我正在尝试构建一个使用函数式API的模型，该模型可以处理多个输入和多个输出。我按照这个指南创建了代码。
def create_model_multiple(): input1 = tf.keras.Input(shape=(13,), name = 'I1') input2 = tf.keras.Input(shape=(6,), name = 'I2') hidden1 = tf.keras.layers.Dense(units = 4, activation='relu')(input1) hidden2 = tf.keras.layers.Dense(units = 4, activation='relu')(input2) merge = tf.keras.layers.concatenate([hidden1, hidden2]) hidden3 = tf.keras.layers.Dense(units = 3, activation='relu')(merge) output1 = tf.keras.layers.Dense(units = 2, activation='softmax', name ='O1')(hidden3) output2 = tf.keras.layers.Dense(units = 2, activation='softmax', name = 'O2')(hidden3) model = tf.keras.models.Model(inputs = [input1,input2], outputs = [output1,output2]) model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']) return model我的model.fit命令如下所示：
history = model.fit({'I1':train_data, 'I2':new_train_data}, {'O1':train_labels, 'O2': new_target_label}, validation_data=(val_data,val_labels), epochs=100, verbose = 1)输入数据的形状如下：
train_data是(192,13)
new_train_data是(192,6)
train-labels,new_target_labels是(192,)
代码运行了几步后就出现了这个错误：
Epoch 1/1001/6 [====>.........................] - ETA: 0s - loss: 360.3317 - O1_loss: 127.8019 - O2_loss: 232.5298 - O1_accuracy: 0.3438 - O2_accuracy: 0.4062---------------------------------------------------------------------------AssertionError Traceback (most recent call last)<ipython-input-29-db61ad0a9d8b> in <module> 3 validation_data=(val_data,val_labels), 4 epochs=100,----> 5 verbose = 1)c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\keras\engine\training.py in _method_wrapper(self, *args, **kwargs) 64 def _method_wrapper(self, *args, **kwargs): 65 if not self._in_multi_worker_mode(): # pylint: disable=protected-access---> 66 return method(self, *args, **kwargs) 67 68 # Running inside `run_distribute_coordinator` already.c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\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) 870 workers=workers, 871 use_multiprocessing=use_multiprocessing,--> 872 return_dict=True) 873 val_logs = {'val_' + name: val for name, val in val_logs.items()} 874 epoch_logs.update(val_logs)c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\keras\engine\training.py in _method_wrapper(self, *args, **kwargs) 64 def _method_wrapper(self, *args, **kwargs): 65 if not self._in_multi_worker_mode(): # pylint: disable=protected-access---> 66 return method(self, *args, **kwargs) 67 68 # Running inside `run_distribute_coordinator` already.c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\keras\engine\training.py in evaluate(self, x, y, batch_size, verbose, sample_weight, steps, callbacks, max_queue_size, workers, use_multiprocessing, return_dict) 1079 step_num=step): 1080 callbacks.on_test_batch_begin(step)-> 1081 tmp_logs = test_function(iterator) 1082 # Catch OutOfRangeError for Datasets of unknown size. 1083 # This blocks until the batch has finished executing.c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds) 578 xla_context.Exit() 579 else:--> 580 result = self._call(*args, **kwds) 581 582 if tracing_count == self._get_tracing_count():c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds) 616 # In this case we have not created variables on the first call. So we can 617 # run the first trace but we should fail if variables are created.--> 618 results = self._stateful_fn(*args, **kwds) 619 if self._created_variables: 620 raise ValueError("Creating variables on a non-first call to a function"c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\eager\function.py in __call__(self, *args, **kwargs) 2417 """Calls a graph function specialized to the inputs.""" 2418 with self._lock:-> 2419 graph_function, args, kwargs = self._maybe_define_function(args, kwargs) 2420 return graph_function._filtered_call(args, kwargs) # pylint: disable=protected-access 2421 c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs) 2772 and self.input_signature is None 2773 and call_context_key in self._function_cache.missed):-> 2774 return self._define_function_with_shape_relaxation(args, kwargs) 2775 2776 self._function_cache.missed.add(call_context_key)c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\eager\function.py in _define_function_with_shape_relaxation(self, args, kwargs) 2704 relaxed_arg_shapes) 2705 graph_function = self._create_graph_function(-> 2706 args, kwargs, override_flat_arg_shapes=relaxed_arg_shapes) 2707 self._function_cache.arg_relaxed[rank_only_cache_key] = graph_function 2708 c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes) 2665 arg_names=arg_names, 2666 override_flat_arg_shapes=override_flat_arg_shapes,-> 2667 capture_by_value=self._capture_by_value), 2668 self._function_attributes, 2669 # Tell the ConcreteFunction to clean up its graph once it goes out ofc:\users\aniket\documents\aniket\learning-ml\ml_env\lib\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) 979 _, original_func = tf_decorator.unwrap(python_func) 980 --> 981 func_outputs = python_func(*func_args, **func_kwargs) 982 983 # invariant: `func_outputs` contains only Tensors, CompositeTensors,c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds) 439 # __wrapped__ allows AutoGraph to swap in a converted function. We give 440 # the function a weak reference to itself to avoid a reference cycle.--> 441 return weak_wrapped_fn().__wrapped__(*args, **kwds) 442 weak_wrapped_fn = weakref.ref(wrapped_fn) 443 c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs) 966 except Exception as e: # pylint:disable=broad-except 967 if hasattr(e, "ag_error_metadata"):--> 968 raise e.ag_error_metadata.to_exception(e) 969 else: 970 raiseAssertionError: in user code: c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\keras\engine\training.py:941 test_function * outputs = self.distribute_strategy.run( c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:951 run ** return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs) c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2290 call_for_each_replica return self._call_for_each_replica(fn, args, kwargs) c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2649 _call_for_each_replica return fn(*args, **kwargs) c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\keras\engine\training.py:909 test_step ** y_pred = self(x, training=False) c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:927 __call__ outputs = call_fn(cast_inputs, *args, **kwargs) c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\keras\engine\network.py:719 call convert_kwargs_to_constants=base_layer_utils.call_context().saving) c:\users\aniket\documents\aniket\learning-ml\ml_env\lib\site-packages\tensorflow\python\keras\engine\network.py:899 _run_internal_graph assert str(id(x)) in tensor_dict, 'Could not compute output ' + str(x) AssertionError: Could not compute output Tensor("O1_6/Identity:0", shape=(None, 2), dtype=float32)包含完整代码的jupyter-notebook在这里：链接
回答：
你必须以正确的格式提供验证数据（就像你的训练数据一样）。你需要传递两个输入数据和两个目标…你只传递了一个
这是一个示例代码：
def create_model_multiple(): input1 = tf.keras.Input(shape=(13,), name = 'I1') input2 = tf.keras.Input(shape=(6,), name = 'I2') hidden1 = tf.keras.layers.Dense(units = 4, activation='relu')(input1) hidden2 = tf.keras.layers.Dense(units = 4, activation='relu')(input2) merge = tf.keras.layers.concatenate([hidden1, hidden2]) hidden3 = tf.keras.layers.Dense(units = 3, activation='relu')(merge) output1 = tf.keras.layers.Dense(units = 2, activation='softmax', name ='O1')(hidden3) output2 = tf.keras.layers.Dense(units = 2, activation='softmax', name = 'O2')(hidden3) model = tf.keras.models.Model(inputs = [input1,input2], outputs = [output1,output2]) model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']) return modelx1 = np.random.uniform(0,1, (190,13))x2 = np.random.uniform(0,1, (190,6))val_x1 = np.random.uniform(0,1, (50,13))val_x2 = np.random.uniform(0,1, (50,6))y1 = np.random.randint(0,2, 190)y2 = np.random.randint(0,2, 190)val_y1 = np.random.randint(0,2, 50)val_y2 = np.random.randint(0,2, 50)model = create_model_multiple()history = model.fit({'I1':x1, 'I2':x2}, {'O1':y1, 'O2': y2}, validation_data=([val_x1,val_x2], [val_y1,val_y2]), # <========= epochs=100, verbose = 1)