我正在使用一个采用MNIST数据集并生成输出的模型,但是我想将自己的数据集提供给该模型,我的数据集中的图像大小为(512x512),但是该模型采用的图像大小为( 28x28)。现在,当我将数据集图像转换为(28x28)模型时,可以正常工作,但我必须以512x512的尺寸输入图像。谁能帮助我解决这个问题。 我也在这里分享完整的代码。您可以在(加载数据集)上看到我正在加载自己的数据集并将其转换为28x28,但实际上我想加载512x512大小的图像。
class DCGAN():
def init(self):
# Input shape
self.img_rows = 28
self.img_cols = 28
self.channels = 1
self.img_shape = (self.img_rows, self.img_cols, self.channels)
self.latent_dim = 100
optimizer = Adam(0.0002, 0.5)
# Build and compile the discriminator
self.discriminator = self.build_discriminator()
self.discriminator.compile(loss='binary_crossentropy',
optimizer=optimizer,
metrics=['accuracy'])
# Build the generator
self.generator = self.build_generator()
# The generator takes noise as input and generates imgs
z = Input(shape=(self.latent_dim,))
img = self.generator(z)
# For the combined model we will only train the generator
self.discriminator.trainable = False
# The discriminator takes generated images as input and determines validity
valid = self.discriminator(img)
# The combined model (stacked generator and discriminator)
# Trains the generator to fool the discriminator
self.combined = Model(z, valid)
self.combined.compile(loss='binary_crossentropy', optimizer=optimizer)
def build_generator(self):
model = Sequential()
model.add(Dense(128 * 7 * 7, activation="relu", input_dim=self.latent_dim))
model.add(Reshape((7, 7, 128)))
model.add(UpSampling2D())
model.add(Conv2D(128, kernel_size=3, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation("relu"))
model.add(UpSampling2D())
model.add(Conv2D(64, kernel_size=3, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation("relu"))
model.add(Conv2D(self.channels, kernel_size=3, padding="same"))
model.add(Activation("tanh"))
model.summary()
noise = Input(shape=(self.latent_dim,))
img = model(noise)
return Model(noise, img)
def build_discriminator(self):
model = Sequential()
model.add(Conv2D(32, kernel_size=3, strides=2, input_shape=self.img_shape, padding="same"))
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.25))
model.add(Conv2D(64, kernel_size=3, strides=2, padding="same"))
model.add(ZeroPadding2D(padding=((0,1),(0,1))))
model.add(BatchNormalization(momentum=0.8))
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.25))
model.add(Conv2D(128, kernel_size=3, strides=2, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.25))
model.add(Conv2D(256, kernel_size=3, strides=1, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(1, activation='sigmoid'))
model.summary()
img = Input(shape=self.img_shape)
validity = model(img)
return Model(img, validity)
def train(self, epochs, batch_size=128, save_interval=50):
# Load the dataset
#(X_train, _), (_, _) = mnist.load_data()
files_name = os.listdir('./Dataset/Train')
train_x = []
#train_y = []
for _,i in enumerate(files_name):
train_x.append(cv2.imread(os.path.join('./Dataset/Train',i),0))
train_x = np.asarray(train_x).reshape(-1, 512,512, 1)
train_x_28 = []
for i in range(len(train_x)):
train_x_28.append(cv2.resize(train_x[i], (28, 28)))
X_train = np.asarray(train_x_28).reshape(-1, 28,28)
# Rescale -1 to 1
X_train = X_train / 127.5 - 1.
X_train = np.expand_dims(X_train, axis=3)
# Adversarial ground truths
valid = np.ones((batch_size, 1))
fake = np.zeros((batch_size, 1))
for epoch in range(epochs):
# ---------------------
# Train Discriminator
# ---------------------
# Select a random half of images
idx = np.random.randint(0, X_train.shape[0], batch_size)
imgs = X_train[idx]
# Sample noise and generate a batch of new images
noise = np.random.normal(0, 1, (batch_size, self.latent_dim))
gen_imgs = self.generator.predict(noise)
# Train the discriminator (real classified as ones and generated as zeros)
d_loss_real = self.discriminator.train_on_batch(imgs, valid)
d_loss_fake = self.discriminator.train_on_batch(gen_imgs, fake)
d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)
# ---------------------
# Train Generator
# ---------------------
# Train the generator (wants discriminator to mistake images as real)
g_loss = self.combined.train_on_batch(noise, valid)
# Plot the progress
print ("%d [D loss: %f, acc.: %.2f%%] [G loss: %f]" % (epoch, d_loss[0], 100*d_loss[1], g_loss))
# If at save interval => save generated image samples
if epoch % save_interval == 0:
self.save_imgs(epoch)
def save_imgs(self, epoch):
r, c = 2, 2
noise = np.random.normal(0, 1, (r * c, self.latent_dim))
gen_imgs = self.generator.predict(noise)
# Rescale images 0 - 1
gen_imgs = 0.5 * gen_imgs + 0.5
fig, axs = plt.subplots(r, c)
cnt = 0
for i in range(r):
for j in range(c):
axs[i,j].imshow(gen_imgs[cnt, :,:,0], cmap='gray')
axs[i,j].axis('off')
cnt += 1
fig.savefig("dcgan/images/mnist_%d.png" % epoch)
plt.close()
if name == 'main':
dcgan = DCGAN()
dcgan.train(epochs=4000, batch_size=32, save_interval=50)
检查输入时出错:预期input_49的形状为(512,512,1),但数组的形状为(28,28,1)
答案 0 :(得分:1)
您需要修改生成器以生成与数据集相同大小的图像。如果您只想运行某些内容,则可以继续重复执行升级步骤:
model.add(UpSampling2D())
model.add(Conv2D(num_filters, kernel_size=3, padding="same"))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation("relu"))
典型网络将每个上采样的滤波器数量减半。这样可以使每种分辨率的操作数保持不变(尽管每层内存需求增加了一倍)。
您越深入,就会遇到更多的麻烦。您可能需要增加潜在的尺寸大小,或在最初的密集/重塑中使用的过滤器数量。如何做到这一点是一个开放的研究问题。