我试图了解如何将tensorflowsDataset用于简单的回归模型，而不是用单独np.array的训练输入和输出来喂养它。
这是一个简单的独立示例：
import tensorflow as tf
import numpy as np
# create training data
X_train_set = np.random.random(size=(1000,10))
y_train_set = np.random.random(size=(1000))
# convert to dataset
train_dataset = tf.data.Dataset.from_tensor_slices((X_train_set, y_train_set))
my_model = tf.keras.Sequential([
tf.keras.layers.Input(shape=(10,)),
tf.keras.layers.Dense(100, activation='relu'),
tf.keras.layers.Dense(10, activation='relu'),
tf.keras.layers.Dense(1)
])
my_model.compile(optimizer=tf.optimizers.Adam(learning_rate=0.1),
loss='mean_absolute_error')
# train with np.array data
my_model.fit(X_train_set,y_train_set,epochs=2)
print('Success Training 1\n')
# train with datasets
my_model.fit(train_dataset,epochs=2)
print('Success Training 2\n')
运行该示例my_model.fit(X_train_set,y_train_set,epochs=2)确实有效。但是，my_model.fit(train_dataset,epochs=2)会引发错误：
Epoch 1/2
32/32 [==============================] - 0s 2ms/step - loss: 0.3424
Epoch 2/2
32/32 [==============================] - 0s 2ms/step - loss: 0.2501
Success Training 1
Epoch 1/2
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-82-31d0c7e586d8> in <module>
21
22 # train with datasets
---> 23 my_model.fit(train_dataset,epochs=2)
24 print('Success Training 2\n')
~/virtualEnv/py3_TF23/lib/python3.6/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.
~/virtualEnv/py3_TF23/lib/python3.6/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()
~/virtualEnv/py3_TF23/lib/python3.6/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()
~/virtualEnv/py3_TF23/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
805 # In this case we have created variables on the first call, so we run the
806 # defunned version which is guaranteed to never create variables.
--> 807 return self._stateless_fn(*args, **kwds) # pylint: disable=not-callable
808 elif self._stateful_fn is not None:
809 # Release the lock early so that multiple threads can perform the call
~/virtualEnv/py3_TF23/lib/python3.6/site-packages/tensorflow/python/eager/function.py in __call__(self, *args, **kwargs)
2826 """Calls a graph function specialized to the inputs."""
2827 with self._lock:
-> 2828 graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
2829 return graph_function._filtered_call(args, kwargs) # pylint: disable=protected-access
2830
~/virtualEnv/py3_TF23/lib/python3.6/site-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
3208 and self.input_signature is None
3209 and call_context_key in self._function_cache.missed):
-> 3210 return self._define_function_with_shape_relaxation(args, kwargs)
3211
3212 self._function_cache.missed.add(call_context_key)
~/virtualEnv/py3_TF23/lib/python3.6/site-packages/tensorflow/python/eager/function.py in _define_function_with_shape_relaxation(self, args, kwargs)
3140
3141 graph_function = self._create_graph_function(
-> 3142 args, kwargs, override_flat_arg_shapes=relaxed_arg_shapes)
3143 self._function_cache.arg_relaxed[rank_only_cache_key] = graph_function
3144
~/virtualEnv/py3_TF23/lib/python3.6/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,
~/virtualEnv/py3_TF23/lib/python3.6/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,
~/virtualEnv/py3_TF23/lib/python3.6/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
~/virtualEnv/py3_TF23/lib/python3.6/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:
/home/max/virtualEnv/py3_TF23/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py:806 train_function *
return step_function(self, iterator)
/home/max/virtualEnv/py3_TF23/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py:796 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/home/max/virtualEnv/py3_TF23/lib/python3.6/site-packages/tensorflow/python/distribute/distribute_lib.py:1211 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/home/max/virtualEnv/py3_TF23/lib/python3.6/site-packages/tensorflow/python/distribute/distribute_lib.py:2585 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/home/max/virtualEnv/py3_TF23/lib/python3.6/site-packages/tensorflow/python/distribute/distribute_lib.py:2945 _call_for_each_replica
return fn(*args, **kwargs)
/home/max/virtualEnv/py3_TF23/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py:789 run_step **
outputs = model.train_step(data)
/home/max/virtualEnv/py3_TF23/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py:747 train_step
y_pred = self(x, training=True)
/home/max/virtualEnv/py3_TF23/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py:976 __call__
self.name)
/home/max/virtualEnv/py3_TF23/lib/python3.6/site-packages/tensorflow/python/keras/engine/input_spec.py:216 assert_input_compatibility
' but received input with shape ' + str(shape))
ValueError: Input 0 of layer sequential_26 is incompatible with the layer: expected axis -1 of input shape to have value 10 but received input with shape [10, 1]
问题是：我必须创建一个不同的Sequential模型还是我的train_dataset完全不正确？我会假设 anp.array应该可以Dataset在训练步骤中与 a 交换？