TensorFlow/Keras中Conv1D层维度不匹配问题排查

问题背景 #

输入为100×1的bathyZ向量（含空间变异性），搭配两个标量输入Tperiod、AMP_WK，目标是预测100×1的skew向量。首次使用TensorFlow Record数据集处理数据，持续遇到维度不匹配错误，核心问题为首个Dense层输入维度不符：期望轴-1维度为6402，但实际接收输入形状为(None, 165)。已尝试调整输入张量形状（如[1,100]、[1,100,1]），以批量大小1调试，仍无法解决。

报错信息 #

ValueError: Exception encountered when calling Functional.call().

Input 0 of layer "dense_110" is incompatible with the layer: expected axis -1 of input shape to have value 6402, but received input with shape (None, 165)

Arguments received by Functional.call():
  • inputs={'bathyZ': 'tf.Tensor(shape=(None, 100, 1), dtype=float32)', 'AMP_WK': 'tf.Tensor(shape=(None, 1), dtype=float32)', 'Tperiod': 'tf.Tensor(shape=(None, 1), dtype=float32)'}
  • training=True
  • mask={'bathyZ': 'None', 'AMP_WK': 'None', 'Tperiod': 'None'}

完整代码 #

feature_description = {
        'bathyZ': tf.io.FixedLenFeature([], tf.string),
        'bathyZ_shape': tf.io.FixedLenFeature([3], tf.int64),
        'AMP_WK': tf.io.FixedLenFeature([], tf.float32),
        'Tperiod': tf.io.FixedLenFeature([], tf.float32),
        'skew': tf.io.FixedLenFeature([], tf.string),
        'skew_shape': tf.io.FixedLenFeature([3], tf.int64),
    }
    
def _parse_function(proto):
    # Parse
    parsed_features = tf.io.parse_single_example(proto, feature_description)

    # Decode/reshape the serialized tensors
    bathyZ = parsed_features['bathyZ']
    bathyZ = tf.io.parse_tensor(bathyZ, out_type=tf.float32)
    bathyZ = tf.reshape(bathyZ, [100, 1])

    skew = parsed_features['skew']
    skew = tf.io.parse_tensor(skew, out_type=tf.float32)
    skew = tf.reshape(skew, [100, 1])

    # Get other inputs, reshape
    AMP_WK = parsed_features['AMP_WK']
    Tperiod = parsed_features['Tperiod']

    AMP_WK = tf.reshape(AMP_WK, [1])
    Tperiod = tf.reshape(Tperiod, [1])
    
    # Create tuple
    inputs = {'bathyZ': bathyZ, 'AMP_WK': AMP_WK, 'Tperiod': Tperiod}
    outputs = {'skew': skew}
    
    return inputs, outputs

# Create a TFRecordDataset and map the parsing function
tfrecord_path = 'ML_0004.tfrecord'
dataset = tf.data.TFRecordDataset(tfrecord_path)
dataset = dataset.map(_parse_function)
    
    
# Model
    
def create_model():
    # Tensor input branch (shape: 100 timesteps, 1 feature)
    bathyZ = Input(shape=(100, 1), name='bathyZ')
    x = layers.Conv1D(32, 3, activation='relu', padding='same')(bathyZ)
    x = layers.Conv1D(64, 3, activation='relu', padding='same')(x)
    x = layers.Flatten()(x)

    # Scalar inputs
    AMP_WK = Input(shape=(1,), name='AMP_WK')
    Tperiod = Input(shape=(1,), name='Tperiod')
    
    # Combine all branches
    combined = layers.concatenate([x, AMP_WK, Tperiod])

    # Fully connected layer
    z = layers.Dense(64, activation='relu')(combined)
    z = layers.Dense(128, activation='relu')(z)

    # Output layer (tensor output, same shape as input tensor)
    skew = layers.Dense(100, activation='linear', name='skew')(z)

    # Create the model
    model = models.Model(inputs=[bathyZ, AMP_WK, Tperiod], outputs=skew)
    return model

# Example usage:
model = create_model()
model.compile(optimizer='adam', loss='mse')
model.summary()
dataset = dataset.batch(1)  
model.fit(dataset)

解决方案 #

1. 对齐模型输入与数据集的输出结构

模型定义中，输入使用了列表[bathyZ, AMP_WK, Tperiod]，但数据集返回的是字典格式的输入{'bathyZ': ..., 'AMP_WK': ..., 'Tperiod': ...}，两者结构不匹配导致模型接收错误的张量组合，引发维度计算错误。

修改模型创建代码，将输入改为字典形式：

# Create the model
model = models.Model(inputs={'bathyZ': bathyZ, 'AMP_WK': AMP_WK, 'Tperiod': Tperiod}, outputs=skew)

2. 匹配输出层与目标张量的形状

当前输出层Dense(100)的输出形状为(None, 100)，但数据集返回的目标skew形状是(100, 1)，会导致损失计算时维度不匹配，需二选一调整：

• 方案A：修改解析函数中的目标形状
  将skew的形状调整为(100,)，与输出层匹配：

  skew = tf.reshape(skew, [100])
  

• 方案B：在模型输出层后添加Reshape层
  保持目标形状为(100,1)，调整模型输出：

  # Output layer (tensor output, same shape as input tensor)
  skew = layers.Dense(100, activation='linear', name='skew')(z)
  skew = layers.Reshape((100, 1))(skew)
  

3. 验证维度计算逻辑

卷积分支的维度计算是正确的：

• 输入bathyZ形状为(100,1)，经过Conv1D(32,3,padding='same')后形状为(100,32)
• 再经过Conv1D(64,3,padding='same')后形状为(100,64)
• Flatten后维度为100*64=6400，加上两个标量输入（各1维），合并后总维度为6400+1+1=6402，与模型期望的输入维度一致。之前的错误完全是输入结构不匹配导致的。

内容的提问来源于stack exchange，提问作者water_worlds