昇思25天学习打卡营第7天|Pix2Pix实现图像转换

文章目录

- - 昇思MindSpore应用实践
  - - 基于MindSpore的Pix2Pix图像转换
    - - 1、Pix2Pix 概述
      - 2、U-Net架构
      - 定义UNet Skip Connection Block
      - 2、生成器部分
      - 3、基于PatchGAN的判别器
      - 4、Pix2Pix的生成器和判别器初始化
      - 5、模型训练
      - 6、模型推理
  - Reference

昇思MindSpore应用实践

本系列文章主要用于记录昇思25天学习打卡营的学习心得。

基于MindSpore的Pix2Pix图像转换

1、Pix2Pix 概述

Pix2Pix 是一个专门为图像到图像的转换任务设计的网络，可以实现语义/标签到真实图片、灰度图到彩色图、航空图到地图、白天到黑夜、线稿图到实物图的转换。Pix2Pix是将条件GAN（CGAN）应用于有监督（需要成对的输入素描图像Sketch和真实图像GT，来训练网络）的图像到图像翻译的经典之作，和所有的GANs一样，模型同样包括：生成器和判别器两个部分。

CGAN：CGAN(条件GAN) 的目标是生成与给定条件匹配的数据样本。这些条件可以是标签、部分实例标注数据或任何其他形式的多模态辅助信息。CGAN 通过将条件并入网络的生成器和判别器中来指导数据生成过程。
在这里插入图片描述
相比普通的生成对抗损失：
$L_{GAN}(G,D)=\mathbb{E}_{y}[log(D(y))]+\mathbb{E}_{(x,z)}[log(1-D(x,z))]$

$x$ ：代表观测图像的数据。
$z$ ：代表随机噪声的数据。
$y = G (x, z)$ ：生成器网络，给出由观测图像 $x$ 与随机噪声 $z$ 生成的“假”图片，其中 $x$ 来自于训练数据而非生成器。
$D (x, G (x, z))$ ：判别器网络，给出图像判定为真实图像的概率，其中 $x$ 来自于训练数据， $G (x, z)$ 来自于生成器。

CGAN多了来自于观测图像的条件 $x$ （因此Pix2Pix训练时采用有监督的方式，需要标注好的语义数据，如下图中的
Map2Aerial数据集、Anime Sketch Colorization Pair 素描生成动漫数据集），
在这里插入图片描述

CGAN的目标可以表示为：

$L_{CGAN}(G,D)=\mathbb{E}_{(x,y)}[log(D(x,y))]+\mathbb{E}_{(x,z)}[log(1-D(x,G(x,z)))]$

Pix2Pix 还包括 L1 损失，帮助生成器产生结构上接近真实图像的结果，这一点在图像翻译任务中尤为重要：
$L_{L1}(G)=\mathbb{E}_{(x,y,z)}[||y-G(x,z)||_{1}]$

进而得到最终目标：

$arg\min_{G}\max_{D}L_{CGAN}(G,D)+\lambda L_{L1}(G)$

图像转换问题本质上其实就是像素到像素的映射问题，Pix2Pix使用完全一样的网络结构和目标函数，仅更换不同的训练数据集就能分别实现以上的任务。

2、U-Net架构

U-Net架构：Pix2Pix 使用 U-Net 架构作为其生成器，在传统的编解码网络结构基础上加入了跳跃连接的方式，可以更好地捕捉图像的细节和上下文信息，适合于图像到图像的翻译任务。相比于普通的编解码结构（Encoder-Decoder），U-Net在编码器和解码器之间引入了跳跃连接，极大地改善了梯度流：
在这里插入图片描述

定义UNet Skip Connection Block

import mindspore
import mindspore.nn as nn
import mindspore.ops as ops

class UNetSkipConnectionBlock(nn.Cell):
    def __init__(self, outer_nc, inner_nc, in_planes=None, dropout=False,
                 submodule=None, outermost=False, innermost=False, alpha=0.2, norm_mode='batch'):
        super(UNetSkipConnectionBlock, self).__init__()
        down_norm = nn.BatchNorm2d(inner_nc)
        up_norm = nn.BatchNorm2d(outer_nc)
        use_bias = False
        if norm_mode == 'instance':
            down_norm = nn.BatchNorm2d(inner_nc, affine=False)
            up_norm = nn.BatchNorm2d(outer_nc, affine=False)
            use_bias = True
        if in_planes is None:
            in_planes = outer_nc
        down_conv = nn.Conv2d(in_planes, inner_nc, kernel_size=4,
                              stride=2, padding=1, has_bias=use_bias, pad_mode='pad')
        down_relu = nn.LeakyReLU(alpha)
        up_relu = nn.ReLU()
        if outermost:
            up_conv = nn.Conv2dTranspose(inner_nc * 2, outer_nc,
                                         kernel_size=4, stride=2,
                                         padding=1, pad_mode='pad')
            down = [down_conv]
            up = [up_relu, up_conv, nn.Tanh()]
            model = down + [submodule] + up
        elif innermost:
            up_conv = nn.Conv2dTranspose(inner_nc, outer_nc,
                                         kernel_size=4, stride=2,
                                         padding=1, has_bias=use_bias, pad_mode='pad')
            down = [down_relu, down_conv]
            up = [up_relu, up_conv, up_norm]
            model = down + up
        else:
            up_conv = nn.Conv2dTranspose(inner_nc * 2, outer_nc,
                                         kernel_size=4, stride=2,
                                         padding=1, has_bias=use_bias, pad_mode='pad')
            down = [down_relu, down_conv, down_norm]
            up = [up_relu, up_conv, up_norm]

            model = down + [submodule] + up
            if dropout:
                model.append(nn.Dropout(p=0.5))
        self.model = nn.SequentialCell(model)
        self.skip_connections = not outermost

    def construct(self, x):
        out = self.model(x)
        if self.skip_connections:
            out = ops.concat((out, x), axis=1)
        return out

2、生成器部分

原始CGAN的输入是条件x和噪声z两种信息，这里的生成器只使用了条件信息，因此不能生成多样性的结果。因此Pix2Pix在训练和测试时都使用了dropout，这样可以生成多样性的结果。

通过MindSpore实现基于U-Net的生成器：

class UNetGenerator(nn.Cell):
    def __init__(self, in_planes, out_planes, ngf=64, n_layers=8, norm_mode='bn', dropout=False):
        super(UNetGenerator, self).__init__()
        unet_block = UNetSkipConnectionBlock(ngf * 8, ngf * 8, in_planes=None, submodule=None,
                                             norm_mode=norm_mode, innermost=True)
        for _ in range(n_layers - 5):
            unet_block = UNetSkipConnectionBlock(ngf * 8, ngf * 8, in_planes=None, submodule=unet_block,
                                                 norm_mode=norm_mode, dropout=dropout)
        unet_block = UNetSkipConnectionBlock(ngf * 4, ngf * 8, in_planes=None, submodule=unet_block,
                                             norm_mode=norm_mode)
        unet_block = UNetSkipConnectionBlock(ngf * 2, ngf * 4, in_planes=None, submodule=unet_block,
                                             norm_mode=norm_mode)
        unet_block = UNetSkipConnectionBlock(ngf, ngf * 2, in_planes=None, submodule=unet_block,
                                             norm_mode=norm_mode)
        self.model = UNetSkipConnectionBlock(out_planes, ngf, in_planes=in_planes, submodule=unet_block,
                                             outermost=True, norm_mode=norm_mode)

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

3、基于PatchGAN的判别器

判别器使用的PatchGAN结构，可看做卷积。
生成的矩阵中的每个点代表原图的一小块区域（patch）。通过矩阵中的各个值来判断原图中对应每个Patch的真假。

import mindspore.nn as nn

class ConvNormRelu(nn.Cell):
    def __init__(self,
                 in_planes,
                 out_planes,
                 kernel_size=4,
                 stride=2,
                 alpha=0.2,
                 norm_mode='batch',
                 pad_mode='CONSTANT',
                 use_relu=True,
                 padding=None):
        super(ConvNormRelu, self).__init__()
        norm = nn.BatchNorm2d(out_planes)
        if norm_mode == 'instance':
            norm = nn.BatchNorm2d(out_planes, affine=False)
        has_bias = (norm_mode == 'instance')
        if not padding:
            padding = (kernel_size - 1) // 2
        if pad_mode == 'CONSTANT':
            conv = nn.Conv2d(in_planes, out_planes, kernel_size, stride, pad_mode='pad',
                             has_bias=has_bias, padding=padding)
            layers = [conv, norm]
        else:
            paddings = ((0, 0), (0, 0), (padding, padding), (padding, padding))
            pad = nn.Pad(paddings=paddings, mode=pad_mode)
            conv = nn.Conv2d(in_planes, out_planes, kernel_size, stride, pad_mode='pad', has_bias=has_bias)
            layers = [pad, conv, norm]
        if use_relu:
            relu = nn.ReLU()
            if alpha > 0:
                relu = nn.LeakyReLU(alpha)
            layers.append(relu)
        self.features = nn.SequentialCell(layers)

    def construct(self, x):
        output = self.features(x)
        return output

class Discriminator(nn.Cell):
    def __init__(self, in_planes=3, ndf=64, n_layers=3, alpha=0.2, norm_mode='batch'):
        super(Discriminator, self).__init__()
        kernel_size = 4
        layers = [
            nn.Conv2d(in_planes, ndf, kernel_size, 2, pad_mode='pad', padding=1),
            nn.LeakyReLU(alpha)
        ]
        nf_mult = ndf
        for i in range(1, n_layers):
            nf_mult_prev = nf_mult
            nf_mult = min(2 ** i, 8) * ndf
            layers.append(ConvNormRelu(nf_mult_prev, nf_mult, kernel_size, 2, alpha, norm_mode, padding=1))
        nf_mult_prev = nf_mult
        nf_mult = min(2 ** n_layers, 8) * ndf
        layers.append(ConvNormRelu(nf_mult_prev, nf_mult, kernel_size, 1, alpha, norm_mode, padding=1))
        layers.append(nn.Conv2d(nf_mult, 1, kernel_size, 1, pad_mode='pad', padding=1))
        self.features = nn.SequentialCell(layers)

    def construct(self, x, y):
        x_y = ops.concat((x, y), axis=1)
        output = self.features(x_y)
        return output

4、Pix2Pix的生成器和判别器初始化

实例化Pix2Pix生成器和判别器：

import mindspore.nn as nn
from mindspore.common import initializer as init

g_in_planes = 3
g_out_planes = 3
g_ngf = 64
g_layers = 8
d_in_planes = 6
d_ndf = 64
d_layers = 3
alpha = 0.2
init_gain = 0.02
init_type = 'normal'


net_generator = UNetGenerator(in_planes=g_in_planes, out_planes=g_out_planes,
                              ngf=g_ngf, n_layers=g_layers)
for _, cell in net_generator.cells_and_names():
    if isinstance(cell, (nn.Conv2d, nn.Conv2dTranspose)):
        if init_type == 'normal':
            cell.weight.set_data(init.initializer(init.Normal(init_gain), cell.weight.shape))
        elif init_type == 'xavier':
            cell.weight.set_data(init.initializer(init.XavierUniform(init_gain), cell.weight.shape))
        elif init_type == 'constant':
            cell.weight.set_data(init.initializer(0.001, cell.weight.shape))
        else:
            raise NotImplementedError('initialization method [%s] is not implemented' % init_type)
    elif isinstance(cell, nn.BatchNorm2d):
        cell.gamma.set_data(init.initializer('ones', cell.gamma.shape))
        cell.beta.set_data(init.initializer('zeros', cell.beta.shape))


net_discriminator = Discriminator(in_planes=d_in_planes, ndf=d_ndf,
                                  alpha=alpha, n_layers=d_layers)
for _, cell in net_discriminator.cells_and_names():
    if isinstance(cell, (nn.Conv2d, nn.Conv2dTranspose)):
        if init_type == 'normal':
            cell.weight.set_data(init.initializer(init.Normal(init_gain), cell.weight.shape))
        elif init_type == 'xavier':
            cell.weight.set_data(init.initializer(init.XavierUniform(init_gain), cell.weight.shape))
        elif init_type == 'constant':
            cell.weight.set_data(init.initializer(0.001, cell.weight.shape))
        else:
            raise NotImplementedError('initialization method [%s] is not implemented' % init_type)
    elif isinstance(cell, nn.BatchNorm2d):
        cell.gamma.set_data(init.initializer('ones', cell.gamma.shape))
        cell.beta.set_data(init.initializer('zeros', cell.beta.shape))

class Pix2Pix(nn.Cell):
    """Pix2Pix模型网络"""
    def __init__(self, discriminator, generator):
        super(Pix2Pix, self).__init__(auto_prefix=True)
        self.net_discriminator = discriminator
        self.net_generator = generator

    def construct(self, reala):
        fakeb = self.net_generator(reala)
        return fakeb

5、模型训练

训练分为两个主要部分：训练判别器和训练生成器；
训练判别器的目的是最大程度地提高判别图像真伪的概率；
训练生成器是希望能产生更好的虚假图像；
在这两个部分中，分别获取训练过程中的损失，并在每个周期结束时进行统计。

通过MindSpore进行训练：

import numpy as np
import os
import datetime
from mindspore import value_and_grad, Tensor

epoch_num = 3
ckpt_dir = "results/ckpt"
dataset_size = 400
val_pic_size = 256
lr = 0.0002
n_epochs = 100
n_epochs_decay = 100

def get_lr():
    lrs = [lr] * dataset_size * n_epochs
    lr_epoch = 0
    for epoch in range(n_epochs_decay):
        lr_epoch = lr * (n_epochs_decay - epoch) / n_epochs_decay
        lrs += [lr_epoch] * dataset_size
    lrs += [lr_epoch] * dataset_size * (epoch_num - n_epochs_decay - n_epochs)
    return Tensor(np.array(lrs).astype(np.float32))

dataset = ds.MindDataset("./dataset/dataset_pix2pix/train.mindrecord", columns_list=["input_images", "target_images"], shuffle=True, num_parallel_workers=1)
steps_per_epoch = dataset.get_dataset_size()
loss_f = nn.BCEWithLogitsLoss()
l1_loss = nn.L1Loss()

def forword_dis(reala, realb):
    lambda_dis = 0.5
    fakeb = net_generator(reala)
    pred0 = net_discriminator(reala, fakeb)
    pred1 = net_discriminator(reala, realb)
    loss_d = loss_f(pred1, ops.ones_like(pred1)) + loss_f(pred0, ops.zeros_like(pred0))
    loss_dis = loss_d * lambda_dis
    return loss_dis

def forword_gan(reala, realb):
    lambda_gan = 0.5
    lambda_l1 = 100
    fakeb = net_generator(reala)
    pred0 = net_discriminator(reala, fakeb)
    loss_1 = loss_f(pred0, ops.ones_like(pred0))
    loss_2 = l1_loss(fakeb, realb)
    loss_gan = loss_1 * lambda_gan + loss_2 * lambda_l1
    return loss_gan

d_opt = nn.Adam(net_discriminator.trainable_params(), learning_rate=get_lr(),
                beta1=0.5, beta2=0.999, loss_scale=1)
g_opt = nn.Adam(net_generator.trainable_params(), learning_rate=get_lr(),
                beta1=0.5, beta2=0.999, loss_scale=1)

grad_d = value_and_grad(forword_dis, None, net_discriminator.trainable_params())
grad_g = value_and_grad(forword_gan, None, net_generator.trainable_params())

def train_step(reala, realb):
    loss_dis, d_grads = grad_d(reala, realb)
    loss_gan, g_grads = grad_g(reala, realb)
    d_opt(d_grads)
    g_opt(g_grads)
    return loss_dis, loss_gan

if not os.path.isdir(ckpt_dir):
    os.makedirs(ckpt_dir)

g_losses = []
d_losses = []
data_loader = dataset.create_dict_iterator(output_numpy=True, num_epochs=epoch_num)

for epoch in range(epoch_num):
    for i, data in enumerate(data_loader):
        start_time = datetime.datetime.now()
        input_image = Tensor(data["input_images"])
        target_image = Tensor(data["target_images"])
        dis_loss, gen_loss = train_step(input_image, target_image)
        end_time = datetime.datetime.now()
        delta = (end_time - start_time).microseconds
        if i % 2 == 0:
            print("ms per step:{:.2f}  epoch:{}/{}  step:{}/{}  Dloss:{:.4f}  Gloss:{:.4f} ".format((delta / 1000), (epoch + 1), (epoch_num), i, steps_per_epoch, float(dis_loss), float(gen_loss)))
        d_losses.append(dis_loss.asnumpy())
        g_losses.append(gen_loss.asnumpy())
    if (epoch + 1) == epoch_num:
        mindspore.save_checkpoint(net_generator, ckpt_dir + "Generator.ckpt")

在这里插入图片描述

6、模型推理

导入模型训练保存的权重：

from mindspore import load_checkpoint, load_param_into_net

param_g = load_checkpoint(ckpt_dir + "Generator.ckpt")
load_param_into_net(net_generator, param_g)
dataset = ds.MindDataset("./dataset/dataset_pix2pix/train.mindrecord", columns_list=["input_images", "target_images"], shuffle=True)
data_iter = next(dataset.create_dict_iterator())
predict_show = net_generator(data_iter["input_images"])
plt.figure(figsize=(10, 3), dpi=140)
for i in range(10):
    plt.subplot(2, 10, i + 1)
    plt.imshow((data_iter["input_images"][i].asnumpy().transpose(1, 2, 0) + 1) / 2)
    plt.axis("off")
    plt.subplots_adjust(wspace=0.05, hspace=0.02)
    plt.subplot(2, 10, i + 11)
    plt.imshow((predict_show[i].asnumpy().transpose(1, 2, 0) + 1) / 2)
    plt.axis("off")
    plt.subplots_adjust(wspace=0.05, hspace=0.02)
plt.show()