“ListWrapper”对象没有“最小化”属性答案

【问题标题】：'ListWrapper' object has no attribute 'minimize'“ListWrapper”对象没有“最小化”属性
【发布时间】：2021-10-07 09:14:46
【问题描述】：

我正在编写一个带有多输出鉴别器的 GAN。尝试批量训练鉴别器但出现错误 - AttributeError: 'ListWrapper' 对象没有属性 'minimize'。下面是判别器代码，这里c_model是多输出的判别器-

# custom activation function
def custom_activation(output):
    logexpsum = backend.sum(backend.exp(output), axis=-1, keepdims=True)
    result = logexpsum / (logexpsum + 1.0)
    return result

# define the standalone supervised and unsupervised discriminator models
def define_discriminator(in_shape=input, n_classes=n_class):
    # image input
    in_image = Input(shape=in_shape)
    # downsample
    fe = Conv2D(128, (3,3), strides=(2,2), padding='same')(in_image)
    fe = LeakyReLU(alpha=0.2)(fe)
    # downsample
    fe = Conv2D(128, (3,3), strides=(2,2), padding='same')(fe)
    fe = LeakyReLU(alpha=0.2)(fe)
    # downsample
    fe = Conv2D(128, (3,3), strides=(2,2), padding='same')(fe)
    fe = LeakyReLU(alpha=0.2)(fe)
    # flatten feature maps
    fe = Flatten()(fe)
    # dropout
    fe = Dropout(0.4)(fe)
    # output layer nodes
    fe = Dense(n_classes)(fe)
    # supervised output
    c_out_layer = Activation('softmax')(fe)
    # unsupervised output
    d_out_layer = Lambda(custom_activation)(fe)


    # The part of discriminator that is giving the error
    # define and compile supervised discriminator model
    c_model = Model(inputs = in_image, outputs = [c_out_layer, d_out_layer])
    opt = tf.keras.optimizers.SGD(learning_rate=0.0002)
    c_model.compile(loss=['sparse_categorical_crossentropy', 'binary_crossentropy'], optimizer=[opt, opt], metrics=['accuracy', 'accuracy'])


    # define and compile unsupervised discriminator model
    d_model = Model(in_image, d_out_layer)
    d_model.compile(loss='binary_crossentropy', optimizer = opt)
    return d_model, c_model

下面是训练模型的代码sn-p-

c_loss, c_acc = c_model.train_on_batch(Xsup_real, [ysup_real, label_real])

3 个输入的输入形状是 -

Xsup_real = (60, 64, 64, 1)
ysup_real = (60, 1)
label_real = (60, 1)

tensorflow版本是2.6.0，keras版本是2.6.0 谢谢！

【问题讨论】：

嗨！你能附上错误堆栈跟踪吗？附上类似问题供参考。 stackoverflow.com/questions/59443567/…

标签： python tensorflow keras conv-neural-network generative-adversarial-network

【解决方案1】：

问题来自以下调用

c_model.compile(
    loss=['sparse_categorical_crossentropy', 'binary_crossentropy'],
    optimizer=[opt, opt],
    metrics=['accuracy', 'accuracy']
)

您不能将多个优化器作为列表传递给compile 函数。如果确实需要，请改用 tensorflow-addons 中的 tfa.optimizers.MultiOptimizer。

multiOpt = tfa.optimizers.MultiOptimizer(
    [(opt, c_out_layer), (opt, d_out_layer)]
)
c_model.compile(
    loss=['sparse_categorical_crossentropy', 'binary_crossentropy'],
    optimizer=multiOpt,
    metrics=['accuracy', 'accuracy']
)

但是，更仔细地查看您的代码，您可能甚至不需要拥有多个优化器。做吧

c_model.compile(
   loss=['sparse_categorical_crossentropy', 'binary_crossentropy'],
   optimizer=opt,
   metrics=['accuracy', 'accuracy']
)

【讨论】：