利用DCGAN生成动漫头像
作者：互联网
1.首先获取到动漫图片，这里用python的scrapy框架来爬取动漫图片。图片来自于https://konachan.net/post?page=1。这里给出几个关键文件内容：
（1）items.py
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html
import scrapy
class KonachanItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
img = scrapy.Field()
（2）spider.py（自己创建的）
import scrapy
import os
import requests
from ..items import KonachanItem
class MySpider(scrapy.spiders.Spider):
name = "konachan"
start_urls = ['https://konachan.net/post?page=1']
def parse(self,response):
base_url = 'https://konachan.net/post?page='
page_info = response.xpath("//div[@class='pagination']/a/text()").extract()
last_page = int(page_info[-2])
for page in range(1, last_page+1):
url = base_url + str(page)
yield scrapy.Request(url,callback=self.getImg)
def getImg(self,response):
imgs = response.xpath("//a[@class='thumb']/img/@src").extract()
for img in imgs:
item = KonachanItem()
imglist = []
imglist.append(img) #要用列表，否则会报错
item['img'] = imglist
yield item
（3）settings.py（只给出修改的几行）
ITEM_PIPELINES = {'scrapy.pipelines.images.ImagesPipeline': 300}
IMAGES_STORE = 'images' #保存文件的目录
IMAGES_URLS_FIELD = 'img' #和在items.py里面定义的field一致
最后在项目根目录运行项目即可，scrapy crawl konachan。
最后结果：在项目根目录会生成faces/full文件夹，里面是爬取的图片。大约有16w+张图片。
2.由于我们需要获取的是头像图片来训练DCGAN，故需要对这些图片进行处理。这里使用github上的一个基于opencv的工具。https://github.com/nagadomi/lbpcascade_animeface。
import cv2
import sys
import os.path
from glob import glob
def detect(filename, cascade_file="lbpcascade_animeface.xml"):
if not os.path.isfile(cascade_file):
raise RuntimeError("%s: not found" % cascade_file)
cascade = cv2.CascadeClassifier(cascade_file)
image = cv2.imread(filename)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = cv2.equalizeHist(gray)
faces = cascade.detectMultiScale(gray,
# detector options
scaleFactor=1.1,
minNeighbors=5,
minSize=(48, 48))
for i, (x, y, w, h) in enumerate(faces):
face = image[y: y + h, x:x + w, :]
face = cv2.resize(face, (96, 96))
save_filename = '%s-%d.jpg' % (os.path.basename(filename).split('.')[0], i)
cv2.imwrite("faces/" + save_filename, face)
if __name__ == '__main__':
if os.path.exists('faces') is False:
os.makedirs('faces') #存放最后头像图片的目录
file_list = glob('images/full/*.jpg') #之前爬取的图片所在目录
for filename in file_list:
detect(filename)
注意：一定要有lbpcascade_animeface.xml文件。
最后结果：大约有64000+张头像图片。
3.现在用这些头像图片来训练DCGAN。这里使用pytorch框架实现。github源码地址：https://github.com/eriklindernoren/PyTorch-GAN/blob/master/implementations/dcgan/dcgan.py（需要根据自己的要求修改模型配置）
import argparse
import os
import numpy as np
import math
import torchvision.transforms as transforms
from torchvision.utils import save_image
from torch.utils.data import DataLoader
from torchvision import datasets
from torch.autograd import Variable
import torch.nn as nn
import torch.nn.functional as F
import torch
os.makedirs("fake", exist_ok=True)
parser = argparse.ArgumentParser()
parser.add_argument("--n_epochs", type=int, default=100, help="number of epochs of training")
parser.add_argument("--batch_size", type=int, default=64, 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("--n_cpu", type=int, default=8, help="number of cpu threads to use during batch generation")
parser.add_argument("--latent_dim", type=int, default=100, help="dimensionality of the latent space")
parser.add_argument("--img_size", type=int, default=96, help="size of each image dimension")
parser.add_argument("--channels", type=int, default=3, help="number of image channels")
opt = parser.parse_args()
print(opt)
cuda = True if torch.cuda.is_available() else False
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)# init the params of conv layer
elif classname.find("BatchNorm2d") != -1:
torch.nn.init.normal_(m.weight.data, 1.0, 0.02) #init the params of bn layer
torch.nn.init.constant_(m.bias.data, 0.0)
class Generator(nn.Module):
def __init__(self):
super(Generator, self).__init__()
self.init_size = opt.img_size // 4
self.l1 = nn.Sequential(nn.Linear(opt.latent_dim, 128 * self.init_size ** 2))
self.conv_blocks = nn.Sequential(
nn.BatchNorm2d(128),
nn.Upsample(scale_factor=2),
nn.Conv2d(128, 128, 3, stride=1, padding=1),
nn.BatchNorm2d(128, 0.8),
nn.LeakyReLU(0.2, inplace=True),
nn.Upsample(scale_factor=2),
nn.Conv2d(128, 64, 3, stride=1, padding=1),
nn.BatchNorm2d(64, 0.8),
nn.LeakyReLU(0.2, inplace=True),
nn.Conv2d(64, opt.channels, 3, stride=1, padding=1),
nn.Tanh(),
)
def forward(self, z):
out = self.l1(z)
out = out.view(out.shape[0], 128, self.init_size, self.init_size)
img = self.conv_blocks(out)
return img
class Discriminator(nn.Module):
def __init__(self):
super(Discriminator, self).__init__()
def discriminator_block(in_filters, out_filters, bn=True):
block = [nn.Conv2d(in_filters, out_filters, 3, 2, 1), nn.LeakyReLU(0.2, inplace=True), nn.Dropout2d(0.25)]
if bn:
block.append(nn.BatchNorm2d(out_filters, 0.8))
return block
self.model = nn.Sequential(
*discriminator_block(opt.channels, 16, bn=False),
*discriminator_block(16, 32),
*discriminator_block(32, 64),
*discriminator_block(64, 128),
)
# The height and width of downsampled image
ds_size = opt.img_size // 2 ** 4
self.adv_layer = nn.Sequential(nn.Linear(128 * ds_size ** 2, 1), nn.Sigmoid())
def forward(self, img):
out = self.model(img)
out = out.view(out.shape[0], -1)
validity = self.adv_layer(out)
return validity
# Loss function
adversarial_loss = torch.nn.BCELoss()
# Initialize generator and discriminator
generator = Generator()
discriminator = Discriminator()
if cuda:
generator.cuda()
discriminator.cuda()
adversarial_loss.cuda()
# Initialize weights
generator.apply(weights_init_normal)
discriminator.apply(weights_init_normal)
# Configure data loader
dataloader = torch.utils.data.DataLoader(
datasets.ImageFolder(
root="./faces", #这里改为训练数据所在目录
transform=transforms.Compose(
[transforms.Resize(opt.img_size), transforms.ToTensor(), transforms.Normalize((0.5,0.5,0.5), (0.5,0.5,0.5))]
)),
batch_size=opt.batch_size,
shuffle=True,
drop_last=True
)
# Optimizers
optimizer_G = torch.optim.Adam(generator.parameters(), lr=opt.lr, betas=(opt.b1, opt.b2))
optimizer_D = torch.optim.Adam(discriminator.parameters(), lr=opt.lr, betas=(opt.b1, opt.b2))
Tensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor
# ----------
# Training
# ----------
for epoch in range(opt.n_epochs):
for i, (imgs, _) in enumerate(dataloader):
# Adversarial ground truths
valid = Variable(Tensor(imgs.shape[0], 1).fill_(1.0), requires_grad=False)
fake = Variable(Tensor(imgs.shape[0], 1).fill_(0.0), requires_grad=False)
# Configure input
real_imgs = Variable(imgs.type(Tensor))
# -----------------
# Train Generator
# -----------------
optimizer_G.zero_grad()
# Sample noise as generator input
z = Variable(Tensor(np.random.normal(0, 1, (imgs.shape[0], opt.latent_dim))))
# Generate a batch of images
gen_imgs = generator(z)
# Loss measures generator's ability to fool the discriminator
g_loss = adversarial_loss(discriminator(gen_imgs), valid) # make the img generated from generator close to real image,minimize the loss of fake image with valid
g_loss.backward()
optimizer_G.step()
# ---------------------
# Train Discriminator
# ---------------------
optimizer_D.zero_grad()
# Measure discriminator's ability to classify real from generated samples
real_loss = adversarial_loss(discriminator(real_imgs), valid)
fake_loss = adversarial_loss(discriminator(gen_imgs.detach()), fake)
d_loss = (real_loss + fake_loss) / 2
d_loss.backward()
optimizer_D.step()
print(
"[Epoch %d/%d] [Batch %d/%d] [D loss: %f] [G loss: %f]"
% (epoch, opt.n_epochs, i, len(dataloader), d_loss.item(), g_loss.item())
)
#save_image every epoch
if((i + 1) == len(dataloader)):
save_image(gen_imgs.data[:25], "fake/%d.png" % epoch, nrow=5, normalize=True)
注意：在DataLoader中的root应该配置成自己训练数据的目录，并且在该目录下还需要再创建一个目录，该目录是训练数据的分类名。比如，我的训练数据存放在"faces/real/"下，而root应该写"faces"。否则会报错。
第一个epoch：
第10个epoch：
第100个epoch：
额，感觉看的很别扭，不知道哪出问题了，以后有时间再调下参数吧。如果有大神知道的话，希望大神指出错误，万分感谢。
注：使用爬虫收集的数据只是用于学习，不作商业用途，如有侵权，还请告知。
标签：opt,loss,nn,动漫,self,头像,init,DCGAN,import 来源： https://www.cnblogs.com/liualex1109/p/11769506.html