我正在尝试建立一个 GAN 模型来重新创建人脸
我的输入形状是 (5298, 64, 64, 3) 但是当我将它输入模型时它变成了 (1, 5298, 64, 64,3)
WARNING:tensorflow:Model was constructed with shape (None, 64, 64, 3) for input KerasTensor(type_spec=TensorSpec(shape=(None, 64, 64, 3), dtype=tf.float32, name='conv2d_input'), name='conv2d_input', description="created by layer 'conv2d_input'")
但它是在形状不兼容的输入 (1, 5298, 64, 64, 3) 上调用的。
我想我在构建图层时做错了什么，但我找不到问题所在。能不能给个提示？
from tensorflow.keras.preprocessing.image import load_img
from tensorflow.keras.preprocessing.image import img_to_array
from numpy import expand_dims
from numpy import zeros
from numpy import ones
from numpy.random import randn
from numpy.random import randint
import os
from os import listdir
from numpy import asarray
from numpy import load
import numpy as np
import tensorflow as tf
from keras.optimizers import Adam
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Reshape
from keras.layers import Flatten
from keras.layers import Conv2D
from keras.layers import Conv2DTranspose
from keras.layers import LeakyReLU
from keras.layers import Dropout
from tensorflow.keras.preprocessing.image import ImageDataGenerator
# define the standalone discriminator model
def define_discriminator(in_shape=(64,64,3)):
model = Sequential()
# downsample
model.add(Conv2D(128, (3,3), strides=(2,2), padding='same', input_shape=in_shape))
model.add(LeakyReLU(alpha=0.2))
# downsample
model.add(Conv2D(128, (3,3), strides=(2,2), padding='same'))
model.add(LeakyReLU(alpha=0.2))
# classifier
model.add(Flatten())
model.add(Dropout(0.4))
model.add(Dense(1, activation='sigmoid'))
# compile model
opt = Adam(lr=0.0002, beta_1=0.5)
model.compile(loss='binary_crossentropy', optimizer=opt, metrics=['accuracy'])
return model
# define the standalone generator model
def define_generator(latent_dim):
model = Sequential()
# foundation for 7x7 image
n_nodes = 512 * 8 * 8
model.add(Dense(n_nodes, input_dim=latent_dim))
model.add(LeakyReLU(alpha=0.2))
model.add(Reshape((8, 8, 512)))
model.add(Conv2DTranspose(512, (4,4), strides=(2,2), padding='same'))
model.add(LeakyReLU(alpha=0.2))
model.add(Conv2DTranspose(512, (4,4), strides=(2,2), padding='same'))
model.add(LeakyReLU(alpha=0.2))
model.add(Conv2DTranspose(512, (4,4), strides=(2,2), padding='same'))
model.add(LeakyReLU(alpha=0.2))
# generate
model.add(Conv2D(3, (8,8), activation='tanh', padding='same'))
return model
# define the combined generator and discriminator model, for updating the generator
def define_gan(generator, discriminator):
# make weights in the discriminator not trainable
discriminator.trainable = False
# connect them
model = Sequential()
# add generator
model.add(generator)
# add the discriminator
model.add(discriminator)
# compile model
opt = Adam(lr=0.0002, beta_1=0.5)
model.compile(loss='binary_crossentropy', optimizer=opt)
return model
# load images
def load_real_samples(path, size=(64,64)):
data_list = list()
# enumerate filenames in directory, assume all are images
for filename in listdir(path):
pixels = load_img(path + filename, target_size=size)
pixels = img_to_array(pixels)
data_list.append(pixels)
return asarray(data_list)
# select real samples
def generate_real_samples(dataset, n_samples):
# choose random instances
ix = randint(0, 5298, n_samples).any()
# select images
X = dataset[ix]
# generate class labels
y = ones((n_samples, 1))
return X, y
# generate points in latent space as input for the generator
def generate_latent_points(latent_dim, n_samples):
# generate points in the latent space
x_input = randn(latent_dim * n_samples)
# reshape into a batch of inputs for the network
x_input = x_input.reshape(n_samples, latent_dim)
return x_input
# use the generator to generate n fake examples, with class labels
def generate_fake_samples(generator, latent_dim, n_samples):
# generate points in latent space
x_input = generate_latent_points(latent_dim, n_samples)
# predict outputs
X = generator.predict(x_input)
# create class labels
y = zeros((n_samples, 1))
return X, y
# train the generator and discriminator
def train(g_model, d_model, gan_model, dataset, latent_dim, n_epochs=100, n_batch=1):
bat_per_epo = int(5298 // n_batch)
half_batch = int(n_batch / 2)
# manually enumerate epochs
for i in range(n_epochs):
# enumerate batches over the training set
for j in range(bat_per_epo):
# get randomly selected 'real' samples
X_real, y_real = generate_real_samples(dataset, half_batch)
# update discriminator model weights
d_loss1, _ = d_model.train_on_batch(X_real, y_real)
# generate 'fake' examples
X_fake, y_fake = generate_fake_samples(g_model, latent_dim, half_batch)
# update discriminator model weights
d_loss2, _ = d_model.train_on_batch(X_fake, y_fake)
# prepare points in latent space as input for the generator
X_gan = generate_latent_points(latent_dim, n_batch)
# create inverted labels for the fake samples
y_gan = ones((n_batch, 1))
# update the generator via the discriminator's error
g_loss = gan_model.train_on_batch(X_gan, y_gan)
# summarize loss on this batch
print('>%d, %d/%d, d1=%.3f, d2=%.3f g=%.3f' %
(i+1, j+1, bat_per_epo, d_loss1, d_loss2, g_loss))
# save the generator model
g_model.save('generator.h5')
# size of the latent space
latent_dim = 100
# create the discriminator
discriminator = define_discriminator()
# create the generator
generator = define_generator(latent_dim)
# create the gan
gan_model = define_gan(generator, discriminator)
# load image data
dataset = load_real_samples('dir')
# train model
train(generator, discriminator, gan_model, dataset, latent_dim)
ValueError: Input 0 of layer dense is incompatible with the layer: expected axis -1 of input shape to have value 32768 but received input with shape (1, 173604864)