mindspore框架下Pix2Pix模型实现真实图到线稿图的转换|（三）Pix2Pix模型训练与模型推理

mindspore框架下Pix2Pix模型实现真实图到线稿图的转换

1. mindspore框架下Pix2Pix模型实现真实图到线稿图的转换|（一）dataset_pix2pix数据集准备
2. mindspore框架下Pix2Pix模型实现真实图到线稿图的转换|（二）Pix2Pix模型构建
3. mindspore框架下Pix2Pix模型实现真实图到线稿图的转换|（三）Pix2Pix模型训练与模型推理
4. mindspore框架下Pix2Pix模型实现真实图到线稿图的转换|（四）模型应用实践

---

Pix2Pix模型训练

训练分为两个主要部分：

1. 训练判别器。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。
2. 训练生成器。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。

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")

Pix2Pix模型加载与推理

1. 加载训练过程完成后的ckpt文件；
2. 通过load_checkpoint和load_param_into_net将ckpt中的权重参数导入到模型中；
3. 获取数据进行推理并对推理的效果图进行演示。

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()