Python ValueError:layer sequential_9的输入0与layer:：expected min_ndim=4不兼容，found ndim=3。收到完整形状：[无，无，无]_Python_Tensorflow_Keras_Deep Learning_Max Pooling

Python ValueError:layer sequential_9的输入0与layer:：expected min_ndim=4不兼容，found ndim=3。收到完整形状：[无，无，无]

python tensorflow keras deep-learning

Python ValueError:layer sequential_9的输入0与layer:：expected min_ndim=4不兼容，found ndim=3。收到完整形状：[无，无，无],python,tensorflow,keras,deep-learning,max-pooling,Python,Tensorflow,Keras,Deep Learning,Max Pooling,我正在努力解决分类问题。我不知道为什么会出现这样的错误： ValueError:layer sequential_9的输入0与layer:：expected min_ndim=4不兼容，found ndim=3。收到完整形状：[无，无，无] 这是主代码： model = createModel() filesPath=getFilesPathWithoutSeizure(i, indexPat) history=model.fit_generator(generate_arrays_for_tr

我正在努力解决分类问题。我不知道为什么会出现这样的错误：

ValueError:layer sequential_9的输入0与layer:：expected min_ndim=4不兼容，found ndim=3。收到完整形状：[无，无，无]

这是主代码：

model = createModel()
filesPath=getFilesPathWithoutSeizure(i, indexPat)
history=model.fit_generator(generate_arrays_for_training(indexPat, filesPath, end=75)##problem here
def createModel():
    input_shape=(1,11, 3840)
    model = Sequential()
    #C1
    model.add(Conv2D(16, (5, 5), strides=( 2, 2), padding='same',activation='relu',data_format= "channels_first", input_shape=input_shape))
    model.add(keras.layers.MaxPooling2D(pool_size=( 2, 2),data_format= "channels_first",  padding='same'))
    model.add(BatchNormalization())
    #C2
    model.add(Conv2D(32, ( 3, 3), strides=(1,1), padding='same',data_format= "channels_first",  activation='relu'))#incertezza se togliere padding
    model.add(keras.layers.MaxPooling2D(pool_size=(2, 2),data_format= "channels_first", padding='same'))
    model.add(BatchNormalization())
    #c3
    model.add(Conv2D(64, (3, 3), strides=( 1,1), padding='same',data_format= "channels_first",  activation='relu'))#incertezza se togliere padding
    model.add(keras.layers.MaxPooling2D(pool_size=(2, 2),data_format= "channels_first", padding='same'))
    model.add(BatchNormalization())
    model.add(Flatten())
    model.add(Dropout(0.5))
    model.add(Dense(256, activation='sigmoid'))
    model.add(Dropout(0.5))
    model.add(Dense(2, activation='softmax'))
    opt_adam = keras.optimizers.Adam(lr=0.00001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)
    model.compile(loss='categorical_crossentropy', optimizer=opt_adam, metrics=['accuracy'])
    
    return model

    history=model.fit_generator(generate_arrays_for_training(indexPat, filesPath, end=75), #end=75),#It take the first 75%
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/util/deprecation.py", line 324, in new_func
    return func(*args, **kwargs)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py", line 1815, in fit_generator
    return self.fit(
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py", line 108, in _method_wrapper
    return method(self, *args, **kwargs)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py", line 1098, in fit
    tmp_logs = train_function(iterator)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 780, in __call__
    result = self._call(*args, **kwds)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 823, in _call
    self._initialize(args, kwds, add_initializers_to=initializers)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 696, in _initialize
    self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 2855, in _get_concrete_function_internal_garbage_collected
    graph_function, _, _ = self._maybe_define_function(args, kwargs)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 3213, in _maybe_define_function
    graph_function = self._create_graph_function(args, kwargs)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 3065, in _create_graph_function
    func_graph_module.func_graph_from_py_func(
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py", line 986, in func_graph_from_py_func
    func_outputs = python_func(*func_args, **func_kwargs)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 600, in wrapped_fn
    return weak_wrapped_fn().__wrapped__(*args, **kwds)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py", line 973, in wrapper
    raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:

    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:806 train_function  *
        return step_function(self, iterator)
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:796 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:1211 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2585 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2945 _call_for_each_replica
        return fn(*args, **kwargs)
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:789 run_step  **
        outputs = model.train_step(data)
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:747 train_step
        y_pred = self(x, training=True)
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer.py:975 __call__
        input_spec.assert_input_compatibility(self.input_spec, inputs,
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/input_spec.py:191 assert_input_compatibility
        raise ValueError('Input ' + str(input_index) + ' of layer ' +

    ValueError: Input 0 of layer sequential_9 is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [None, None, None]

错误：

model = createModel()
filesPath=getFilesPathWithoutSeizure(i, indexPat)
history=model.fit_generator(generate_arrays_for_training(indexPat, filesPath, end=75)##problem here
def createModel():
    input_shape=(1,11, 3840)
    model = Sequential()
    #C1
    model.add(Conv2D(16, (5, 5), strides=( 2, 2), padding='same',activation='relu',data_format= "channels_first", input_shape=input_shape))
    model.add(keras.layers.MaxPooling2D(pool_size=( 2, 2),data_format= "channels_first",  padding='same'))
    model.add(BatchNormalization())
    #C2
    model.add(Conv2D(32, ( 3, 3), strides=(1,1), padding='same',data_format= "channels_first",  activation='relu'))#incertezza se togliere padding
    model.add(keras.layers.MaxPooling2D(pool_size=(2, 2),data_format= "channels_first", padding='same'))
    model.add(BatchNormalization())
    #c3
    model.add(Conv2D(64, (3, 3), strides=( 1,1), padding='same',data_format= "channels_first",  activation='relu'))#incertezza se togliere padding
    model.add(keras.layers.MaxPooling2D(pool_size=(2, 2),data_format= "channels_first", padding='same'))
    model.add(BatchNormalization())
    model.add(Flatten())
    model.add(Dropout(0.5))
    model.add(Dense(256, activation='sigmoid'))
    model.add(Dropout(0.5))
    model.add(Dense(2, activation='softmax'))
    opt_adam = keras.optimizers.Adam(lr=0.00001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)
    model.compile(loss='categorical_crossentropy', optimizer=opt_adam, metrics=['accuracy'])
    
    return model

    history=model.fit_generator(generate_arrays_for_training(indexPat, filesPath, end=75), #end=75),#It take the first 75%
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/util/deprecation.py", line 324, in new_func
    return func(*args, **kwargs)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py", line 1815, in fit_generator
    return self.fit(
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py", line 108, in _method_wrapper
    return method(self, *args, **kwargs)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py", line 1098, in fit
    tmp_logs = train_function(iterator)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 780, in __call__
    result = self._call(*args, **kwds)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 823, in _call
    self._initialize(args, kwds, add_initializers_to=initializers)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 696, in _initialize
    self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 2855, in _get_concrete_function_internal_garbage_collected
    graph_function, _, _ = self._maybe_define_function(args, kwargs)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 3213, in _maybe_define_function
    graph_function = self._create_graph_function(args, kwargs)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 3065, in _create_graph_function
    func_graph_module.func_graph_from_py_func(
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py", line 986, in func_graph_from_py_func
    func_outputs = python_func(*func_args, **func_kwargs)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 600, in wrapped_fn
    return weak_wrapped_fn().__wrapped__(*args, **kwds)
  File "/home/user1/.local/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py", line 973, in wrapper
    raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:

    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:806 train_function  *
        return step_function(self, iterator)
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:796 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:1211 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2585 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2945 _call_for_each_replica
        return fn(*args, **kwargs)
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:789 run_step  **
        outputs = model.train_step(data)
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:747 train_step
        y_pred = self(x, training=True)
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer.py:975 __call__
        input_spec.assert_input_compatibility(self.input_spec, inputs,
    /home/user1/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/input_spec.py:191 assert_input_compatibility
        raise ValueError('Input ' + str(input_index) + ' of layer ' +

    ValueError: Input 0 of layer sequential_9 is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [None, None, None]

Keras实际上总是隐藏第0个维度，也称为批处理维度。在您放置

input\u shape=（A，B，C）

的任何地方，实际上都不应该提到批处理维度，

（A，B，C）

应该是一个对象的形状（或者在您的情况下是图像）。例如，如果你说

input\u shape=（1,11,3840）

，那么它实际上意味着用于训练或预测的数据应该是一个形状的numpy数组，类似于

（7,1,11,3840）

，即训练在批处理中有

7个对象。所以这个7
是批量的大小，并行训练的对象数
因此，如果您的一个对象（例如图像）的形状是（113840）
，那么您必须在任何地方编写输入\u shape=（113840）
，而不必提及批量大小
为什么Keras隐藏第0个批次维度？因为keras期望不同大小的批处理，所以今天您可以提供7个对象，明天提供9个对象，并且相同的网络将同时适用于这两个对象。但是（113840）
的一个对象的形状永远不应该改变，并且由函数生成用于训练的数组（）生成的训练所提供的数据应该总是大小（BatchSize，113840）
，其中BatchSize
可以变化，您可以批量生成1
或7
或9
对象图像，每个形状（113840）

如果所有层的图像都应该是三维的，只有一个通道，那么您必须扩展生成的训练数据的dims，请执行X=np。使用展开dims（X，0）
，以便训练X数据的形状（1，1，11，3840）
，例如使用一个对象进行批处理，只有这样您才能使用输入\u shape=（1，11，3840）

此外，我还看到您正在到处写入data\u format=“channels\u first”
，默认情况下，所有函数都是channels\u last
，为了不到处写入，您可以重塑由generate\u array\u为\u training（）生成的数据，只要一次，如果它是X
形状（1,11,3840）
然后执行X=X.transpose（0,2,3,1）
。你的通道将成为最后一个维度
转置将一个维度移动到另一个位置。但是对于您的情况，因为您只有1
频道，所以您可以只重塑形状（1，1，11，3840）
的X
，而不是转置。可以通过X=X来重塑形状（1，11，3840，1）
，它将变成形状（1，11，3840，1）
。仅当您不想在任何地方编写“channels\u first”
时，才需要此功能，但如果您不想美化代码，则根本不需要转置/重塑
从我过去的记忆中，Keras不知何故不喜欢大小为1的维度，它基本上尝试在几个不同的函数中删除它们，即，如果Keras看到形状数组（1,2,1,3,1,4）
，它几乎总是尝试将其重塑为（2,3,4）
。因此，np.expand_dims（）
实际上被忽略了。在这种情况下，可能唯一的解决方案是至少生成一批大小为2的图像
您也可以阅读我的，尽管这有点不相关，但它可能有助于您理解Keras中的训练/预测是如何工作的，尤其是您可以阅读编号为1-12
的最后几段
更新：由于下一次修改的帮助，问题似乎得到了解决：
在数据生成函数中，需要进行两次DIM扩展，即X=np.expand_-dims（np.expand_-dims（X，0），0）


在数据生成函数中，需要另一个X=X.transpose（0，2，3，1）


网络输入形状的代码设置为input\u shape=（113840,1）


在网络代码中，删除了所有子字符串data\u format=“channels\u first”


哪一行代码触发了该异常？这行代码在你提供的代码中吗？你能不能把全部的异常放进去？它没有起始部分（跳过第一行）。因此，我们无法看到哪一行代码触发了异常。通过函数generate\u arrays\u for_training（）
，生成的numpy数组的形状是什么？@Arty是的，这是行history=model.fit\u生成器（generate\u arrays\u for_training）（indexPat，filepath，end=75）##这里的问题
，由generate_arrays\u for_training（）生成的numpy数组的形状
（1,113840）@Edaildiz我明白了原因，我现在就写一个答案。非常感谢您的解决方案。但是我不明白为什么我要做X=X.transpose（0,2,3,1）
？？@Edayildiz转置可以将一个维度移动到另一个位置。但是，对于您的情况，是的，因为您只有一个通道，而不是转置，您可以只重塑形状（1,1,11,3840）
的XX=X。重塑（1,11,3840,1）
它将变成形状（1,11,3840,1）
。如果您不想先编写“channels\u”
，这一切都是必需的，但如果您不想美化代码，则根本不需要转置/重塑！非常好，因此如果我编写“channels\u last”，那么我的输入形状应该是input\u shape=（1,113840,1）
？？不幸的是，通过扩展dimension@Edayildiz我想可能是这样的，至少我从过去的记忆中记得Keras错误地处理ba