【Pytorch深度学习50篇】·······第七篇:【4】GAN生成对抗网络---cycleGAN

本来GAN这系列我只打算说到pix2pix的,但是情况有变,因为有人再看(感谢各位老铁支持)

所以决定再来一篇难度更大的GAN----cycleGAN,这次我们来个莫奈画生成,上强度!!

4.CycleGAN

4.1 cycleGAN的模型结构

【Pytorch深度学习50篇】·······第七篇:【4】GAN生成对抗网络---cycleGAN_第1张图片

仍旧是:生成器+判别器

好了,这次肯定有人要说了,这哪里变难了,感觉比之前的都简单。其实并不是的,cycle这个单词就是循环,弯弯绕绕的意思,你看你一会晕不晕。希望别晕。

4.2算法逻辑

还是先来介绍一下数据集monet2photo,莫奈画和自然画

【Pytorch深度学习50篇】·······第七篇:【4】GAN生成对抗网络---cycleGAN_第2张图片                                     【Pytorch深度学习50篇】·······第七篇:【4】GAN生成对抗网络---cycleGAN_第3张图片

左边是莫奈画(有点像油画),右边是自然画,我们的目的是,输入一张自然画能够生成一张莫奈画。这个也就是传说中的风格迁移

算法逻辑:

1.首先我们先定义两个生成器:生成器A和生成器B。再定义两个判别器:判别器A,判别器B;生成器A用于生成自然图,生成器B用于生成莫奈画。

将莫奈画送入生成器B得到gene_A,gene_A和莫奈画求L1loss,将自然画送入生成器A得到gene_B,gene_B和自然画求L1loss,这一步的目的是让生成器A有生成自然画的能力,让生成器B有生成莫奈画的能力。于此同时,我们将莫奈画送入生成器A得到fack_B,将fack_B送入判别器A,我们自然画送入生成器B得到fack_A,将fack_A送入判别器B,让输出的N*16*16*1的数据全为1,这里是优化生成器,能够生成逼真的图像。还没完,现在我们开始cycle了,我们将fack_B再次送入生成器B得到recov_A,将fack_A再次送入生成器A得到recov_B,我们再求recov_A和莫奈画的L1loss以及recov_B和自然画的L1loss,这个的目的是为了,为了让生成器A有能够将莫奈画转换为自然化的能力。所有的loss全部加起来然后反向传播,所以第一步的目的还是为了优化生成器,和以往不同的是,我们优化了两个生成器。

2.因为我们有两个判别器,所以我们也要优化两个判别器。

莫奈画送入判别器B,我们此时希望生成的N*16*16*1的数据是全1的,fack_A也送入判别器B,此时我们希望生成的N*16*16*1的数据是全0的。以此来优化判别器B。

自然画送入判别器A,我们此时希望生成的N*16*16*1的数据是全1的,fack_B也送入判别器A,此时我们希望生成的N*16*16*1的数据是全0的。以此来优化判别器A。

3.至此,生成器和判别器就开始对抗起来了,印证了那句老话,人生就是一个圈。

4.3代码实现

models.py

import torch.nn as nn
import torch.nn.functional as F
import torch


def weights_init_normal(m):
    classname = m.__class__.__name__
    if classname.find("Conv") != -1:
        torch.nn.init.normal_(m.weight.data, 0.0, 0.02)
        if hasattr(m, "bias") and m.bias is not None:
            torch.nn.init.constant_(m.bias.data, 0.0)
    elif classname.find("BatchNorm2d") != -1:
        torch.nn.init.normal_(m.weight.data, 1.0, 0.02)
        torch.nn.init.constant_(m.bias.data, 0.0)


##############################
#           RESNET
##############################


class ResidualBlock(nn.Module):
    def __init__(self, in_features):
        super(ResidualBlock, self).__init__()

        self.block = nn.Sequential(
            nn.ReflectionPad2d(1),
            nn.Conv2d(in_features, in_features, 3),
            nn.InstanceNorm2d(in_features),
            nn.ReLU(inplace=True),
            nn.ReflectionPad2d(1),
            nn.Conv2d(in_features, in_features, 3),
            nn.InstanceNorm2d(in_features),
        )

    def forward(self, x):
        return x + self.block(x)


class GeneratorResNet(nn.Module):
    def __init__(self, input_shape, num_residual_blocks):
        super(GeneratorResNet, self).__init__()

        channels = input_shape[0]

        # Initial convolution block
        out_features = 64
        model = [
            nn.ReflectionPad2d(channels),
            nn.Conv2d(channels, out_features, 7),
            nn.InstanceNorm2d(out_features),
            nn.ReLU(inplace=True),
        ]
        in_features = out_features

        # Downsampling
        for _ in range(2):
            out_features *= 2
            model += [
                nn.Conv2d(in_features, out_features, 3, stride=2, padding=1),
                nn.InstanceNorm2d(out_features),
                nn.ReLU(inplace=True),
            ]
            in_features = out_features

        # Residual blocks
        for _ in range(num_residual_blocks):
            model += [ResidualBlock(out_features)]

        # Upsampling
        for _ in range(2):
            out_features //= 2
            model += [
                nn.Upsample(scale_factor=2),
                nn.Conv2d(in_features, out_features, 3, stride=1, padding=1),
                nn.InstanceNorm2d(out_features),
                nn.ReLU(inplace=True),
            ]
            in_features = out_features

        # Output layer
        model += [nn.ReflectionPad2d(channels), nn.Conv2d(out_features, channels, 7), nn.Tanh()]

        self.model = nn.Sequential(*model)

    def forward(self, x):
        return self.model(x)


##############################
#        Discriminator
##############################


class Discriminator(nn.Module):
    def __init__(self, input_shape):
        super(Discriminator, self).__init__()

        channels, height, width = input_shape

        # Calculate output shape of image discriminator (PatchGAN)
        self.output_shape = (1, height // 2 ** 4, width // 2 ** 4)

        def discriminator_block(in_filters, out_filters, normalize=True):
            """Returns downsampling layers of each discriminator block"""
            layers = [nn.Conv2d(in_filters, out_filters, 4, stride=2, padding=1)]
            if normalize:
                layers.append(nn.InstanceNorm2d(out_filters))
            layers.append(nn.LeakyReLU(0.2, inplace=True))
            return layers

        self.model = nn.Sequential(
            *discriminator_block(channels, 64, normalize=False),
            *discriminator_block(64, 128),
            *discriminator_block(128, 256),
            *discriminator_block(256, 512),
            nn.ZeroPad2d((1, 0, 1, 0)),
            nn.Conv2d(512, 1, 4, padding=1)
        )

    def forward(self, img):
        return self.model(img)

datasets.py

import glob
import random
import os

from torch.utils.data import Dataset
from PIL import Image
import torchvision.transforms as transforms


def to_rgb(image):
    rgb_image = Image.new("RGB", image.size)
    rgb_image.paste(image)
    return rgb_image


class ImageDataset(Dataset):
    def __init__(self, root, transforms_=None, unaligned=False, mode="train"):
        self.transform = transforms.Compose(transforms_)
        self.unaligned = unaligned

        self.files_A = sorted(glob.glob(os.path.join(root, "%s/A" % mode) + "/*.*"))
        self.files_B = sorted(glob.glob(os.path.join(root, "%s/B" % mode) + "/*.*"))

    def __getitem__(self, index):
        image_A = Image.open(self.files_A[index % len(self.files_A)])

        if self.unaligned:
            image_B = Image.open(self.files_B[random.randint(0, len(self.files_B) - 1)])
        else:
            image_B = Image.open(self.files_B[index % len(self.files_B)])

        # Convert grayscale images to rgb
        if image_A.mode != "RGB":
            image_A = to_rgb(image_A)
        if image_B.mode != "RGB":
            image_B = to_rgb(image_B)

        # print(self.files_A[index % len(self.files_A)])
        # print(self.files_B[index % len(self.files_B)])


        item_A = self.transform(image_A)
        item_B = self.transform(image_B)
        return {"A": item_A, "B": item_B}

    def __len__(self):
        return max(len(self.files_A), len(self.files_B))

utils.py

import random
import time
import datetime
import sys

from torch.autograd import Variable
import torch
import numpy as np

from torchvision.utils import save_image


class ReplayBuffer:
    def __init__(self, max_size=50):
        assert max_size > 0, "Empty buffer or trying to create a black hole. Be careful."
        self.max_size = max_size
        self.data = []

    def push_and_pop(self, data):
        to_return = []
        for element in data.data:
            element = torch.unsqueeze(element, 0)
            if len(self.data) < self.max_size:
                self.data.append(element)
                to_return.append(element)
            else:
                if random.uniform(0, 1) > 0.5:
                    i = random.randint(0, self.max_size - 1)
                    to_return.append(self.data[i].clone())
                    self.data[i] = element
                else:
                    to_return.append(element)
        return Variable(torch.cat(to_return))


class LambdaLR:
    def __init__(self, n_epochs, offset, decay_start_epoch):
        assert (n_epochs - decay_start_epoch) > 0, "Decay must start before the training session ends!"
        self.n_epochs = n_epochs
        self.offset = offset
        self.decay_start_epoch = decay_start_epoch

    def step(self, epoch):
        return 1.0 - max(0, epoch + self.offset - self.decay_start_epoch) / (self.n_epochs - self.decay_start_epoch)

cyclegan.py

import argparse
import os
import numpy as np
import math
import itertools
import datetime
import time

import torchvision.transforms as transforms
from torchvision.utils import save_image, make_grid

from torch.utils.data import DataLoader
from torchvision import datasets
from torch.autograd import Variable

from models import *
from datasets import *
from utils import *

import torch.nn as nn
import torch.nn.functional as F
import torch

parser = argparse.ArgumentParser()
parser.add_argument("--epoch", type=int, default=0, help="epoch to start training from")
parser.add_argument("--n_epochs", type=int, default=200, help="number of epochs of training")
parser.add_argument("--dataset_name", type=str, default="monet2photo", help="name of the dataset")
parser.add_argument("--batch_size", type=int, default=1, help="size of the batches")
parser.add_argument("--lr", type=float, default=0.0002, help="adam: learning rate")
parser.add_argument("--b1", type=float, default=0.5, help="adam: decay of first order momentum of gradient")
parser.add_argument("--b2", type=float, default=0.999, help="adam: decay of first order momentum of gradient")
parser.add_argument("--decay_epoch", type=int, default=100, help="epoch from which to start lr decay")
parser.add_argument("--n_cpu", type=int, default=0, help="number of cpu threads to use during batch generation") # 8
parser.add_argument("--img_height", type=int, default=200, help="size of image height")  # 256
parser.add_argument("--img_width", type=int, default=200, help="size of image width")  # 256
parser.add_argument("--channels", type=int, default=3, help="number of image channels")
parser.add_argument("--sample_interval", type=int, default=100, help="interval between saving generator outputs")
parser.add_argument("--checkpoint_interval", type=int, default=-1, help="interval between saving model checkpoints")
parser.add_argument("--n_residual_blocks", type=int, default=9, help="number of residual blocks in generator")
parser.add_argument("--lambda_cyc", type=float, default=10.0, help="cycle loss weight")
parser.add_argument("--lambda_id", type=float, default=5.0, help="identity loss weight")
opt = parser.parse_args()
print(opt)

# Create sample and checkpoint directories
os.makedirs("images/%s" % opt.dataset_name, exist_ok=True)
os.makedirs("saved_models/%s" % opt.dataset_name, exist_ok=True)

# Losses
criterion_GAN = torch.nn.MSELoss()
criterion_cycle = torch.nn.L1Loss()
criterion_identity = torch.nn.L1Loss()

cuda = torch.cuda.is_available()

input_shape = (opt.channels, opt.img_height, opt.img_width)

# Initialize generator and discriminator
G_AB = GeneratorResNet(input_shape, opt.n_residual_blocks)
G_BA = GeneratorResNet(input_shape, opt.n_residual_blocks)
D_A = Discriminator(input_shape)
D_B = Discriminator(input_shape)

if cuda:
    G_AB = G_AB.cuda()
    G_BA = G_BA.cuda()
    D_A = D_A.cuda()
    D_B = D_B.cuda()
    criterion_GAN.cuda()
    criterion_cycle.cuda()
    criterion_identity.cuda()

if opt.epoch != 0:
    # Load pretrained models
    G_AB.load_state_dict(torch.load("saved_models/%s/G_AB_%d.pth" % (opt.dataset_name, opt.epoch)))
    G_BA.load_state_dict(torch.load("saved_models/%s/G_BA_%d.pth" % (opt.dataset_name, opt.epoch)))
    D_A.load_state_dict(torch.load("saved_models/%s/D_A_%d.pth" % (opt.dataset_name, opt.epoch)))
    D_B.load_state_dict(torch.load("saved_models/%s/D_B_%d.pth" % (opt.dataset_name, opt.epoch)))
else:
    # Initialize weights
    G_AB.apply(weights_init_normal)
    G_BA.apply(weights_init_normal)
    D_A.apply(weights_init_normal)
    D_B.apply(weights_init_normal)

# Optimizers
optimizer_G = torch.optim.Adam(
    itertools.chain(G_AB.parameters(), G_BA.parameters()), lr=opt.lr, betas=(opt.b1, opt.b2)
)
optimizer_D_A = torch.optim.Adam(D_A.parameters(), lr=opt.lr, betas=(opt.b1, opt.b2))
optimizer_D_B = torch.optim.Adam(D_B.parameters(), lr=opt.lr, betas=(opt.b1, opt.b2))

# Learning rate update schedulers
lr_scheduler_G = torch.optim.lr_scheduler.LambdaLR(
    optimizer_G, lr_lambda=LambdaLR(opt.n_epochs, opt.epoch, opt.decay_epoch).step
)
lr_scheduler_D_A = torch.optim.lr_scheduler.LambdaLR(
    optimizer_D_A, lr_lambda=LambdaLR(opt.n_epochs, opt.epoch, opt.decay_epoch).step
)
lr_scheduler_D_B = torch.optim.lr_scheduler.LambdaLR(
    optimizer_D_B, lr_lambda=LambdaLR(opt.n_epochs, opt.epoch, opt.decay_epoch).step
)

Tensor = torch.cuda.FloatTensor if cuda else torch.Tensor

# Buffers of previously generated samples
fake_A_buffer = ReplayBuffer()
fake_B_buffer = ReplayBuffer()

# Image transformations
transforms_ = [
    transforms.Resize(int(opt.img_height * 1.12), Image.BICUBIC),
    transforms.RandomCrop((opt.img_height, opt.img_width)),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
]

# Training data loader
dataloader = DataLoader(
    ImageDataset("./data/%s" % opt.dataset_name, transforms_=transforms_, unaligned=True),
    batch_size=opt.batch_size,
    shuffle=True,
    num_workers=opt.n_cpu,
)
# Test data loader
val_dataloader = DataLoader(
    ImageDataset("./data/%s" % opt.dataset_name, transforms_=transforms_, unaligned=True, mode="test"),
    batch_size=5,
    shuffle=True,
    num_workers=1,
)


def sample_images(batches_done):
    """Saves a generated sample from the test set"""
    imgs = next(iter(val_dataloader))
    G_AB.eval()
    G_BA.eval()
    real_A = Variable(imgs["A"].type(Tensor))
    fake_B = G_AB(real_A)
    real_B = Variable(imgs["B"].type(Tensor))
    fake_A = G_BA(real_B)
    # Arange images along x-axis
    real_A = make_grid(real_A, nrow=5, normalize=True)
    real_B = make_grid(real_B, nrow=5, normalize=True)
    fake_A = make_grid(fake_A, nrow=5, normalize=True)
    fake_B = make_grid(fake_B, nrow=5, normalize=True)
    # Arange images along y-axis
    image_grid = torch.cat((real_A, fake_B, real_B, fake_A), 1)
    save_image(image_grid, "images/%s/%s.png" % (opt.dataset_name, batches_done), normalize=False)


# ----------
#  Training
# ----------

if __name__ == '__main__':
    prev_time = time.time()
    # i, batch = next(enumerate(dataloader))
    for epoch in range(opt.epoch, opt.n_epochs):
        for i, batch in enumerate(dataloader):

            # Set model input
            real_A = Variable(batch["A"].type(Tensor))  # 莫奈画
            real_B = Variable(batch["B"].type(Tensor))  # 自然画

            # Adversarial ground truths
            valid = Variable(Tensor(np.ones((real_A.size(0), *D_A.output_shape))), requires_grad=False)
            fake = Variable(Tensor(np.zeros((real_A.size(0), *D_A.output_shape))), requires_grad=False)

            # ------------------
            #  Train Generators
            # ------------------

            G_AB.train()
            G_BA.train()

            optimizer_G.zero_grad()

            # Identity loss
            loss_id_A = criterion_identity(G_BA(real_A), real_A)
            loss_id_B = criterion_identity(G_AB(real_B), real_B)

            loss_identity = (loss_id_A + loss_id_B) / 2

            # GAN loss
            fake_B = G_AB(real_A)
            loss_GAN_AB = criterion_GAN(D_B(fake_B), valid)
            fake_A = G_BA(real_B)
            loss_GAN_BA = criterion_GAN(D_A(fake_A), valid)

            loss_GAN = (loss_GAN_AB + loss_GAN_BA) / 2

            # Cycle loss
            recov_A = G_BA(fake_B)
            loss_cycle_A = criterion_cycle(recov_A, real_A)
            recov_B = G_AB(fake_A)
            loss_cycle_B = criterion_cycle(recov_B, real_B)

            loss_cycle = (loss_cycle_A + loss_cycle_B) / 2

            # Total loss
            loss_G = loss_GAN + opt.lambda_cyc * loss_cycle + opt.lambda_id * loss_identity

            loss_G.backward()
            optimizer_G.step()

            # -----------------------
            #  Train Discriminator A
            # -----------------------

            optimizer_D_A.zero_grad()

            # Real loss
            loss_real = criterion_GAN(D_A(real_A), valid)
            # Fake loss (on batch of previously generated samples)
            fake_A_ = fake_A_buffer.push_and_pop(fake_A)
            loss_fake = criterion_GAN(D_A(fake_A_.detach()), fake)
            # Total loss
            loss_D_A = (loss_real + loss_fake) / 2

            loss_D_A.backward()
            optimizer_D_A.step()

            # -----------------------
            #  Train Discriminator B
            # -----------------------

            optimizer_D_B.zero_grad()

            # Real loss
            loss_real = criterion_GAN(D_B(real_B), valid)
            # Fake loss (on batch of previously generated samples)
            fake_B_ = fake_B_buffer.push_and_pop(fake_B)
            loss_fake = criterion_GAN(D_B(fake_B_.detach()), fake)
            # Total loss
            loss_D_B = (loss_real + loss_fake) / 2

            loss_D_B.backward()
            optimizer_D_B.step()

            loss_D = (loss_D_A + loss_D_B) / 2

            # --------------
            #  Log Progress
            # --------------

            # Determine approximate time left
            batches_done = epoch * len(dataloader) + i
            batches_left = opt.n_epochs * len(dataloader) - batches_done
            time_left = datetime.timedelta(seconds=batches_left * (time.time() - prev_time))
            prev_time = time.time()

            # Print log
            sys.stdout.write(
                "\r[Epoch %d/%d] [Batch %d/%d] [D loss: %f] [G loss: %f, adv: %f, cycle: %f, identity: %f] ETA: %s"
                % (
                    epoch,
                    opt.n_epochs,
                    i,
                    len(dataloader),
                    loss_D.item(),
                    loss_G.item(),
                    loss_GAN.item(),
                    loss_cycle.item(),
                    loss_identity.item(),
                    time_left,
                )
            )

            # If at sample interval save image
            if batches_done % opt.sample_interval == 0:
                sample_images(batches_done)

        # Update learning rates
        lr_scheduler_G.step()
        lr_scheduler_D_A.step()
        lr_scheduler_D_B.step()

        if opt.checkpoint_interval != -1 and epoch % opt.checkpoint_interval == 0:
            # Save model checkpoints
            torch.save(G_AB.state_dict(), "saved_models/%s/G_AB_%d.pth" % (opt.dataset_name, epoch))
            torch.save(G_BA.state_dict(), "saved_models/%s/G_BA_%d.pth" % (opt.dataset_name, epoch))
            torch.save(D_A.state_dict(), "saved_models/%s/D_A_%d.pth" % (opt.dataset_name, epoch))
            torch.save(D_B.state_dict(), "saved_models/%s/D_B_%d.pth" % (opt.dataset_name, epoch))

 4.4效果展示

这是训练第二轮的结果,所以大家可以寻来你久一点来看看效果。我等不及了。

如果大家像要这整个项目的话,可以私信我!!!!!!!!!!!!!!

至此,敬礼,salute!!!!!

老规矩上咩咩

【Pytorch深度学习50篇】·······第七篇:【4】GAN生成对抗网络---cycleGAN_第4张图片

 

你可能感兴趣的:(生成对抗网络,人工智能,神经网络,python,pytorch)