ValueError：层equential_9的输入0与层不兼容：：预期min_ndim = 4，发现ndim = 3。收到完整形状：[无，无，无]

我正在尝试解决分类问题。我不知道为什么会收到此错误：

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]

这是主要代码：

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

Error:

    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0-th维度，也称为batch方面。无论你放置的地方input_shape = (A, B, C)实际上不应该在那里提到批次尺寸，(A, B, C)应该是一个物体的形状（或者在你的情况下是图像）。例如，如果你说input_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形状类似于(7, 1,11, 3840)，即训练有7批次中的对象。所以这7是批量大小，并行训练的对象数量。

因此，如果您的一个对象（例如图像）具有形状(11, 3840)那么你必须写input_shape = (11, 3840)无处不在，更不用说批量大小了。

Keras 为何隐藏0-th批量维度？因为 keras 期望批量大小不同，所以今天您可以提供 7 个对象，明天提供 9 个对象，并且相同的网络将适用于这两个对象。但是一个物体的形状是(11, 3840)永远不应该改变并为函数生成的训练提供数据generate_arrays_for_training()应该始终是大小(BatchSize, 11, 3840), where BatchSize可能会有所不同，您可能会生成一批1 or 7 or 9每个形状的物体图像(11, 3840).

如果所有层的图像应该是 3 维的，具有 1 个通道，那么您必须扩展生成的训练数据的维度，执行X = np.expand_dims(X, 0) using 这个功能 https://numpy.org/doc/stable/reference/generated/numpy.expand_dims.html这样你的训练 X 数据就成型了(1, 1, 11, 3840)，例如批处理 1 个对象，只有这样你才能拥有input_shape = (1, 11, 3840).

我还看到你到处写data_format= "channels_first"，默认情况下所有函数都是channels_last，为了不到处写这个，你可以重塑你生成的generate_arrays_for_training()数据仅一次，如果是的话X形状的(1, 1, 11, 3840)那么你就做X = X.transpose(0, 2, 3, 1)。你的渠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。但对于你的情况，因为你刚刚1通道而不是转置，您可以只重塑例如X形状的(1, 1, 11, 3840)可以通过以下方式重塑X = X.reshape(1, 11, 3840, 1)它将变得有形状(1, 11, 3840, 1)。仅当您不想写时才需要"channels_first"到处都是，但如果你不想美化你的代码，那么根本不需要转置/重塑！

我记得过去 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)它几乎总是试图将其重塑为(2, 3, 4). Thus np.expand_dims()实际上被忽略了。在这种情况下，唯一的解决方案可能是至少生成大小为 2 的图像批次。

您也可以阅读我的长答案 https://stackoverflow.com/a/64101952/941531，虽然有点不相关，但它可能会帮助您理解 Keras 中的训练/预测是如何工作的，特别是您可以阅读最后几段，编号为1-12.

Update：由于下一个修改的帮助，问题似乎得到了解决：

1. 在数据生成函数中，需要进行两次扩展dim，即X = np.expand_dims(np.expand_dims(X, 0), 0).

2. 在数据生成功能中需要另一个X = X.transpose(0, 2, 3, 1).

3. 在网络输入形状的代码中设置为input_shape = (11, 3840, 1).

4. 在网络代码中所有子字符串data_format = "channels_first"被删除。