用GAN训练自己的数据生成新的图片 |
您所在的位置：网站首页 › 你自己的图片不是我的图片 › 用GAN训练自己的数据生成新的图片 |
用GAN训练自己的数据生成新的图片
|
出于工作需要，学习了GAN，原理这块就不多讲了，主要讲怎么训练自己的数据生成新的图片，因为博客上大多是生成MNIST数据集,生成自己的图片时，有些小坑。下面记录一下本人基于参考链接，将MNIST数据集的代码改成生成自己数据时遇到的坑。 一、读取数据问题 # MNIST dataset mnist = datasets.MNIST( root='./data/', train=True, transform=img_transform, download=True) # Data loader dataloader = torch.utils.data.DataLoader( dataset=mnist, batch_size=batch_size, shuffle=True)可以看到，datasets.MNIST这个肯定不能用于我们自己的数据。我借鉴了原来做二分类的datasets.ImageFolder。发现老是报错： RuntimeError: Found 0 files in subfolders of: E:\Projects\gan\battery\ng Supported extensions are: .jpg,.jpeg,.png,.ppm,.bmp,.pgm,.tif,.tiff,.webp后面单步调试，原来这个函数是需要文件夹下面有分类标签的，根据子文件夹名生成分类标签。故放弃，只能自己写了。下面是参考网上的，写了个读取数据的函数： import numpy as np import torch import os import random from PIL import Image from torch.utils.data import Dataset class myDataset(Dataset): def __init__(self, data_dir, transform): self.data_dir = data_dir self.transform = transform self.img_names = [name for name in list(filter(lambda x: x.endswith(".jpg"), os.listdir(self.data_dir)))] def __getitem__(self, index): path_img = os.path.join(self.data_dir, self.img_names[index]) img = Image.open(path_img).convert('RGB') if self.transform is not None: img = self.transform(img) return img def __len__(self): if len(self.img_names) == 0: raise Exception("\ndata_dir:{} is a empty dir! Please checkout your path to images!".format(self.data_dir)) return len(self.img_names) 二、维度不匹配问题解决了读取数据之后，发现可以训练了，因为参考链接的MINIST数据都是单通道的，我们大部分图像都是3通道的，所以我将通道改为3后，发现判别器那块老是报错，标签和数据不匹配。 RuntimeError: mat1 dim 1 must match mat2 dim 0后面一查，发现问题出在这句上面： for i, (imgs, _) in enumerate(dataloader)这样得到的imgs已经没有batch-size的信息了，需要改为这样： for i, imgs in enumerate(dataloader):下面是整个代码块，贴上去记录下来，以便过段时间万一忘了，还有个看的地方。 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, models, transforms from torch.autograd import Variable import torch.nn as nn import torch.nn.functional as F from tools.my_dataset import myDataset import torch os.makedirs("images", exist_ok=True) parser = argparse.ArgumentParser() parser.add_argument("--n_epochs", type=int, default=50, help="number of epochs of training") parser.add_argument("--batch_size", type=int, default=2, 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=4, 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=128, help="size of each image dimension") parser.add_argument("--channels", type=int, default=3, help="number of image channels") parser.add_argument("--sample_interval", type=int, default=400, help="interval betwen image samples") opt = parser.parse_args() print(opt) img_shape = (opt.channels, opt.img_size, opt.img_size) cuda = True if torch.cuda.is_available() else False print('cuda is',cuda) class Generator(nn.Module): def __init__(self): super(Generator, self).__init__() def block(in_feat, out_feat, normalize=True): layers = [nn.Linear(in_feat, out_feat)] if normalize: layers.append(nn.BatchNorm1d(out_feat, 0.8)) layers.append(nn.LeakyReLU(0.2, inplace=True)) return layers self.model = nn.Sequential( *block(opt.latent_dim, 128, normalize=False), *block(128, 256), *block(256, 512), *block(512, 1024), nn.Linear(1024, int(np.prod(img_shape))), nn.Tanh() ) def forward(self, z): img = self.model(z) img = img.view(img.size(0), *img_shape) return img class Discriminator(nn.Module): def __init__(self): super(Discriminator, self).__init__() self.model = nn.Sequential( nn.Linear(int(np.prod(img_shape)), 512), nn.LeakyReLU(0.2, inplace=True), nn.Linear(512, 256), nn.LeakyReLU(0.2, inplace=True), nn.Linear(256, 1), nn.Sigmoid(), ) def forward(self, img): img_flat = img.view(img.size(0), -1) validity = self.model(img_flat) 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() # # Configure data loader # os.makedirs("./data/mnist", exist_ok=True) # dataloader = torch.utils.data.DataLoader( # datasets.MNIST( # "./data/mnist", # train=True, # download=True, # transform=transforms.Compose( # [transforms.Resize(opt.img_size), transforms.ToTensor(), transforms.Normalize([0.5], [0.5])] # ), # ), # batch_size=opt.batch_size, # shuffle=True, # ) dataset = r'E:\Projects\gan\battery' ng_directory = os.path.join(dataset, 'ng') ok_directory = os.path.join(dataset, 'ok') image_transforms = { 'ng': transforms.Compose([ transforms.Resize([opt.img_size,opt.img_size]), transforms.ToTensor(), ]), 'ok': transforms.Compose([ transforms.Resize([opt.img_size,opt.img_size]), transforms.ToTensor(), ])} data = { 'ng': myDataset(data_dir=ng_directory, transform=image_transforms['ng']), 'ok': myDataset(data_dir=ok_directory, transform=image_transforms['ok']) } dataloader = DataLoader(data['ng'], batch_size=opt.batch_size, shuffle=True) ng_data_size = len(data['ng']) ok_data_size = len(data['ok']) print('train_size: {:4d} valid_size:{:4d}'.format(ng_data_size, ok_data_size)) # 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): for i, imgs in enumerate(dataloader): # Adversarial ground truths valid = Variable(Tensor(imgs.size(0), 1).fill_(1.0), requires_grad=False) fake = Variable(Tensor(imgs.size(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, 3, (imgs.shape[0], opt.latent_dim)))) # Generate a batch of images gen_imgs = generator(z) # Loss measures generator's ability to fool the discriminator aa = discriminator(gen_imgs) g_loss = adversarial_loss(aa, valid) g_loss.backward() optimizer_G.step() # --------------------- # Train Discriminator # --------------------- optimizer_D.zero_grad() # Measure discriminator's ability to classify real from generated samples bb = discriminator(real_imgs) real_loss = adversarial_loss(bb, valid) # 此处需要注意，detach()是为了截断梯度流，不计算生成网络的损失， # 因为d_loss包含了fake_loss，回传的时候如果不做处理，默认会计算generator的梯度， # 而这里只需要计算判别网络的梯度，更新其权重值，生成网络保持不变即可。 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()) ) batches_done = epoch * len(dataloader) + i if batches_done % opt.sample_interval == 0: save_image(gen_imgs.data[:25], "images/%d.png" % batches_done, nrow=5, normalize=True)
上面是原始图片，下面是生成的图片，从开始的噪声，到慢慢有点样子，还没训练完，由于我的显卡比较小，GTX1660Ti，6G显存，所以将原始图片从800x800压缩到了128x128，可能影响了效果，没关系，后面还可以优化，包括将全连接网络改为卷积的，图片设置大点，等等。
参考链接 GANs入门系列之（二）用GAN生成MNIST数据集之pytorch实现 |
【本文地址】