因此，我正在使用tf.keras中的功能API创建模型，在该模型中我正在执行多输入模型。
用于训练的输入是形状（n_examples = 58667，n_dim = 2748）。每个示例都是2048和700维向量的连接。
但是我收到了一条我不理解的错误消息：
InvalidArgumentError：两个形状的尺寸0必须相等，但必须为1和0。形状为[1]和[0]。对于“ model_27 / concatenate_28 / concat”（运算符：“ ConcatV2”），其输入形状为[1,100]，[0,100]，[]，并具有计算的输入张量：input [2] = <1>。
这里有虚拟输入和导入，使其可运行：
from tensorflow.keras import models, layers, losses, metrics, optimizers
from tensorflow.keras.layers import Dense, Concatenate, Input, Lambda
from tensorflow.keras.models import Model
from tensorflow.keras import backend as K
from sklearn.model_selection import train_test_split
import numpy as np
fake_train = np.random.rand(10000,2748)
fake_test = np.random.randint(0,1,(10000,1))
x_train, x_dev, y_train, y_dev = train_test_split(fake_train, fake_test, test_size = 0.2)
使用此功能创建我的模型：
def build_model():
input0 = Input(shape=(2748,))
branch1 = Lambda(lambda x:x[:2048])(input0)
branch1 = Dense(1000, activation='relu')(branch1)
branch1 = Dense(100, activation='relu')(branch1)
branch1 = Dense(100, activation='relu')(branch1)
branch2 = Lambda(lambda x:x[2048:])(input0)
branch2 = Dense(1000, activation='relu')(branch2)
branch2 = Dense(100, activation='relu')(branch2)
branch2 = Dense(100, activation='relu')(branch2)
out = layers.concatenate([branch1, branch2],axis=-1)
out = Dense(10, activation = 'relu')(out)
out = Dense(1, activation='sigmoid')(out)
model = Model(inputs=input0, outputs=out)
model.compile(optimizer=optimizers.Adam(lr=0.001),
loss='binary_crossentropy',
metrics=['accuracy', recall_m, precision_m])
return model
以下是用于对伪数据进行交叉验证的参数：
k = 3 #Number of folds for CV
num_epochs = 4 #for test only
batch_size = 1
这是我对模型的交叉验证，这开始了错误：
all_loss_histories = []
all_recall_histories = []
all_precision_histories = []
for i in range(k):
val_data = x_train[i * num_val_samples:(i+1) * num_val_samples]
val_targets = y_train[i * num_val_samples:(i+1) * num_val_samples]
partial_train_data = np.concatenate(
[x_train[:i*num_val_samples],
x_train[(i+1)*num_val_samples:]],
axis = 0)
partial_train_targets = np.concatenate(
[y_train[:i*num_val_samples],
y_train[(i+1)*num_val_samples:]],
axis = 0)
model = build_model()
history = model.fit(partial_train_data,
partial_train_targets,
epochs = num_epochs,
batch_size = batch_size,
verbose = 1,
validation_data = (val_data, val_targets),
use_multiprocessing=False)
print('Finished training fold '+str(i+1))
loss_history = history.history['val_loss']
recall_history = history.history['val_recall_m']
precision_history = history.history['val_precision_m']
all_loss_histories.append(loss_history)
all_recall_histories.append(recall_history)
all_precision_histories.append(precision_history)
知道为什么会有错误吗？
[在MacBook Pro 2018上使用python3.7和tf 2.0（在OSX上，而不在Linux VM上）
谢谢！
完整错误：
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py in _create_c_op(graph, node_def, inputs, control_inputs)
1609 try:
-> 1610 c_op = c_api.TF_FinishOperation(op_desc)
1611 except errors.InvalidArgumentError as e:
InvalidArgumentError: Dimension 0 in both shapes must be equal, but are 1 and 0. Shapes are [1] and [0]. for 'model_33/concatenate_34/concat' (op: 'ConcatV2') with input shapes: [1,100], [0,100], [] and with computed input tensors: input[2] = <1>.
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<timed exec> in <module>
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/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_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
726 max_queue_size=max_queue_size,
727 workers=workers,
--> 728 use_multiprocessing=use_multiprocessing)
729
730 def evaluate(self,
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py in fit(self, model, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, **kwargs)
322 mode=ModeKeys.TRAIN,
323 training_context=training_context,
--> 324 total_epochs=epochs)
325 cbks.make_logs(model, epoch_logs, training_result, ModeKeys.TRAIN)
326
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py in run_one_epoch(model, iterator, execution_function, dataset_size, batch_size, strategy, steps_per_epoch, num_samples, mode, training_context, total_epochs)
121 step=step, mode=mode, size=current_batch_size) as batch_logs:
122 try:
--> 123 batch_outs = execution_function(iterator)
124 except (StopIteration, errors.OutOfRangeError):
125 # TODO(kaftan): File bug about tf function and errors.OutOfRangeError?
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py in execution_function(input_fn)
84 # `numpy` translates Tensors to values in Eager mode.
85 return nest.map_structure(_non_none_constant_value,
---> 86 distributed_function(input_fn))
87
88 return execution_function
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in __call__(self, *args, **kwds)
455
456 tracing_count = self._get_tracing_count()
--> 457 result = self._call(*args, **kwds)
458 if tracing_count == self._get_tracing_count():
459 self._call_counter.called_without_tracing()
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in _call(self, *args, **kwds)
501 # This is the first call of __call__, so we have to initialize.
502 initializer_map = object_identity.ObjectIdentityDictionary()
--> 503 self._initialize(args, kwds, add_initializers_to=initializer_map)
504 finally:
505 # At this point we know that the initialization is complete (or less
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
406 self._concrete_stateful_fn = (
407 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
--> 408 *args, **kwds))
409
410 def invalid_creator_scope(*unused_args, **unused_kwds):
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
1846 if self.input_signature:
1847 args, kwargs = None, None
-> 1848 graph_function, _, _ = self._maybe_define_function(args, kwargs)
1849 return graph_function
1850
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _maybe_define_function(self, args, kwargs)
2148 graph_function = self._function_cache.primary.get(cache_key, None)
2149 if graph_function is None:
-> 2150 graph_function = self._create_graph_function(args, kwargs)
2151 self._function_cache.primary[cache_key] = graph_function
2152 return graph_function, args, kwargs
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
2039 arg_names=arg_names,
2040 override_flat_arg_shapes=override_flat_arg_shapes,
-> 2041 capture_by_value=self._capture_by_value),
2042 self._function_attributes,
2043 # Tell the ConcreteFunction to clean up its graph once it goes out of
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/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)
913 converted_func)
914
--> 915 func_outputs = python_func(*func_args, **func_kwargs)
916
917 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in wrapped_fn(*args, **kwds)
356 # __wrapped__ allows AutoGraph to swap in a converted function. We give
357 # the function a weak reference to itself to avoid a reference cycle.
--> 358 return weak_wrapped_fn().__wrapped__(*args, **kwds)
359 weak_wrapped_fn = weakref.ref(wrapped_fn)
360
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py in distributed_function(input_iterator)
71 strategy = distribution_strategy_context.get_strategy()
72 outputs = strategy.experimental_run_v2(
---> 73 per_replica_function, args=(model, x, y, sample_weights))
74 # Out of PerReplica outputs reduce or pick values to return.
75 all_outputs = dist_utils.unwrap_output_dict(
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/distribute/distribute_lib.py in experimental_run_v2(self, fn, args, kwargs)
758 fn = autograph.tf_convert(fn, ag_ctx.control_status_ctx(),
759 convert_by_default=False)
--> 760 return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
761
762 def reduce(self, reduce_op, value, axis):
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/distribute/distribute_lib.py in call_for_each_replica(self, fn, args, kwargs)
1785 kwargs = {}
1786 with self._container_strategy().scope():
-> 1787 return self._call_for_each_replica(fn, args, kwargs)
1788
1789 def _call_for_each_replica(self, fn, args, kwargs):
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/distribute/distribute_lib.py in _call_for_each_replica(self, fn, args, kwargs)
2130 self._container_strategy(),
2131 replica_id_in_sync_group=constant_op.constant(0, dtypes.int32)):
-> 2132 return fn(*args, **kwargs)
2133
2134 def _reduce_to(self, reduce_op, value, destinations):
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/autograph/impl/api.py in wrapper(*args, **kwargs)
290 def wrapper(*args, **kwargs):
291 with ag_ctx.ControlStatusCtx(status=ag_ctx.Status.DISABLED):
--> 292 return func(*args, **kwargs)
293
294 if inspect.isfunction(func) or inspect.ismethod(func):
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py in train_on_batch(model, x, y, sample_weight, class_weight, reset_metrics)
262 y,
263 sample_weights=sample_weights,
--> 264 output_loss_metrics=model._output_loss_metrics)
265
266 if reset_metrics:
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_eager.py in train_on_batch(model, inputs, targets, sample_weights, output_loss_metrics)
309 sample_weights=sample_weights,
310 training=True,
--> 311 output_loss_metrics=output_loss_metrics))
312 if not isinstance(outs, list):
313 outs = [outs]
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_eager.py in _process_single_batch(model, inputs, targets, output_loss_metrics, sample_weights, training)
250 output_loss_metrics=output_loss_metrics,
251 sample_weights=sample_weights,
--> 252 training=training))
253 if total_loss is None:
254 raise ValueError('The model cannot be run '
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_eager.py in _model_loss(model, inputs, targets, output_loss_metrics, sample_weights, training)
125 inputs = nest.map_structure(ops.convert_to_tensor, inputs)
126
--> 127 outs = model(inputs, **kwargs)
128 outs = nest.flatten(outs)
129
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/base_layer.py in __call__(self, inputs, *args, **kwargs)
845 outputs = base_layer_utils.mark_as_return(outputs, acd)
846 else:
--> 847 outputs = call_fn(cast_inputs, *args, **kwargs)
848
849 except errors.OperatorNotAllowedInGraphError as e:
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/network.py in call(self, inputs, training, mask)
706 return self._run_internal_graph(
707 inputs, training=training, mask=mask,
--> 708 convert_kwargs_to_constants=base_layer_utils.call_context().saving)
709
710 def compute_output_shape(self, input_shape):
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/network.py in _run_internal_graph(self, inputs, training, mask, convert_kwargs_to_constants)
858
859 # Compute outputs.
--> 860 output_tensors = layer(computed_tensors, **kwargs)
861
862 # Update tensor_dict.
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/base_layer.py in __call__(self, inputs, *args, **kwargs)
845 outputs = base_layer_utils.mark_as_return(outputs, acd)
846 else:
--> 847 outputs = call_fn(cast_inputs, *args, **kwargs)
848
849 except errors.OperatorNotAllowedInGraphError as e:
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/layers/merge.py in call(self, inputs)
180 return y
181 else:
--> 182 return self._merge_function(inputs)
183
184 @tf_utils.shape_type_conversion
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/layers/merge.py in _merge_function(self, inputs)
392
393 def _merge_function(self, inputs):
--> 394 return K.concatenate(inputs, axis=self.axis)
395
396 @tf_utils.shape_type_conversion
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/backend.py in concatenate(tensors, axis)
2706 return sparse_ops.sparse_concat(axis, tensors)
2707 else:
-> 2708 return array_ops.concat([to_dense(x) for x in tensors], axis)
2709
2710
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/util/dispatch.py in wrapper(*args, **kwargs)
178 """Call target, and fall back on dispatchers if there is a TypeError."""
179 try:
--> 180 return target(*args, **kwargs)
181 except (TypeError, ValueError):
182 # Note: convert_to_eager_tensor currently raises a ValueError, not a
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/ops/array_ops.py in concat(values, axis, name)
1429 dtype=dtypes.int32).get_shape().assert_has_rank(0)
1430 return identity(values[0], name=name)
-> 1431 return gen_array_ops.concat_v2(values=values, axis=axis, name=name)
1432
1433
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/ops/gen_array_ops.py in concat_v2(values, axis, name)
1255 _attr_N = len(values)
1256 _, _, _op = _op_def_lib._apply_op_helper(
-> 1257 "ConcatV2", values=values, axis=axis, name=name)
1258 _result = _op.outputs[:]
1259 _inputs_flat = _op.inputs
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/framework/op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords)
791 op = g.create_op(op_type_name, inputs, dtypes=None, name=scope,
792 input_types=input_types, attrs=attr_protos,
--> 793 op_def=op_def)
794 return output_structure, op_def.is_stateful, op
795
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/framework/func_graph.py in create_op(***failed resolving arguments***)
546 return super(FuncGraph, self)._create_op_internal( # pylint: disable=protected-access
547 op_type, inputs, dtypes, input_types, name, attrs, op_def,
--> 548 compute_device)
549
550 def capture(self, tensor, name=None):
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py in _create_op_internal(self, op_type, inputs, dtypes, input_types, name, attrs, op_def, compute_device)
3427 input_types=input_types,
3428 original_op=self._default_original_op,
-> 3429 op_def=op_def)
3430 self._create_op_helper(ret, compute_device=compute_device)
3431 return ret
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py in __init__(self, node_def, g, inputs, output_types, control_inputs, input_types, original_op, op_def)
1771 op_def, inputs, node_def.attr)
1772 self._c_op = _create_c_op(self._graph, node_def, grouped_inputs,
-> 1773 control_input_ops)
1774 # pylint: enable=protected-access
1775
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py in _create_c_op(graph, node_def, inputs, control_inputs)
1611 except errors.InvalidArgumentError as e:
1612 # Convert to ValueError for backwards compatibility.
-> 1613 raise ValueError(str(e))
1614
1615 return c_op
ValueError: Dimension 0 in both shapes must be equal, but are 1 and 0. Shapes are [1] and [0]. for 'model_33/concatenate_34/concat' (op: 'ConcatV2') with input shapes: [1,100], [0,100], [] and with computed input tensors: input[2] = <1>.```
我相信你想要
Lambda(lambda x:x[:, :2048])(input0)
和
Lambda(lambda x:x[:,2048:])(input0)
因为存在应该保留的批处理轴。您当前的代码在2048 沿批处理轴上拆分，这导致concatenate的一个输入的批次大小为0，一个输入的批次大小为1。由于批次大小不匹配，因此它们无法连接。
进行此更正可以使我运行您的代码而不会出现错误。