1. 背景：
使用 MindSpore 学习神经网络，打卡第 24 天；主要内容也依据 mindspore 的学习记录。
2. PixPix 介绍：
MindSpore 的 Pix2Pix 图像转换
-
介绍
Pix2Pix是基于条件生成对抗网络（cGAN, Condition Generative Adversarial Networks ）实现的一种深度学习图像转换模型，该模型是由Phillip Isola等作者在2017年CVPR上提出的，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cGAN应用于有监督的图像到图像翻译的经典之作，其包括两个模型：生成器和判别器。 -
论文
Conditional Generative Adversarial Networks 论文地址
Image-to-Image Translation with Conditional Adversarial Networks -
基本原理：
cGAN 与 GAN 区别：
a. 输入不同：
cGAN 生成器输入图片，作为指导信息，生成假图像。本质是：输入图像转换输出为相应“假”图像的本质是从像素到另一个像素的映射。
GAN 输入是一个给定的随机噪声生成图像，输出图像通过其他约束条件控制生成。
MindSpore 的 docs 中有详细的说明；
https://gitee.com/mindspore/docs/blob/r2.3.0rc2/tutorials/application/source_zh_cn/generative/pix2pix.ipynb
3. 具体实现：
mindspore 使用 pix2pix 数据；
3.1 数据下载：
# 数据下载
ffrom download import download
url = "https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/models/application/dataset_pix2pix.tar"
download(url, "./dataset", kind="tar", replace=True)
3.2 构造网络
生成器G用到的是U-Net结构，输入的轮廓图 𝑥 编码再解码成真是图片，判别器D用到的是作者自己提出来的条件判别器PatchGAN，判别器D的作用是在轮廓图 𝑥 的条件下，对于生成的图片 𝐺(𝑥) 判断为假，对于真实判断为真。
- 生成器的 G 结构如下所示：
使用的是 U-Net 结构
- 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
- 基于 UNet 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)
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。
- 构建判别器，基于 PatchGAN：
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
3.3 生成器与判别器的初始化
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
3.4 训练
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。
- 损失函数：
定义了 Generator 和 Discriminator 后，损失函数使用MindSpore中二进制交叉熵损失函数BCELoss ；这里生成器和判别器都是使用Adam优化器。
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")
3.5 推理
获取上述训练过程完成后的ckpt文件，通过load_checkpoint和load_param_into_net将ckpt中的权重参数导入到模型中，获取数据进行推理并对推理的效果图进行演示（由于时间问题，训练过程只进行了3个epoch，可根据需求调整epoch）
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()
4. 相关链接：
- https://xihe.mindspore.cn/events/mindspore-training-camp
- [1] Phillip Isola,Jun-Yan Zhu,Tinghui Zhou,Alexei A. Efros. Image-to-Image Translation with Conditional Adversarial Networks.[J]. CoRR,2016,abs/1611.07004. https://arxiv.org/pdf/1611.07004
