快捷導(dǎo)航

如何用GAN訓(xùn)練自己的數(shù)據(jù)生成新的圖片

更新時間：2023年03月25日 09:42:55 作者：雪地(>^ω^<)

這篇文章主要介紹了如何用GAN訓(xùn)練自己的數(shù)據(jù)生成新的圖片問題，具有很好的參考價值，希望對大家有所幫助。如有錯誤或未考慮完全的地方，望不吝賜教

一、讀取數(shù)據(jù)問題

# 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這個肯定不能用于我們自己的數(shù)據(jù)。我借鑒了原來做二分類的datasets.ImageFolder。

發(fā)現(xiàn)老是報錯：

RuntimeError: Found 0 files in subfolders of: E:\Projects\gan\battery\ng
Supported extensions are: .jpg,.jpeg,.png,.ppm,.bmp,.pgm,.tif,.tiff,.webp

后面單步調(diào)試，原來這個函數(shù)是需要文件夾下面有分類標簽的，根據(jù)子文件夾名生成分類標簽。

故放棄，只能自己寫了。

下面是參考網(wǎng)上的，寫了個讀取數(shù)據(jù)的函數(shù)：

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、維度不匹配問題

解決了讀取數(shù)據(jù)之后，發(fā)現(xiàn)可以訓(xùn)練了，因為參考鏈接的MINIST數(shù)據(jù)都是單通道的，我們大部分圖像都是3通道的，所以我將通道改為3后，發(fā)現(xiàn)判別器那塊老是報錯，標簽和數(shù)據(jù)不匹配。

RuntimeError: mat1 dim 1 must match mat2 dim 0

后面一查，發(fā)現(xiàn)問題出在這句上面：

for i, (imgs, _) in enumerate(dataloader)

這樣得到的imgs已經(jīng)沒有batch-size的信息了，需要改為這樣：

for i, imgs in enumerate(dataloader):

下面是整個代碼塊，貼上去記錄下來，以便過段時間萬一忘了，還有個看的地方。

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)
        # 此處需要注意，detach()是為了截斷梯度流，不計算生成網(wǎng)絡(luò)的損失，
        # 因為d_loss包含了fake_loss，回傳的時候如果不做處理，默認會計算generator的梯度，
        # 而這里只需要計算判別網(wǎng)絡(luò)的梯度，更新其權(quán)重值，生成網(wǎng)絡(luò)保持不變即可。
        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)

上面是原始圖片，下面是生成的圖片，從開始的噪聲，到慢慢有點樣子，還沒訓(xùn)練完，由于我的顯卡比較小，GTX1660Ti，6G顯存，所以將原始圖片從800x800壓縮到了128x128，可能影響了效果，沒關(guān)系，后面還可以優(yōu)化，包括將全連接網(wǎng)絡(luò)改為卷積的，圖片設(shè)置大點，等等。