ValueError：layersequence_9 的输入 0 与 layer 不兼容：：预期 min_ndim=4，发现 ndim=3。收到的完整形状：[无，无，无]

Question

我正在尝试解决分类问题。我不知道为什么会出现此错误：

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

错误：

    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]

Answer 1

Keras 实际上总是隐藏0-th 维度，也称为batch 维度。在您放置input_shape = (A, B, C) 的任何地方，实际上不应提及批处理尺寸，(A, B, C) 应该是一个对象的形状（或您的情况下的图像）。例如，如果您说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) 的numpy 数组，即训练批次中有7 对象。所以这个7 是批量大小，要并行训练的对象数量。

因此，如果您的一个对象（例如图像）的形状为 (11, 3840)，那么您必须在任何地方都写上 input_shape = (11, 3840)，而无需提及批量大小。

为什么 Keras 隐藏了0-th 批量维度？因为 keras 期望不同大小的批次，今天你可以提供 7 个对象，明天 9 个对象和相同的网络将适用于两者。但是(11, 3840) 的一个对象的形状永远不会改变，并且为函数generate_arrays_for_training() 生成的训练提供的数据应该始终是(BatchSize, 11, 3840) 的大小，其中BatchSize 可以变化，您可以生成一批1 或@ 987654339@ 或 9 objects-images 每个形状 (11, 3840)。

如果您的所有层的图像都应该是 3 维的，有 1 个通道，那么您必须扩展生成的训练数据的尺寸，使用 this function 执行 X = np.expand_dims(X, 0) 以便您的训练 X 数据形状为 (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由generate_arrays_for_training()生成的数据一次，如果它是@987654348 @ 形状 (1, 1, 11, 3840) 然后你做 X = X.transpose(0, 2, 3, 1)。而你的频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，而不是转置，您可以重塑例如形状为(1, 1, 11, 3840) 的X 可以被X = X.reshape(1, 11, 3840, 1) 重新调整形状，它会变成(1, 11, 3840, 1) 的形状。仅当您不想到处写 "channels_first" 时才需要这样做，但如果您不想美化代码，则根本不需要转置/重塑！

我记得我过去 Keras 不喜欢尺寸为 1 的尺寸，它基本上会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)。因此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一批大小为 2 的图像。

您也可以阅读我的long answer，虽然它有点无关，但它可以帮助您了解 Keras 中的训练/预测是如何工作的，尤其是您可以阅读最后几段，编号为 1-12。

更新：由于下一次修改的帮助，问题似乎得到了解决：

1. 在数据生成函数中需要做两次扩展dim，即X = np.expand_dims(np.expand_dims(X, 0), 0)。

2. 在数据生成函数中需要另一个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" 都被删除了。