尝试将以前训练过的tf.keras模型用作预训练，但得到“ ValueError:图层density_3的输入0与该布局不兼容 - python

我创建并训练了一个模型，该模型可以将发票字符串中的啤酒名称分类为字符的整数序列。

batch_size = 512  # Batch size for training.
epochs = 5  # Number of epochs to train for.

model = Sequential()
model.add(Dense(512, activation='relu'))
model.add(Dropout(rate=0.2, noise_shape=None, seed=None))
model.add(Dense(512, activation='relu'))
model.add(Dropout(rate=0.2, noise_shape=None, seed=None))
model.add(Dense(train_beer['product_name'].nunique(), activation='softmax'))

optimizer = RMSprop(learning_rate=0.001)
model.compile(loss=tf.keras.losses.CategoricalCrossentropy(), optimizer=optimizer, metrics=['accuracy'])
model.fit(train_encoded, train_labels, epochs=epochs, batch_size=batch_size, validation_data=(test_encoded,test_labels))

现在，我想将前两层用作其他模型的预训练，因此我删除了激活层并添加了一个新层，然后重新编译了该模型。 （注意，出于测试目的，我重新添加了同一行

model.pop()
model.add(Dense(train_beer['product_name'].nunique(), activation='softmax'))
optimizer = RMSprop(learning_rate=0.001)
model.compile(loss=tf.keras.losses.CategoricalCrossentropy(), optimizer=optimizer, metrics=['accuracy'])
batch_size = 512  # Batch size for training.
epochs = 5  # Number of epochs to train for.

model.fit(train_encoded, train_labels, epochs=epochs, batch_size=batch_size, validation_data=(test_encoded,test_labels))

但是我得到了错误：

 Train on 313213 samples, validate on 16323 samples Epoch 1/5    512/313213 [..............................] - ETA: 29s
--------------------------------------------------------------------------- ValueError                                Traceback (most recent call last) <ipython-input-13-e341e0cd9a82> in <module>
      2 epochs = 5  # Number of epochs to train for.
      3 
----> 4 model.fit(train_encoded, train_labels, epochs=epochs, batch_size=batch_size, validation_data=(test_encoded,test_labels))

~\.conda\envs\fintech_ml\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)
    726         max_queue_size=max_queue_size,
    727         workers=workers,
--> 728         use_multiprocessing=use_multiprocessing)
    729 
    730   def evaluate(self,

~\.conda\envs\fintech_ml\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, **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 

~\.conda\envs\fintech_ml\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)
    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?

~\.conda\envs\fintech_ml\lib\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

~\.conda\envs\fintech_ml\lib\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()

~\.conda\envs\fintech_ml\lib\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

~\.conda\envs\fintech_ml\lib\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):

~\.conda\envs\fintech_ml\lib\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 

~\.conda\envs\fintech_ml\lib\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

~\.conda\envs\fintech_ml\lib\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

~\.conda\envs\fintech_ml\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)
    913                                           converted_func)
    914 
--> 915       func_outputs = python_func(*func_args, **func_kwargs)
    916 
    917       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

~\.conda\envs\fintech_ml\lib\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 

~\.conda\envs\fintech_ml\lib\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(

~\.conda\envs\fintech_ml\lib\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):

~\.conda\envs\fintech_ml\lib\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):

~\.conda\envs\fintech_ml\lib\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):

~\.conda\envs\fintech_ml\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):

~\.conda\envs\fintech_ml\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)
    262       y,
    263       sample_weights=sample_weights,
--> 264       output_loss_metrics=model._output_loss_metrics)
    265 
    266   if reset_metrics:

~\.conda\envs\fintech_ml\lib\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]

~\.conda\envs\fintech_ml\lib\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 '

~\.conda\envs\fintech_ml\lib\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 

~\.conda\envs\fintech_ml\lib\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:

~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\sequential.py in call(self, inputs, training, mask)
    268         kwargs['training'] = training
    269 
--> 270       outputs = layer(inputs, **kwargs)
    271 
    272       # `outputs` will be the inputs to the next layer.

~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\base_layer.py in __call__(self, inputs, *args, **kwargs)
    810         # are casted, not before.
    811         input_spec.assert_input_compatibility(self.input_spec, inputs,
--> 812                                               self.name)
    813         graph = backend.get_graph()
    814         with graph.as_default(), backend.name_scope(self._name_scope()):

~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
    211                 ' incompatible with the layer: expected axis ' + str(axis) +
    212                 ' of input shape to have value ' + str(value) +
--> 213                 ' but received input with shape ' + str(shape))
    214     # Check shape.
    215     if spec.shape is not None:

ValueError: Input 0 of layer dense_3 is incompatible with the layer: expected axis -1 of input shape to have value 6022 but received input with shape [None, 512]

python大神给出的解决方案

我真的不能告诉你为什么会发生这种情况（我可能不得不研究源代码）。我怀疑这些层在线下某处被错误地重新布线。但是您可以执行以下操作以使此工作正常进行。

new_model = Sequential()
for l in model.layers[:-1]:
  new_model.add(l)
new_model.add(Dense(100, activation='softmax'))

Python-熊猫描述了抛出错误:无法散列的类型“ dict” - python

更新：我正在使用“ Socrata开源API”中的一些示例代码。我在代码中注意到以下注释：# First 2000 results, returned as JSON from API / converted to Python # list of dictionaries by sodapy. 我不熟悉JSON。我已经下载了一个数据集，并创建了一个包含大量…

子条件的python条件覆盖 - python

我试图找到一个python代码覆盖率工具，该工具可以衡量语句中是否包含子表达式：例如，我想看看下面的示例是否涵盖了condition1 / condition2 / condtion3？if condition1 or condition2 or condition3: x = true_value python大神给出的解决方案 对此的唯一合理答案是：当前…

USB设备发行 - python

我目前正在使用PyUSB。由于我不熟悉USB，所以我不知道如何执行以下操作。我已经从Python PyUSB成功连接到我的USB设备硬件。在代码中，我需要重置USB设备硬件。通过向硬件发送命令来完成。现在，在硬件重置后，我想从Python PyUSB释放当前的USB设备。然后，我想在重置后将其重新连接到USB设备硬件。请让我知道，如何释放USB设备连接和接口…

在Pytorch中重复张量的特定列 - python

我有一个大小为X的pytorch张量m x n和一个长度为num_repeats的非负整数n列表（假定sum（num_repeats）> 0）。在forward（）方法中，我想创建一个大小为X_dup的张量m x sum(num_repeats)，其中i的列X重复num_repeats[i]次。张量X_dup将在forward（）方法的下游使用，因此需…

PyCharm中Django的文档字符串中未解决的引用 - python

我在Django的专案中使用Google Style Python Docstrings like in this Example。当我创建一个类并在文档字符串中使用属性符号时，Pycharm总是说-“未解决的引用”。class Post(models.Model): """ Class for posts. Attribute…