebook catch everything. Here’s my output for the “comparator” step:

All tests passed!
['InputLayer', [(None, 160, 160, 3)], 0]
['Sequential', (None, 160, 160, 3), 0]
['TensorFlowOpLayer', [(None, 160, 160, 3)], 0]
['TensorFlowOpLayer', [(None, 160, 160, 3)], 0]
['Functional', (None, 5, 5, 1280), 2257984]
['GlobalAveragePooling2D', (None, 1280), 0]
['Dropout', (None, 1280), 0, 0.2]
['Dense', (None, 1), 1281, 'linear']

You’ll notice that you are missing the “Dense” layer that should be the last entry. There is a bug in the comparator routine (which I filed literally months ago) that it succeeds if the user’s input is shorter than the full answer. Looks like you stepped on that landmine.

[paulinpaloalto]

Also BTW they show the full output in the test block.

Ok, I checked and I filed the bug about comparator against the Residual Net exercise and they fixed it there, but apparently did not propagate the fix to other versions of that function in other exercises. Sigh. I’ll file a new bug about this one.

[TMosh]

Interesting, thanks for re-reporting bug in the unit test.

[paulinpaloalto]

@TMosh: I see you have an outstanding bug about a different unit test in that assignment, but unfortunately that one does not involve the comparator function. So it’s probably better to file a new bug.

[TMosh]

Note that there are several other errors in the alpaca_model() code, I have replied via a private message.

[menezesluiz]

When making the changes, the following error occurred.

[menezesluiz]

So can I treat this error as a system “bug” and move on to next week while the technical team investigates the issue? Or is this error occurring because of my failure to structure the codes?

[paulinpaloalto]

I can’t see the actual error message in what you posted. Rather than post an image, please “copy/paste” the entire exception log. I was able to get this to work, so I think you should assume this is some kind of mistake on your part.

[TMosh]

You have spelled “dense(…)” incorrectly.