转载:GAN实例——野马变斑马【实测成功】

仅作为记录,大佬请跳过。

文章目录

  • 参考
  • 第一部分——数据集准备的源代码
  • 第二部分——训练与效果的源代码
  • 展示

参考

感谢大佬博主文章传送门

(博主完全参考上面的大佬博主文章)

第一部分——数据集准备的源代码

文件夹位置:
下载的数据解压后放在任何路径(该路径在c1gan_calcu.py引入);
在任何路径新建c1gan_calcu.py


1、数据下载

2、新建c1gan_calcu.py文件

3、c1gan_calcu.py放着第一部分源代码,——将数据集解压后的文件夹的路径写入c1gan_calcu.py文件

在这里插入图片描述

4、直接运行.py即可。(——得到整理后的数据集文件horse2zebra_256.npz)

c1gan_calcu.py文件的源代码:

from os import listdir
import numpy as np
from numpy import asarray
from keras.preprocessing.image import img_to_array
from keras.preprocessing.image import load_img

# load all images in a directory into memory
def load_images(path, size=(256, 256)):
    data_list = list()
    # enumerate filenames in directory, assume all are images
    for filename in listdir(path):
        # load and resize the image
        pixels = load_img(path + filename, target_size=size)
        # convert to numpy array
        pixels = img_to_array(pixels)
        # store
        data_list.append(pixels)
    return asarray(data_list)


# dataset path
path = 'F:/cycleganhorse/horse2zebra/'
# load dataset A
dataA1 = load_images(path + 'trainA/')
dataAB = load_images(path + 'testA/')
dataA = np.vstack((dataA1, dataAB))
print('Loaded dataA: ', dataA.shape)
# load dataset B
dataB1 = load_images(path + 'trainB/')
dataB2 = load_images(path + 'testB/')
dataB = np.vstack((dataB1, dataB2))
print('Loaded dataB: ', dataB.shape)
# save as compressed numpy array
filename = 'horse2zebra_256.npz'
# np.savez_compressed(filename, dataA, dataB)
print('Saved dataset: ', filename)






# 查看horse2zebra_256.npz里的图片

# load and plot the prepared dataset
from numpy import load
from matplotlib import pyplot
# load the dataset
data = load(r'F:\cycleganhorse\horse2zebra_256.npz')
dataA, dataB = data['arr_0'], data['arr_1']
print('Loaded: ', dataA.shape, dataB.shape)
# plot source images
n_samples = 3
for i in range(n_samples):
	pyplot.subplot(2, n_samples, 1 + i)
	pyplot.axis('off')
	pyplot.imshow(dataA[i].astype('uint8'))
# plot target image
for i in range(n_samples):
	pyplot.subplot(2, n_samples, 1 + n_samples + i)
	pyplot.axis('off')
	pyplot.imshow(dataB[i].astype('uint8'))
pyplot.show()


运行后还可查看horse2zebra_256.npz里的图片

展示:

转载:GAN实例——野马变斑马【实测成功】_第1张图片

第二部分——训练与效果的源代码

1、将第一部分生成的数据集文件horse2zebra_256.npz,与c1gan.py放在同一个文件夹:

2、然后运行c1gan.py文件即可,

c1gan.py的源代码:

import tensorflow as tf

from tensorflow.keras.optimizers import Adam
from tensorflow.keras.initializers import RandomNormal
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input
from tensorflow.keras.layers import Conv2D
from tensorflow.keras.layers import Conv2DTranspose

from tensorflow.keras.layers import Activation
from tensorflow.keras.layers import Concatenate
from tensorflow.keras.layers import Dropout

from matplotlib import pyplot
from tensorflow.keras.layers import LeakyReLU
import tensorflow_addons as tfa
import numpy as np
from random import random

def define_discriminator(image_shape):
	# weight initialization
	init = RandomNormal(stddev=0.02)
	# source image input
	in_image = Input(shape=image_shape)
	# C64
	d = Conv2D(64, (4,4), strides=(2,2), padding='same', kernel_initializer=init)(in_image)
	d = LeakyReLU(alpha=0.2)(d)
	# C128
	d = Conv2D(128, (4,4), strides=(2,2), padding='same', kernel_initializer=init)(d)
	d = tfa.layers.InstanceNormalization(axis=-1)(d)
	d = LeakyReLU(alpha=0.2)(d)
	# C256
	d = Conv2D(256, (4,4), strides=(2,2), padding='same', kernel_initializer=init)(d)
	d = tfa.layers.InstanceNormalization(axis=-1)(d)
	d = LeakyReLU(alpha=0.2)(d)
	# C512
	d = Conv2D(512, (4,4), strides=(2,2), padding='same', kernel_initializer=init)(d)
	d = tfa.layers.InstanceNormalization(axis=-1)(d)
	d = LeakyReLU(alpha=0.2)(d)
	# second last output layer
	d = Conv2D(512, (4,4), padding='same', kernel_initializer=init)(d)
	d = tfa.layers.InstanceNormalization(axis=-1)(d)
	d = LeakyReLU(alpha=0.2)(d)
	# patch output
	patch_out = Conv2D(1, (4,4), padding='same', kernel_initializer=init)(d)
	# define model
	model = Model(in_image, patch_out)
	# compile model
	model.compile(loss='mse', optimizer=Adam(lr=0.0002, beta_1=0.5), loss_weights=[0.5])
	return model

# generator a resnet block
def resnet_block(n_filters, input_layer):
	# weight initialization
	init = RandomNormal(stddev=0.02)
	# first layer convolutional layer
	g = Conv2D(n_filters, (3,3), padding='same', kernel_initializer=init)(input_layer)
	g = tfa.layers.InstanceNormalization(axis=-1)(g)
	g = Activation('relu')(g)
	# second convolutional layer
	g = Conv2D(n_filters, (3,3), padding='same', kernel_initializer=init)(g)
	g = tfa.layers.InstanceNormalization(axis=-1)(g)
	# concatenate merge channel-wise with input layer
	g = Concatenate()([g, input_layer])
	return g

# define the standalone generator model
def define_generator(image_shape, n_resnet=9):
	# weight initialization
	init = RandomNormal(stddev=0.02)
	# image input
	in_image = Input(shape=image_shape)
	# c7s1-64
	g = Conv2D(64, (7,7), padding='same', kernel_initializer=init)(in_image)
	g = tfa.layers.InstanceNormalization(axis=-1)(g)
	g = Activation('relu')(g)
	# d128
	g = Conv2D(128, (3,3), strides=(2,2), padding='same', kernel_initializer=init)(g)
	g = tfa.layers.InstanceNormalization(axis=-1)(g)
	g = Activation('relu')(g)
	# d256
	g = Conv2D(256, (3,3), strides=(2,2), padding='same', kernel_initializer=init)(g)
	g = tfa.layers.InstanceNormalization(axis=-1)(g)
	g = Activation('relu')(g)
	# R256
	for _ in range(n_resnet):
		g = resnet_block(256, g)
	# u128
	g = Conv2DTranspose(128, (3,3), strides=(2,2), padding='same', kernel_initializer=init)(g)
	g = tfa.layers.InstanceNormalization(axis=-1)(g)
	g = Activation('relu')(g)
	# u64
	g = Conv2DTranspose(64, (3,3), strides=(2,2), padding='same', kernel_initializer=init)(g)
	g = tfa.layers.InstanceNormalization(axis=-1)(g)
	g = Activation('relu')(g)
	# c7s1-3
	g = Conv2D(3, (7,7), padding='same', kernel_initializer=init)(g)
	g = tfa.layers.InstanceNormalization(axis=-1)(g)
	out_image = Activation('tanh')(g)
	# define model
	model = Model(in_image, out_image)
	return model

# define a composite model for updating generators by adversarial and cycle loss
def define_composite_model(g_model_1, d_model, g_model_2, image_shape):
	# ensure the model we're updating is trainable
	g_model_1.trainable = True
	# mark discriminator as not trainable
	d_model.trainable = False
	# mark other generator model as not trainable
	g_model_2.trainable = False
	# discriminator element
	input_gen = Input(shape=image_shape)
	gen1_out = g_model_1(input_gen) # A >B
	output_d = d_model(gen1_out)  # 识别B
	# identity element
	input_id = Input(shape=image_shape)
	output_id = g_model_1(input_id) # B >A
	# forward cycle
	output_f = g_model_2(gen1_out) # A>B >A
	# backward cycle
	gen2_out = g_model_2(input_id) # B >A
	output_b = g_model_1(gen2_out) # B> A >B
	# define model graph
	model = Model([input_gen, input_id], [output_d, output_id, output_f, output_b])
	# define optimization algorithm configuration
	opt = Adam(lr=0.0002, beta_1=0.5)
	# compile model with weighting of least squares loss and L1 loss
	model.compile(loss=['mse', 'mae', 'mae', 'mae'], loss_weights=[1, 5, 10, 10], optimizer=opt)
	return model

# load and prepare training images
def load_real_samples(filename):
	# load the dataset
	data = np.load(filename)
	# unpack arrays
	X1, X2 = data['arr_0'], data['arr_1']
	# scale from [0,255] to [-1,1]
	X1 = (X1 - 127.5) / 127.5
	X2 = (X2 - 127.5) / 127.5
	return [X1, X2]

# select a batch of random samples, returns images and target
def generate_real_samples(dataset, n_samples, patch_shape):
	# choose random instances
	ix = np.random.randint(0, dataset.shape[0], n_samples)
	# retrieve selected images
	X = dataset[ix]
	# generate 'real' class labels (1)
	y = np.ones((n_samples, patch_shape, patch_shape, 1)) #(1,16,16,1)
	return X, y

# generate a batch of images, returns images and targets
def generate_fake_samples(g_model, dataset, patch_shape):
	# generate fake instance
	X = g_model.predict(dataset)
	# create 'fake' class labels (0)
	y = np.zeros((len(X), patch_shape, patch_shape, 1)) # (1, 16,16,1)
	return X, y

# save the generator models to file
def save_models(step, g_model_AtoB, g_model_BtoA):
	# save the first generator model
	filename1 = 'g_model_AtoB_%06d.h5' % (step+1)
	g_model_AtoB.save(filename1)
	# save the second generator model
	filename2 = 'g_model_BtoA_%06d.h5' % (step+1)
	g_model_BtoA.save(filename2)
	print('>Saved: %s and %s' % (filename1, filename2))

# generate samples and save as a plot and save the model
def summarize_performance(step, g_model, trainX, name, n_samples=5):
	# select a sample of input images
	X_in, _ = generate_real_samples(trainX, n_samples, 0)
	# generate translated images
	X_out, _ = generate_fake_samples(g_model, X_in, 0)
	# scale all pixels from [-1,1] to [0,1]
	X_in = (X_in + 1) / 2.0
	X_out = (X_out + 1) / 2.0
	# plot real images
	for i in range(n_samples):
		pyplot.subplot(2, n_samples, 1 + i)
		pyplot.axis('off')
		pyplot.imshow(X_in[i])
	# plot translated image
	for i in range(n_samples):
		pyplot.subplot(2, n_samples, 1 + n_samples + i)
		pyplot.axis('off')
		pyplot.imshow(X_out[i])
	# save plot to file
	filename1 = '%s_generated_plot_%06d.png' % (name, (step+1))
	pyplot.savefig(filename1)
	pyplot.close()

# update image pool for fake images
def update_image_pool(pool, images, max_size=50):
	selected = list()
	for image in images:
		if len(pool) < max_size:
			# stock the pool
			pool.append(image)
			selected.append(image)
		elif random() < 0.5:
			# use image, but don't add it to the pool
			selected.append(image)
		else:
			# replace an existing image and use replaced image
			ix = np.random.randint(0, len(pool))
			selected.append(pool[ix])
			pool[ix] = image
	return np.asarray(selected)

# train cyclegan models
def train(d_model_A, d_model_B, g_model_AtoB, g_model_BtoA, c_model_AtoB, c_model_BtoA, dataset):
	# define properties of the training run
	n_epochs, n_batch, = 100, 1
	# determine the output square shape of the discriminator
	n_patch = d_model_A.output_shape[1] # 16
	# unpack dataset
	trainA, trainB = dataset
	# prepare image pool for fakes
	poolA, poolB = list(), list()
	# calculate the number of batches per training epoch
	bat_per_epo = int(len(trainA) / n_batch) # 1187
	# calculate the number of training iterations
	n_steps = bat_per_epo * n_epochs # 1187 * 100
	# manually enumerate epochs
	for i in range(n_steps):
		# select a batch of real samples
		X_realA, y_realA = generate_real_samples(trainA, n_batch, n_patch) # 1187, 1, 16
		X_realB, y_realB = generate_real_samples(trainB, n_batch, n_patch)
		# generate a batch of fake samples
		X_fakeA, y_fakeA = generate_fake_samples(g_model_BtoA, X_realB, n_patch) # B>A
		X_fakeB, y_fakeB = generate_fake_samples(g_model_AtoB, X_realA, n_patch) # A>B
		# update fakes from pool
		X_fakeA = update_image_pool(poolA, X_fakeA)
		X_fakeB = update_image_pool(poolB, X_fakeB)
		# update generator B->A via adversarial and cycle loss
		g_loss2, _, _, _, _ = c_model_BtoA.train_on_batch([X_realB, X_realA], [y_realA, X_realA, X_realB, X_realA])
		# update discriminator for A -> [real/fake]
		dA_loss1 = d_model_A.train_on_batch(X_realA, y_realA)
		dA_loss2 = d_model_A.train_on_batch(X_fakeA, y_fakeA)
		# update generator A->B via adversarial and cycle loss
		g_loss1, _, _, _, _ = c_model_AtoB.train_on_batch([X_realA, X_realB], [y_realB, X_realB, X_realA, X_realB])
		# update discriminator for B -> [real/fake]
		dB_loss1 = d_model_B.train_on_batch(X_realB, y_realB)
		dB_loss2 = d_model_B.train_on_batch(X_fakeB, y_fakeB)
		# summarize performance
		print('>%d, dA[%.3f,%.3f] dB[%.3f,%.3f] g[%.3f,%.3f]' % (i+1, dA_loss1,dA_loss2, dB_loss1,dB_loss2, g_loss1,g_loss2))
		# evaluate the model performance every so often
		if (i+1) % (bat_per_epo * 1) == 0:
			# plot A->B translation
			summarize_performance(i, g_model_AtoB, trainA, 'AtoB')
			# plot B->A translation
			summarize_performance(i, g_model_BtoA, trainB, 'BtoA')
		if (i+1) % (bat_per_epo * 5) == 0:
			# save the models
			save_models(i, g_model_AtoB, g_model_BtoA)


if __name__ == '__main__':
	# load image data
	dataset = load_real_samples('horse2zebra_256.npz')
	print('Loaded', dataset[0].shape, dataset[1].shape)
	# define input shape based on the loaded dataset
	image_shape = dataset[0].shape[1:]
	# generator: A -> B
	g_model_AtoB = define_generator(image_shape)
	# generator: B -> A
	g_model_BtoA = define_generator(image_shape)
	# discriminator: A -> [real/fake]
	d_model_A = define_discriminator(image_shape)
	# discriminator: B -> [real/fake]
	d_model_B = define_discriminator(image_shape)
	# composite: A -> B -> [real/fake, A]
	c_model_AtoB = define_composite_model(g_model_AtoB, d_model_B, g_model_BtoA, image_shape)
	# composite: B -> A -> [real/fake, B]
	c_model_BtoA = define_composite_model(g_model_BtoA, d_model_A, g_model_AtoB, image_shape)
	# train models
	train(d_model_A, d_model_B, g_model_AtoB, g_model_BtoA, c_model_AtoB, c_model_BtoA, dataset)

展示

第二部分代码运行后生成的生成假图片——野马转斑马,斑马转野马

转载:GAN实例——野马变斑马【实测成功】_第2张图片

转载:GAN实例——野马变斑马【实测成功】_第3张图片
转载:GAN实例——野马变斑马【实测成功】_第4张图片

博主第一部分代码在自己的神舟笔记本的pycharm运行(得到数据集文件horse2zebra_256.npz);

第二部分代码用服务器linux运行。


该部分代码是用cpu运行,运行一个epoch需要10个小时(一共需要运行100个epoch)——所以训练完需要一个月——不知道是因为linux的tensorflow是cpu版本的原因,还是需要将linux的tensorflow重装成gpu版本后再进行cuda设置)

你可能感兴趣的:(python)