一维卷积层尺寸不匹配问题

Question

我正在尝试了解卷积层在神经网络中的工作原理。我针对类似问题找到了两个不同的相关帖子并尝试了这些建议，但无法解决。

ValueError: Input 0 is incompatible with layer conv_1: expected ndim=3, found ndim=4

import tensorflow as tf
model_valid = tf.keras.Sequential([
    tf.keras.layers.Flatten(input_shape=(10,)),
    tf.keras.layers.Dense(16,  activation='relu'),
    tf.keras.layers.Conv1D(16, kernel_size=(2), activation='relu', padding='same'),     
    tf.keras.layers.MaxPooling1D(pool_size=(4), strides=3, padding='valid'),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(1, activation='softmax')
])
model_valid.summary()

我收到 Input 0 of layer conv1d_37 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: [None, 16] 的不兼容问题。构建卷积层时出现问题。

Answer 1

Conv1D 层的输入必须是 3D 张量（batch_size，步数，input_dim）。展平张量会将输入转换为二维张量 (batch_size, input_dim)。尝试移除 Flatten 图层。

Answer 2

第一个 Conv1D 之前的输入形状不正确。正如用户 spb 所建议的那样，Conv1D 的输入必须是 3D 张量，尽管移除展平层（如建议的那样）不会解决问题。

相反，只需在第一个 Dense 层之后添加一个额外的维度。

import tensorflow as tf
model_valid = tf.keras.Sequential([
    tf.keras.layers.Flatten(input_shape=(10,)),
    tf.keras.layers.Dense(16,  activation='relu'),
    tf.keras.layers.Reshape((16, 1)), # ADD THIS LINE OF CODE
    tf.keras.layers.Conv1D(16, kernel_size=(2), activation='relu', padding='same'),     
    tf.keras.layers.MaxPooling1D(pool_size=(4), strides=3, padding='valid'),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(1, activation='softmax')
])
model_valid.summary()

现在模型总结为：

Model: "sequential_2"
_________________________________________________________________
Layer (type)                 Output Shape              Param #
=================================================================
flatten_4 (Flatten)          (None, 10)                0
_________________________________________________________________
dense_4 (Dense)              (None, 16)                176
_________________________________________________________________
reshape (Reshape)            (None, 16, 1)             0
_________________________________________________________________
conv1d_1 (Conv1D)            (None, 16, 16)            48
_________________________________________________________________
max_pooling1d (MaxPooling1D) (None, 5, 16)             0
_________________________________________________________________
flatten_5 (Flatten)          (None, 80)                0
_________________________________________________________________
dense_5 (Dense)              (None, 1)                 81
=================================================================
Total params: 305
Trainable params: 305
Non-trainable params: 0
_________________________________________________________________

一维卷积层尺寸不匹配问题

1D Convolution Layer dimension mismatch issue

python

neural-network

conv-neural-network

keras

tensorflow