I have a model of this structure:
filter_size = (3,3)
filters = 32
pool = 2
input_layer = keras.Input(shape=(100,300,1))
conv_extractor = layers.Conv2D(filters,filter_size, activation='relu')(input_layer)
conv_extractor = layers.MaxPooling2D(pool_size=(pool, pool))(conv_extractor)
conv_extractor = layers.Conv2D(filters,filter_size, activation='relu')(conv_extractor)
conv_extractor = layers.MaxPooling2D(pool_size=(pool, pool))(conv_extractor)
#conv_extractor = layers.Reshape(target_shape=(100 // (pool ** 2), (100 // (pool ** 2)) * filters))(conv_extractor)
shape = ((100 // 4), (300 // 4) * 32)
#conv_extractor = layers.Dense(512, activation='relu')(conv_extractor)
conv_extractor = layers.Reshape(target_shape=(23,2336))(conv_extractor)
gru_1 = GRU(512, return_sequences=True)(conv_extractor)
gru_1b = GRU(512, return_sequences=True, go_backwards=True)(conv_extractor)
gru1_merged = add([gru_1, gru_1b])
gru_2 = GRU(512, return_sequences=True)(gru1_merged)
gru_2b = GRU(512, return_sequences=True, go_backwards=True)(gru1_merged)
inner = layers.Dense(30, activation='LeakyReLU')(concatenate([gru_2, gru_2b]))
inner = layers.Dense(10, activation='LeakyReLU')(inner)
inner = layers.Dense(3, activation='LeakyReLU')(inner)
model = Model(input_layer,inner)
model.compile(loss = "poisson", optimizer = optimizers.Adam(2e-4), metrics=['accuracy'])
All of the above seems to work, when trying to train using model.fit(x_train, y_train,epochs=3) I get the following error:
ValueError Traceback (most recent call last)
/var/folders/nc/c4mgwn897qbg8g52tp3mhbjr0000gp/T/ipykernel_3907/1977739458.py in <module>
----> 1 model.fit(x_train, y_train,epochs=3)
~/opt/anaconda3/lib/python3.8/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)
1181 _r=1):
1182 callbacks.on_train_batch_begin(step)
-> 1183 tmp_logs = self.train_function(iterator)
1184 if data_handler.should_sync:
1185 context.async_wait()
~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
887
888 with OptionalXlaContext(self._jit_compile):
--> 889 result = self._call(*args, **kwds)
890
891 new_tracing_count = self.experimental_get_tracing_count()
~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
931 # This is the first call of __call__, so we have to initialize.
932 initializers = []
--> 933 self._initialize(args, kwds, add_initializers_to=initializers)
934 finally:
935 # At this point we know that the initialization is complete (or less
~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
761 self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph)
762 self._concrete_stateful_fn = (
--> 763 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
764 *args, **kwds))
765
~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
3048 args, kwargs = None, None
3049 with self._lock:
-> 3050 graph_function, _ = self._maybe_define_function(args, kwargs)
3051 return graph_function
3052
~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
3442
3443 self._function_cache.missed.add(call_context_key)
-> 3444 graph_function = self._create_graph_function(args, kwargs)
3445 self._function_cache.primary[cache_key] = graph_function
3446
~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
3277 arg_names = base_arg_names missing_arg_names
3278 graph_function = ConcreteFunction(
-> 3279 func_graph_module.func_graph_from_py_func(
3280 self._name,
3281 self._python_function,
~/opt/anaconda3/lib/python3.8/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)
997 _, original_func = tf_decorator.unwrap(python_func)
998
--> 999 func_outputs = python_func(*func_args, **func_kwargs)
1000
1001 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
670 # the function a weak reference to itself to avoid a reference cycle.
671 with OptionalXlaContext(compile_with_xla):
--> 672 out = weak_wrapped_fn().__wrapped__(*args, **kwds)
673 return out
674
~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
984 except Exception as e: # pylint:disable=broad-except
985 if hasattr(e, "ag_error_metadata"):
--> 986 raise e.ag_error_metadata.to_exception(e)
987 else:
988 raise
ValueError: in user code:
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:855 train_function *
return step_function(self, iterator)
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:845 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:1285 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2833 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:3608 _call_for_each_replica
return fn(*args, **kwargs)
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:838 run_step **
outputs = model.train_step(data)
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:800 train_step
self.compiled_metrics.update_state(y, y_pred, sample_weight)
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/compile_utils.py:460 update_state
metric_obj.update_state(y_t, y_p, sample_weight=mask)
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/utils/metrics_utils.py:86 decorated
update_op = update_state_fn(*args, **kwargs)
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/metrics.py:177 update_state_fn
return ag_update_state(*args, **kwargs)
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/metrics.py:664 update_state **
matches = ag_fn(y_true, y_pred, **self._fn_kwargs)
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/util/dispatch.py:206 wrapper
return target(*args, **kwargs)
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/metrics.py:3485 sparse_categorical_accuracy
return math_ops.cast(math_ops.equal(y_true, y_pred), backend.floatx())
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/util/dispatch.py:206 wrapper
return target(*args, **kwargs)
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/ops/math_ops.py:1729 equal
return gen_math_ops.equal(x, y, name=name)
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/ops/gen_math_ops.py:3228 equal
_, _, _op, _outputs = _op_def_library._apply_op_helper(
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/framework/op_def_library.py:748 _apply_op_helper
op = g._create_op_internal(op_type_name, inputs, dtypes=None,
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py:599 _create_op_internal
return super(FuncGraph, self)._create_op_internal( # pylint: disable=protected-access
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/framework/ops.py:3557 _create_op_internal
ret = Operation(
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/framework/ops.py:2041 __init__
self._c_op = _create_c_op(self._graph, node_def, inputs,
/Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/framework/ops.py:1883 _create_c_op
raise ValueError(str(e))
ValueError: Dimensions must be equal, but are 3 and 23 for '{{node Equal}} = Equal[T=DT_FLOAT, incompatible_shape_error=true](Cast_1, Cast_2)' with input shapes: [?,3], [?,23].
FYI: the shape of x_train is 2000,100,300,1 and y_train is 2000,3
CodePudding user response：
Your model output is (None, 23, 3), while it should be (None, 3) to match with your target variable (y_train) which is (2000,3).
Since your Dense layers input is a 3 dimensional (after concatenate layer), their output will be also a 3D (None, 23, 3). Simply add a Flatten layers before Dense layers.:
gru_2b = layers.GRU(512, return_sequences=True, go_backwards=True)(gru1_merged)
x = layers.concatenate([gru_2, gru_2b]) # move concatenate layer aside
x = layers.Flatten()(x) # add this
inner = layers.Dense(30, activation='LeakyReLU')(x)
Or you can remove return_sequence=True from your last GRU layers like this:
gru_2 = layers.GRU(512)(gru1_merged) # remove return_sequence=True
gru_2b = layers.GRU(512, go_backwards=True)(gru1_merged) # remove return_sequence=True
inner = layers.Dense(30, activation='LeakyReLU')(concatenate([gru_2, gru_2b]))