Question

我有下面的代码，可在374大小为32x32的训练图像上运行创生对抗网络（GAN）。

为什么会有以下错误？

ValueError: Input arrays should have the same number of samples as target arrays. Found 7500 input samples and 40 target samples.

在以下语句中出现：

discriminator_loss = discriminator.train_on_batch(combined_images,labels)

import keras
from keras import layers
import numpy as np
import cv2
import os
from keras.preprocessing import image

latent_dimension = 32
height = 32
width = 32
channels = 3
iterations = 100000
batch_size = 20
real_images = []

# paths to the training and results directories
train_directory = '/training'
results_directory = '/results'

# GAN generator
generator_input = keras.Input(shape=(latent_dimension,))

# transform the input into a 16x16 128-channel feature map
x = layers.Dense(128*16*16)(generator_input)
x = layers.LeakyReLU()(x)
x = layers.Reshape((16,16,128))(x)

x = layers.Conv2D(256,5,padding='same')(x)
x = layers.LeakyReLU()(x)

# upsample to 32x32
x = layers.Conv2DTranspose(256,4,strides=2,padding='same')(x)
x = layers.LeakyReLU()(x)

x = layers.Conv2D(256,5,padding='same')(x)
x = layers.LeakyReLU()(x)
x = layers.Conv2D(256,5,padding='same')(x)
x = layers.LeakyReLU()(x)

# a 32x32 1-channel feature map is generated (i.e. shape of image)
x = layers.Conv2D(channels,7,activation='tanh',padding='same')(x)
# instantiae the generator model, which maps the input of shape (latent dimension) into an image of shape (32,32,1)
generator = keras.models.Model(generator_input,x)
generator.summary()

# GAN discriminator
discriminator_input = layers.Input(shape=(height,width,channels))

x = layers.Conv2D(128,3)(discriminator_input)
x = layers.LeakyReLU()(x)
x = layers.Conv2D(128,4,strides=2)(x)
x = layers.LeakyReLU()(x)
x = layers.Conv2D(128,4,strides=2)(x)
x = layers.LeakyReLU()(x)
x = layers.Conv2D(128,4,strides=2)(x)
x = layers.LeakyReLU()(x)
x = layers.Flatten()(x)

# dropout layer
x = layers.Dropout(0.4)(x)

# classification layer
x = layers.Dense(1,activation='sigmoid')(x)

# instantiate the discriminator model, and turn a (32,32,1) input
# into a binary classification decision (fake or real)
discriminator = keras.models.Model(discriminator_input,x)
discriminator.summary()

discriminator_optimizer = keras.optimizers.RMSprop(
    lr=0.0008,
    clipvalue=1.0,
    decay=1e-8)

discriminator.compile(optimizer=discriminator_optimizer, loss='binary_crossentropy')

# adversarial network
discriminator.trainable = False

gan_input = keras.Input(shape=(latent_dimension,))
gan_output = discriminator(generator(gan_input))
gan = keras.models.Model(gan_input,gan_output)

gan_optimizer = keras.optimizers.RMSprop(
    lr=0.0004,
    clipvalue=1.0,
    decay=1e-8)

gan.compile(optimizer=gan_optimizer,loss='binary_crossentropy')

start = 0
for step in range(iterations):
    # sample random points in the latent space
    random_latent_vectors = np.random.normal(size=(batch_size,latent_dimension))
    # decode the random latent vectors into fake images
    generated_images = generator.predict(random_latent_vectors)
    stop = start + batch_size

    i = start
    for root, dirs, files in os.walk(train_directory):
        for file in files:
            for i in range(stop-start):
                img = cv2.imread(root + '/' + file)
                real_images.append(img)
                i = i+1

    combined_images = np.concatenate([generated_images,real_images])
    # assemble labels and discrminate between real and fake images
    labels = np.concatenate([np.ones((batch_size,1)),np.zeros(batch_size,1)])
    # add random noise to the labels
    labels = labels + 0.05 * np.random.random(labels.shape)
    # train the discriminator
    discriminator_loss = discriminator.train_on_batch(combined_images,labels)
    random_latent_vectors = np.random.normal(size=(batch_size,latent_dimension))
    # assemble labels that classify the images as "real", which is not true
    misleading_targets = np.zeros((batch_size,1))
    # train the generator via the GAN model, where the discriminator weights are frozen
    adversarial_loss = gan.train_on_batch(random_latent_vectors,misleading_targets)
    start = start + batch_size

    if start > len(train_directory)-batch_size:
        start = 0

    # save the model weights
    if step % 100 == 0:
        gan.save_weights('gan.h5')
        print'discriminator loss: ' 
        print discriminator_loss
        print 'adversarial loss: '
        print adversarial_loss
        img = image.array_to_img(generated_images[0] * 255.)
        img.save(os.path.join(results_directory,'generated_melanoma_image' + str(step) + '.png'))
        img = image.array_to_img(real_images[0] * 255.)
        img.save(os.path.join(results_directory,'real_melanoma_image' + str(step) + '.png'))

谢谢。

Answer 1

您导致此问题的后续步骤

i = start
for root, dirs, files in os.walk(train_directory):
    for file in files:
        for i in range(stop-start):
            img = cv2.imread(root + '/' + file)
            real_images.append(img)
            i = i+1

您正尝试收集20的{{1}}个样本，这是通过内部循环完成的。然后有一个外部循环，每个文件都在运行，因此，外部循环正在为每个文件收集real_images个样本，总共收集20个样本，而您计划仅收集{{1} }。

Keras-输入数组应具有与目标数组相同数量的样本

1 个答案: