2

所以我正在尝试按照 DCGAN 指南在 tensorflow https://www.tensorflow.org/tutorials/generation/dcgan上生成图像，并且我将代码复制得非常紧密，只需将数据集更改为我想要的数据集利用。每当我尝试训练模型时，我都会收到此错误-

ValueError: Layersequential_1 需要 1 个输入，但它接收到 2 个输入张量。收到的输入：[<tf.Tensor 'images:0' shape=(256, 28, 28, 3) dtype=float32>, <tf.Tensor 'images_1:0' shape=(256,) dtype=int32>]

特别是 train_step 函数中的这一行导致错误，

real_output = discriminator(images, training=True)

当它在 train 函数中被调用时

train(normalizedData, epochs)

鉴别器函数的定义是这样的，在代码的前面：

def make_discriminator_model():
    model = tf.keras.Sequential()
    model.add(layers.Conv2D(64, (5,5), strides=(2,2), padding='same', input_shape=[28, 28, 1]))
    model.add(layers.LeakyReLU())
    model.add(layers.Dropout(0.3))

    model.add(layers.Conv2D(128, (5,5), strides=(2,2), padding='same'))
    model.add(layers.LeakyReLU())
    model.add(layers.Dropout(0.3))

    model.add(layers.Flatten())
    model.add(layers.Dense(1))

    return model

discriminator = make_discriminator_model()

这是上下文的其余部分。

@tf.function
def train_step(images):
    noise = tf.random.normal([batch_size, noise_dim])

    with tf.GradientTape() as gen_tape, tf.GradientTape() as disc_tape:
        generated_images = generator(noise, training=True)

        real_output = discriminator(images, training=True)
        fake_output = discriminator(generated_images, training=True)

        gen_loss = generator_loss(fake_output)
        disc_loss = discriminator_loss(real_output, fake_output)

    gradients_of_generator = gen_tape.gradient(gen_loss, generator.trainable_variables)
    gradients_of_discriminator = disc_tape.gradient(disc_loss, discriminator.trainable_variables)

    generator_optimizer.apply_gradients(zip(gradients_of_generator, generator.trainable_variables))
    discriminator_optimizer.apply_gradients(zip(gradients_of_discriminator, discriminator.trainable_variables))

def train(dataset, epochs):
    for epoch in range(epochs):
        start = time.time()

        for image_batch in dataset:
            train_step(image_batch)

        display.clear_output(wait=True)
        generate_and_save_images(generator,
                                 epoch + 1,
                                 seed)

        if (epoch + 1) % 15 == 0:
            checkpoint.save(file_prefix = checkpoint_prefix)

        print('Time for epoch {} is {} sec'.format(epoch + 1, time.time()-start))

    display.clear_output(wait=True)
    generate_and_save_images(generator,
                             epochs,
                             seed)

def generate_and_save_images(model, epoch, test_input):

    predictions = model(test_input, training=False)

    fig = plt.figure(figsize=(4,4))

    for i in range(predictions.shape[0]):
        plt.subplot(4,4,i+1)
        plt.imshow(predicitons[i, :, :, 0] * 127.5 + 127.5, cmap='gist_rainbow')
        plt.axis('off')

    plt.savefig('image_at_epoch_{:04d}.png'.format(epoch))
    plt.show()
    
        
train(normalizedData, epochs)

我在这里看到了关于这个值错误的这个问题的不同变体，从我收集的内容来看，顺序层正在输入一个列表而不是一个元组？

感谢您抽出宝贵的时间和您可以提供的任何帮助。

4

2 回答 2

1

该错误告诉您您对鉴别器的输入是 的形状[<tf.Tensor 'images:0' shape=(256, 28, 28, 3) dtype=float32>, <tf.Tensor 'images_1:0' shape=(256,) dtype=int32>]，但您定义的鉴别器具有input_shape=[28, 28, 1]

检查images您输入的鉴别器real_output = discriminator(images, training=True)，确保images与鉴别器的 input_shape 具有相同的形状，例如 (256, 28, 28, 3)

于 2020-12-16T04:04:29.937 回答
0

我在 GAN 教程teasorflow doc https://www.tensorflow.org/tutorials/generation/dcgan中遇到了同样的问题，请使用 tf.reshape 来重塑日期集

discriminator(tf.reshape(images, (1, 28, 28, 1)), training=True)

这个对我有用。

于 2021-08-17T10:40:25.683 回答