TensorFlow 2.3训练音乐生成VAE遇Sequential层名重复错误求助

错误信息 #

All layers added to a Sequential model should have unique names. Name "" is already the name of a layer in this model. Update the name argument to pass a unique name.

问题根源 #

你给自定义Resnet1DBlock内部的卷积、归一化层都加了唯一前缀，但忽略了**Resnet1DBlock本身作为Keras模型（继承自tf.keras.Model）的名称设置**：初始化时你传入了name=''（空字符串），导致每个Resnet1DBlock实例的层名都是空字符串。当Sequential模型中添加多个该Block实例时，就会出现重复的空名称层，触发报错。

修复方案 #

修改Resnet1DBlock的初始化逻辑，利用传入的prefix参数给每个Block实例设置唯一名称，避免重复。同时建议把call方法中重复创建的LeakyReLU层移到初始化中，减少冗余创建。

修改后的完整代码 #

class Resnet1DBlock(tf.keras.Model):
    def __init__(self, kernel_size, filters, type='encode', prefix=''):
        # 用prefix生成唯一的Block名称，避免空名称重复
        super(Resnet1DBlock, self).__init__(name=prefix + 'block')
    
        self.leaky_relu = layers.LeakyReLU(0.4)
        if type == 'encode':
            self.conv1a = layers.Conv1D(filters, kernel_size, 2, padding="same", 
                                        name=prefix + 'conv1a')
            self.conv1b = layers.Conv1D(filters, kernel_size, 1, padding="same", 
                                        name=prefix + 'conv1b')
            self.norm1a = tfa.layers.InstanceNormalization(name=prefix + 'norm1a')
            self.norm1b = tfa.layers.InstanceNormalization(name=prefix + 'norm1b')
        elif type == 'decode':
            self.conv1a = layers.Conv1DTranspose(filters, kernel_size, 1, padding="same", 
                                                name=prefix + 'conv1a')
            self.conv1b = layers.Conv1DTranspose(filters, kernel_size, 1, padding="same", 
                                                name=prefix + 'conv1b')
            self.norm1a = tf.keras.layers.BatchNormalization(name=prefix + 'norm1a')
            self.norm1b = tf.keras.layers.BatchNormalization(name=prefix + 'norm1b')
        else:
            return None

    def call(self, input_tensor):
        x = tf.nn.relu(input_tensor)
        x = self.conv1a(x)
        x = self.norm1a(x)
        x = self.leaky_relu(x)

        x = self.conv1b(x)
        x = self.norm1b(x)
        x = self.leaky_relu(x)

        x += input_tensor
        return tf.nn.relu(x)
    
class CVAE(tf.keras.Model):

    def __init__(self, latent_dim):
        super(CVAE, self).__init__()
        self.latent_dim = latent_dim
        self.encoder = tf.keras.Sequential(
            [
                tf.keras.layers.InputLayer(input_shape=(1, 90001), name='input_encoder'),

                layers.Conv1D(64, 1, 2, name='conv1_layer1'),
                Resnet1DBlock(64, 1, 'encode', prefix='res1_'),
                layers.Conv1D(128, 1, 2, name='conv1_layer2'),
                Resnet1DBlock(128, 1, 'encode', prefix='res2_'),
                layers.Conv1D(128, 1, 2, name='conv1_layer3'),
                Resnet1DBlock(128, 1, 'encode', prefix='res3_'),
                layers.Conv1D(256, 1, 2, name='conv1_layer4'),
                Resnet1DBlock(256, 1, 'encode', prefix='res4_'),

                layers.Flatten(name='flatten'),
                layers.Dense(latent_dim + latent_dim, name='dense'),
            ]
        )
        self.decoder = tf.keras.Sequential(
            [
                tf.keras.layers.InputLayer(input_shape=(latent_dim,), name='input_decoder'),
                layers.Reshape(target_shape=(1, latent_dim)),
                Resnet1DBlock(512, 1, 'decode', prefix='res1_'),
                layers.Conv1DTranspose(512, 1, 1, name='Conv1Trans_Layer1'),
                Resnet1DBlock(256, 1, 'decode', prefix='res2_'),
                layers.Conv1DTranspose(256, 1, 1, name='Conv1Trans_Layer2'),
                Resnet1DBlock(128, 1, 'decode', prefix='res3_'),
                layers.Conv1DTranspose(128, 1, 1, name='Conv1Trans_Layer3'),
                Resnet1DBlock(64, 1, 'decode', prefix='res4_'),
                layers.Conv1DTranspose(64, 1, 1, name='Conv1Trans_Layer4'),
                layers.Conv1DTranspose(90001, 1, 1, name='Conv1Trans_Layer5')
            ]
        )

optimizer = tf.keras.optimizers.Adam(0.0003, beta_1=0.9, beta_2=0.999, epsilon=1e-08)

random_vector_for_generation = tf.random.normal(shape=[num_examples_to_generate, latent_dim])
model = CVAE(latent_dim)

关键修改点 #

1. 将Resnet1DBlock初始化中的name=''改为name=prefix + 'block'，确保每个Block实例有唯一名称（如res1_block、res2_block）。
2. 把call方法中每次调用都创建的LeakyReLU层移到__init__中作为实例属性，避免重复创建层，提升效率。

内容的提问来源于stack exchange，提问作者Wanderer