我正在处理一个简单的多层感知器模型。模型拟合的输入形状如下所示。
fea_train_np.shape = (6000, 1, 15, 21, 512)fea_val_np.shape = (1500, 1, 15, 21, 512)y_train_np.shape = (6000, 2)y_val_np.shape = (1500, 2)这是我正在处理的多层感知器。最后一层使用线性激活函数，因为我想进行回归而不是分类。
mlp1 = keras.Sequential( [ layers.Flatten(), layers.Dense(256, activation='relu'), # 添加一个具有16个单元和relu激活函数的全连接层作为隐藏层 layers.Dense(10, activation='linear') ], )mlp1.compile(optimizer = optimizers.Adam(learning_rate = 0.001), loss = keras.losses.MeanSquaredError(), metrics = [keras.metrics.MeanSquaredError()])mlp = mlp1.fit(fea_train_np, y_train_np, epochs=20, batch_size=8, validation_data=(fea_val_np, y_val_np))result = mlp.predict(fea_val_np, y_val_np)当我试图拟合我的模型时，我得到了这个错误：
Train on 6000 samples, validate on 1500 samplesEpoch 1/20 8/6000 [..............................] - ETA: 12s---------------------------------------------------------------------------InvalidArgumentError Traceback (most recent call last)C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\framework\ops.py in _create_c_op(graph, node_def, inputs, control_inputs) 1618 try:-> 1619 c_op = c_api.TF_FinishOperation(op_desc) 1620 except errors.InvalidArgumentError as e:InvalidArgumentError: Dimensions must be equal, but are 10 and 2 for 'loss/output_1_loss/SquaredDifference' (op: 'SquaredDifference') with input shapes: [8,10], [8,2].During handling of the above exception, another exception occurred:ValueError Traceback (most recent call last)<ipython-input-32-37335a6a8cd3> in <module> 11 metrics = [keras.metrics.MeanSquaredError()]) 12 ---> 13 mlp = mlp1.fit(fea_train_np, y_train_np, epochs=20, batch_size=8, validation_data=(fea_val_np, y_val_np)) 14 result = mlp.predict(fea_val_np, y_val_np)C:\ForHDD\Anaconda\envs\CV\lib\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) 817 max_queue_size=max_queue_size, 818 workers=workers,--> 819 use_multiprocessing=use_multiprocessing) 820 821 def evaluate(self,C:\ForHDD\Anaconda\envs\CV\lib\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, max_queue_size, workers, use_multiprocessing, **kwargs) 340 mode=ModeKeys.TRAIN, 341 training_context=training_context,--> 342 total_epochs=epochs) 343 cbks.make_logs(model, epoch_logs, training_result, ModeKeys.TRAIN) 344 C:\ForHDD\Anaconda\envs\CV\lib\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) 126 step=step, mode=mode, size=current_batch_size) as batch_logs: 127 try:--> 128 batch_outs = execution_function(iterator) 129 except (StopIteration, errors.OutOfRangeError): 130 # TODO(kaftan): File bug about tf function and errors.OutOfRangeError?C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in execution_function(input_fn) 96 # `numpy` translates Tensors to values in Eager mode. 97 return nest.map_structure(_non_none_constant_value,---> 98 distributed_function(input_fn)) 99 100 return execution_functionC:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\eager\def_function.py in __call__(self, *args, **kwds) 566 xla_context.Exit() 567 else:--> 568 result = self._call(*args, **kwds) 569 570 if tracing_count == self._get_tracing_count():C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\eager\def_function.py in _call(self, *args, **kwds) 613 # This is the first call of __call__, so we have to initialize. 614 initializers = []--> 615 self._initialize(args, kwds, add_initializers_to=initializers) 616 finally: 617 # At this point we know that the initialization is complete (or lessC:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to) 495 self._concrete_stateful_fn = ( 496 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access--> 497 *args, **kwds)) 498 499 def invalid_creator_scope(*unused_args, **unused_kwds):C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs) 2387 args, kwargs = None, None 2388 with self._lock:-> 2389 graph_function, _, _ = self._maybe_define_function(args, kwargs) 2390 return graph_function 2391 C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\eager\function.py in _maybe_define_function(self, args, kwargs) 2701 2702 self._function_cache.missed.add(call_context_key)-> 2703 graph_function = self._create_graph_function(args, kwargs) 2704 self._function_cache.primary[cache_key] = graph_function 2705 return graph_function, args, kwargsC:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes) 2591 arg_names=arg_names, 2592 override_flat_arg_shapes=override_flat_arg_shapes,-> 2593 capture_by_value=self._capture_by_value), 2594 self._function_attributes, 2595 # Tell the ConcreteFunction to clean up its graph once it goes out ofC:\ForHDD\Anaconda\envs\CV\lib\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) 976 converted_func) 977 --> 978 func_outputs = python_func(*func_args, **func_kwargs) 979 980 # invariant: `func_outputs` contains only Tensors, CompositeTensors,C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\eager\def_function.py in wrapped_fn(*args, **kwds) 437 # __wrapped__ allows AutoGraph to swap in a converted function. We give 438 # the function a weak reference to itself to avoid a reference cycle.--> 439 return weak_wrapped_fn().__wrapped__(*args, **kwds) 440 weak_wrapped_fn = weakref.ref(wrapped_fn) 441 C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in distributed_function(input_iterator) 83 args = _prepare_feed_values(model, input_iterator, mode, strategy) 84 outputs = strategy.experimental_run_v2(---> 85 per_replica_function, args=args) 86 # Out of PerReplica outputs reduce or pick values to return. 87 all_outputs = dist_utils.unwrap_output_dict(C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\distribute\distribute_lib.py in experimental_run_v2(self, fn, args, kwargs) 761 fn = autograph.tf_convert(fn, ag_ctx.control_status_ctx(), 762 convert_by_default=False)--> 763 return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs) 764 765 def reduce(self, reduce_op, value, axis):C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\distribute\distribute_lib.py in call_for_each_replica(self, fn, args, kwargs) 1817 kwargs = {} 1818 with self._container_strategy().scope():-> 1819 return self._call_for_each_replica(fn, args, kwargs) 1820 1821 def _call_for_each_replica(self, fn, args, kwargs):C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\distribute\distribute_lib.py in _call_for_each_replica(self, fn, args, kwargs) 2162 self._container_strategy(), 2163 replica_id_in_sync_group=constant_op.constant(0, dtypes.int32)):-> 2164 return fn(*args, **kwargs) 2165 2166 def _reduce_to(self, reduce_op, value, destinations):C:\ForHDD\Anaconda\envs\CV\lib\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):C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in train_on_batch(model, x, y, sample_weight, class_weight, reset_metrics, standalone) 431 y, 432 sample_weights=sample_weights,--> 433 output_loss_metrics=model._output_loss_metrics) 434 435 if reset_metrics:C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\engine\training_eager.py in train_on_batch(model, inputs, targets, sample_weights, output_loss_metrics) 310 sample_weights=sample_weights, 311 training=True,--> 312 output_loss_metrics=output_loss_metrics)) 313 if not isinstance(outs, list): 314 outs = [outs]C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\engine\training_eager.py in _process_single_batch(model, inputs, targets, output_loss_metrics, sample_weights, training) 251 output_loss_metrics=output_loss_metrics, 252 sample_weights=sample_weights,--> 253 training=training)) 254 if total_loss is None: 255 raise ValueError('The model cannot be run 'C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\engine\training_eager.py in _model_loss(model, inputs, targets, output_loss_metrics, sample_weights, training) 165 166 if hasattr(loss_fn, 'reduction'):--> 167 per_sample_losses = loss_fn.call(targets[i], outs[i]) 168 weighted_losses = losses_utils.compute_weighted_loss( 169 per_sample_losses,C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\losses.py in call(self, y_true, y_pred) 219 y_pred, y_true = tf_losses_util.squeeze_or_expand_dimensions( 220 y_pred, y_true)--> 221 return self.fn(y_true, y_pred, **self._fn_kwargs) 222 223 def get_config(self):C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\losses.py in mean_squared_error(y_true, y_pred) 769 y_pred = ops.convert_to_tensor(y_pred) 770 y_true = math_ops.cast(y_true, y_pred.dtype)--> 771 return K.mean(math_ops.squared_difference(y_pred, y_true), axis=-1) 772 773 C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\ops\gen_math_ops.py in squared_difference(x, y, name) 10037 try: 10038 _, _, _op, _outputs = _op_def_library._apply_op_helper(> 10039 "SquaredDifference", x=x, y=y, name=name) 10040 except (TypeError, ValueError): 10041 result = _dispatch.dispatch(C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\framework\op_def_library.py in _apply_op_helper(op_type_name, name, **keywords) 740 op = g._create_op_internal(op_type_name, inputs, dtypes=None, 741 name=scope, input_types=input_types,--> 742 attrs=attr_protos, op_def=op_def) 743 744 # `outputs` is returned as a separate return value so that the outputC:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\framework\func_graph.py in _create_op_internal(self, op_type, inputs, dtypes, input_types, name, attrs, op_def, compute_device) 593 return super(FuncGraph, self)._create_op_internal( # pylint: disable=protected-access 594 op_type, inputs, dtypes, input_types, name, attrs, op_def,--> 595 compute_device) 596 597 def capture(self, tensor, name=None, shape=None):C:\ForHDD\Anaconda\envs\CV\lib\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) 3320 input_types=input_types, 3321 original_op=self._default_original_op,-> 3322 op_def=op_def) 3323 self._create_op_helper(ret, compute_device=compute_device) 3324 return retC:\ForHDD\Anaconda\envs\CV\lib\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) 1784 op_def, inputs, node_def.attr) 1785 self._c_op = _create_c_op(self._graph, node_def, grouped_inputs,-> 1786 control_input_ops) 1787 name = compat.as_str(node_def.name) 1788 # pylint: enable=protected-accessC:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\framework\ops.py in _create_c_op(graph, node_def, inputs, control_inputs) 1620 except errors.InvalidArgumentError as e: 1621 # Convert to ValueError for backwards compatibility.-> 1622 raise ValueError(str(e)) 1623 1624 return c_opValueError: Dimensions must be equal, but are 10 and 2 for 'loss/output_1_loss/SquaredDifference' (op: 'SquaredDifference') with input shapes: [8,10], [8,2].我尝试将 loss = keras.losses.MeanSquaredError() 改为 loss = [keras.losses.MeanSquaredError()]，但错误仍然相同。
有人能告诉我我哪里做错了吗？任何建议都将不胜感激。
回答：
我认为问题不在于你使用的损失函数，而在于你使用的数据的维度。我看到 y_val_np.shape 有2个维度（shape[1]），但在模型 mlp1 中，最后一层返回的输出维度为10。如果这对你有帮助，并且这是你需要做的，我相信将 mlp1 的最后一层的维度从10改为2可以解决这个问题
