ValueError: Input 0 of layer "sequential_13" is incompatible with the layer: expected shape=(None, 21367, 9000), found shape=(None, 9000)

Question

我不知道为什么当我运行下面的代码时这个错误一直出现

CNN.fit(X_train_vector, y_train, epochs=10)

我的CNN代码是这样的：

CNN = tf.keras.models.Sequential()
CNN.add(tf.keras.layers.Conv1D(120, kernel_size=3, padding='valid', activation='relu', input_shape = (21367, 9000)))
CNN.add(tf.keras.layers.MaxPooling1D(2))
CNN.add(tf.keras.layers.Dropout(0.2))
CNN.add(tf.keras.layers.Flatten())

CNN.add(tf.keras.layers.Dense(200, activation='relu'))
CNN.add(tf.keras.layers.Dense(20, activation='relu'))
CNN.add(tf.keras.layers.Dense(1, activation='softmax'))

我的“X_train_vector”有一个形状：

(21367, 9000)

我的“y_train”有一个形状：

(21367, 1)

我得到的错误：

Epoch 1/10
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-108-895976bf38cd> in <module>()
----> 1 CNN.fit(X_train_vector, y_train, epochs=10)

1 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in autograph_handler(*args, **kwargs)
   1145           except Exception as e:  # pylint:disable=broad-except
   1146             if hasattr(e, "ag_error_metadata"):
-> 1147               raise e.ag_error_metadata.to_exception(e)
   1148             else:
   1149               raise

ValueError: in user code:

    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1021, in train_function  *
        return step_function(self, iterator)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1010, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1000, in run_step  **
        outputs = model.train_step(data)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 859, in train_step
        y_pred = self(x, training=True)
    File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler
        raise e.with_traceback(filtered_tb) from None
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/input_spec.py", line 264, in assert_input_compatibility
        raise ValueError(f'Input {input_index} of layer "{layer_name}" is '

    ValueError: Input 0 of layer "sequential_13" is incompatible with the layer: expected shape=(None, 21367, 9000), found shape=(None, 9000)

我尝试了几种解决方案，包括将我的CNN第一行更改为：

CNN.add(tf.keras.layers.Conv1D(120, kernel_size=3, padding='valid', activation='relu', input_shape = (9000)))

但是运行ning 它说：

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-109-dd8d734d0a9f> in <module>()
      1 CNN = tf.keras.models.Sequential()
----> 2 CNN.add(tf.keras.layers.Conv1D(120, kernel_size=3, padding='valid', activation='relu', input_shape = (9000)))
      3 CNN.add(tf.keras.layers.MaxPooling1D(2))
      4 CNN.add(tf.keras.layers.Dropout(0.2))
      5 CNN.add(tf.keras.layers.Flatten())

3 frames
/usr/local/lib/python3.7/dist-packages/keras/engine/base_layer.py in __init__(self, trainable, name, dtype, dynamic, **kwargs)
    441         else:
    442           batch_size = None
--> 443         batch_input_shape = (batch_size,) + tuple(kwargs['input_shape'])
    444       self._batch_input_shape = batch_input_shape
    445 

TypeError: 'int' object is not iterable

谁能帮帮我。我一直在寻找解决方案两天，它应该按照我尝试的方式工作。我犯错了吗？请告诉我。提前致谢。

Answer 1

输入数组的形状应为 (None, shape_0, shape_1)，其中 None 表示批量大小，(shape_0, shape_1) 表示特征的形状。所以，你应该重塑你的输入数组：

X_train_vector = X_train_vector.reshape(-1, 9000, 1)

而且在构建模型时你真的 不需要 指定批量大小，所以删除它并只使用 (9000, 1) 作为 input_shape .试试这个：

CNN = tf.keras.models.Sequential()
CNN.add(tf.keras.layers.Conv1D(120, kernel_size=3, padding='valid', activation='relu', input_shape = (9000, 1)))
CNN.add(tf.keras.layers.MaxPooling1D(2))
CNN.add(tf.keras.layers.Dropout(0.2))
CNN.add(tf.keras.layers.Flatten())

CNN.add(tf.keras.layers.Dense(200, activation='relu'))
CNN.add(tf.keras.layers.Dense(20, activation='relu'))
CNN.add(tf.keras.layers.Dense(1, activation='softmax'))

这应该可以解决同样的错误不会再出现的问题。

ValueError: Input 0 of layer "sequential_13" is incompatible with the layer: expected shape=(None, 21367, 9000), found shape=(None, 9000)

ValueError: Input 0 of layer "sequential_13" is incompatible with the layer: expected shape=(None, 21367, 9000), found shape=(None, 9000)

deep-learning

conv-neural-network

keras

tensorflow