基于PaddlePaddle复现Old2Life

本文介绍Old Photo Restoration的Paddle实现，复现相关论文。采用VOC数据集及部分真实老照片，提供模型、配置文件、训练数据等资源。训练分三阶段，给出终端和Notebook启动方式及参数。测试可查看指标和可视化效果，20个epoch训练的模型已呈现较好效果，随训练轮数增加有望提升。

Old Photo Restoration (Paddle Implementation)

github链接：https://github.com/buriedms/Old2Life-Paddle.git

复现论文为：Old Photo Restoration via Deep Latent Space Translation

最新开源 pytorch 代码：Bringing-Old-Photos-Back-to-Life

数据集采用VOC数据集，和小部分真实老照片，老照片数据地址

模型及配置文件存放网盘链接，提取码：xfmp

可视化效果图网盘链接，提取码：s32p

训练数据网盘链接，提取码：07oi

复现指标

摘要

我们提出通过深度学习方法来恢复严重退化的旧照片。与传统的可以通过监督学习解决的恢复任务不同，真实照片的退化非常复杂，而且合成图像与真实旧照片之间的域差距使得网络不能泛化。因此，我们利用真实照片和大量的合成图像对，提出了一种新的三重域平移网络。

具体来说，我们训练两个变分自动编码器(VAEs)分别将旧照片和干净照片转换到两个潜在空间。这两个潜在空间之间的转换是用合成的成对数据学习的。这种平移可以很好地推广到真实的照片，因为域间隙在紧凑的潜在空间是封闭的。此外，为了解决一张老照片中混杂的多种退化问题，我们设计了一个全局分支，针对划痕和灰尘斑点等结构化缺陷，设计了一个局部非局部块，针对噪声和模糊等非结构化缺陷，设计了一个局部分支。两个分支在潜在空间融合，从而提高了从多个缺陷恢复旧照片的能力。此外，我们采用另一种人脸细化网络来恢复旧照片中人脸的精细细节，最终生成感知质量增强的照片。通过全面的实验，提出的管道证明了在旧照片恢复的视觉质量方面优于最先进的方法以及现有的商业工具。

       

图1:我们方法产生的旧照片恢复结果。该方法能够处理真实旧照片中混杂着非结构化和结构化缺陷的复杂退化问题。特别是，我们恢复了人脸区域的高频细节，进一步提高了人像的感知质量。对于每个图像对，左边是输入，而修改后的输出显示在右边。

一、实验前的准备

数据集和预训练模型情况

训练数据

使用Pascal VOC数据集的图像合成虚假旧照片。收集的真实图像旧照片数据集-彩色和黑白色。

数据集可以通过两种方式获取：

通过网盘链接下载数据集， 提取码：07oi。 注:aistudio上已公开制作好的数据集通过自定义数据文件进行创建。制作详情可通过Old2Life-Paddle/Global/data/readme.md当中进行查看学习

预训练模型
已经提供每个阶段训练了20个epoch训练模型，可以自行用来进行测试。

运行环境

安装依赖库

In [8]

!pip install x2paddle

登录后复制        

Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simpleCollecting x2paddle  Using cached https://pypi.tuna.tsinghua.edu.cn/packages/c1/82/49ac2659d7598ddb055316aca92b4cf24c2c3c5df9e1a3cdf7dce3c84f23/x2paddle-1.3.4-py3-none-any.whlInstalling collected packages: x2paddleSuccessfully installed x2paddle-1.3.4

登录后复制        

准备数据集

解压配置文件和数据文件到指定文件夹

In [1]

!unzip /home/aistudio/data/data114496/old2life.zip -d work/old2life/ #训练数据文件/home/aistudio/data/data114496/old2life.zip!unzip /home/aistudio/data/data114816/checkpoints.zip -d work/Old2Life/ # 模型配置文件/home/aistudio/data/data114816/checkpoints.zip

登录后复制        

Archive:  /home/aistudio/data/data114496/old2life.zip   creating: work/old2life/old2life/  inflating: work/old2life/old2life/Real_L_old.bigfile    inflating: work/old2life/old2life/Real_RGB_old.bigfile    inflating: work/old2life/old2life/VOC.bigfile  Archive:  /home/aistudio/data/data114816/checkpoints.zip   creating: work/Old2Life/checkpoints/   creating: work/Old2Life/checkpoints/domainA_SR_old_photos/  inflating: work/Old2Life/checkpoints/domainA_SR_old_photos/best_net_D.pdparams    inflating: work/Old2Life/checkpoints/domainA_SR_old_photos/best_net_featD.pdparams    inflating: work/Old2Life/checkpoints/domainA_SR_old_photos/best_net_G.pdparams    inflating: work/Old2Life/checkpoints/domainA_SR_old_photos/best_optimizer_D.pdparams    inflating: work/Old2Life/checkpoints/domainA_SR_old_photos/best_optimizer_featD.pdparams    inflating: work/Old2Life/checkpoints/domainA_SR_old_photos/best_optimizer_G.pdparams   extracting: work/Old2Life/checkpoints/domainA_SR_old_photos/iter.txt    inflating: work/Old2Life/checkpoints/domainA_SR_old_photos/latest_net_D.pdparams    inflating: work/Old2Life/checkpoints/domainA_SR_old_photos/latest_net_featD.pdparams    inflating: work/Old2Life/checkpoints/domainA_SR_old_photos/latest_net_G.pdparams    inflating: work/Old2Life/checkpoints/domainA_SR_old_photos/latest_optimizer_D.pdparams    inflating: work/Old2Life/checkpoints/domainA_SR_old_photos/latest_optimizer_featD.pdparams    inflating: work/Old2Life/checkpoints/domainA_SR_old_photos/latest_optimizer_G.pdparams    inflating: work/Old2Life/checkpoints/domainA_SR_old_photos/loss_log.txt    inflating: work/Old2Life/checkpoints/domainA_SR_old_photos/model.txt    inflating: work/Old2Life/checkpoints/domainA_SR_old_photos/opt.txt     creating: work/Old2Life/checkpoints/domainB_old_photos/  inflating: work/Old2Life/checkpoints/domainB_old_photos/best_net_D.pdparams    inflating: work/Old2Life/checkpoints/domainB_old_photos/best_net_G.pdparams    inflating: work/Old2Life/checkpoints/domainB_old_photos/best_optimizer_D.pdparams    inflating: work/Old2Life/checkpoints/domainB_old_photos/best_optimizer_G.pdparams   extracting: work/Old2Life/checkpoints/domainB_old_photos/iter.txt    inflating: work/Old2Life/checkpoints/domainB_old_photos/latest_net_D.pdparams    inflating: work/Old2Life/checkpoints/domainB_old_photos/latest_net_G.pdparams    inflating: work/Old2Life/checkpoints/domainB_old_photos/loss_log.txt    inflating: work/Old2Life/checkpoints/domainB_old_photos/model.txt     creating: work/Old2Life/checkpoints/mapping_quality/  inflating: work/Old2Life/checkpoints/mapping_quality/best_net_mapping_net.pdparams   extracting: work/Old2Life/checkpoints/mapping_quality/iter.txt    inflating: work/Old2Life/checkpoints/mapping_quality/latest_net_mapping_net.pdparams    inflating: work/Old2Life/checkpoints/mapping_quality/loss_log.txt    inflating: work/Old2Life/checkpoints/mapping_quality/model.txt    inflating: work/Old2Life/checkpoints/mapping_quality/opt.txt

登录后复制        

进入工作目录

注意：使用Notebook运行必须执行这一步

In [1]

# 进入到工作目录，使用Notebook进行训练必须进行这一步%cd Old2Life-Paddle/

登录后复制        

/home/aistudio/Old2Life-Paddle

登录后复制        

二、训练启动

1. 终端启动

终端在Old2Life-Paddle文件目录下执行以下命令：                

bash train.sh

登录后复制登录后复制            如果想要训练单个阶段，可以通过如下命令执行。
a. 训练第一阶段                

bash Global/run_a.sh

登录后复制b. 训练第二阶段                

bash Global/run_b.sh

登录后复制c. 训练第三阶段                

bash Global/run_map.sh

登录后复制            

如果需要更改训练参数，可以在当中进行修改。

2.Notebook启动

在工作目录Old2Life-Paddle下执行以下命令：

bash train.sh

登录后复制登录后复制            

如果想要训练单个阶段，可以通过如下命令执行。

a. 训练第一阶段

!bash Global/run_a.sh

登录后复制                

b. 训练第二阶段

!bash Global/run_b.sh

登录后复制                

c. 训练第三阶段

!bash Global/run_map.sh

登录后复制            

必选参数解释

In [4]

# Notebook测试代码 # 全阶段开始训练!bash train.sh# # A阶段开始训练# !bash Global/run_a.sh# # B阶段训练启动# !bash Global/run_b.sh# # MAP阶段训练启动# !bash Global/run_map.sh

登录后复制        

Trian A Start !CustomDatasetDataLoaderdataset [UnPairOldPhotos_SR] was createdstart load bigfile (0.00 GB) into memoryfind total 4 imagesload 0 images doneload all 4 images donestart load bigfile (0.01 GB) into memoryfind total 8 imagesload 0 images doneload all 8 images donestart load bigfile (0.09 GB) into memoryfind total 966 imagesload 0 images doneload all 966 images done-------------Filter the imgs whose size <256 in VOC---------------------Origin image num is [966], filtered result is [941]--------#training images = 96012/02/2024 11:46:02 - INFO - root -   ================ Training domainA_SR_old_photos Loss (Thu Dec  2 11:46:02 2024) ================12/02/2024 11:46:02 - INFO - root -   Resuming from epoch 3 at iteration 0W1202 11:46:02.908684  1475 device_context.cc:404] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1W1202 11:46:02.913003  1475 device_context.cc:422] device: 0, cuDNN Version: 7.6.network import path: /home/aistudio/work/Old2Life/test_checkpoints/domainA_SR_old_photos/latest_net_G.pdparams---------- G Networks reloaded -------------network import path: /home/aistudio/work/Old2Life/test_checkpoints/domainA_SR_old_photos/latest_net_D.pdparamsnetwork import path: /home/aistudio/work/Old2Life/test_checkpoints/domainA_SR_old_photos/latest_net_featD.pdparams---------- D Networks reloaded -------------12/02/2024 11:46:08 - INFO - paddle.utils.download -   unique_endpoints {''}12/02/2024 11:46:08 - INFO - paddle.utils.download -   Found /home/aistudio/.cache/paddle/hapi/weights/vgg19-pt.pdparams---------- Optimizers initialized -------------optimizer import path: /home/aistudio/work/Old2Life/test_checkpoints/domainA_SR_old_photos/latest_optimizer_D.pdparamsoptimizer import path: /home/aistudio/work/Old2Life/test_checkpoints/domainA_SR_old_photos/latest_optimizer_G.pdparamsoptimizer import path: /home/aistudio/work/Old2Life/test_checkpoints/domainA_SR_old_photos/latest_optimizer_featD.pdparams---------- Optimizers reloaded ----------------------- Current LR is 0.00020000 -------------12/02/2024 11:46:17 - INFO - paddle.utils.download -   unique_endpoints {''}12/02/2024 11:46:17 - INFO - paddle.utils.download -   Found /home/aistudio/.cache/paddle/hapi/weights/InceptionV3.pdparamsSetting up [LPIPS] perceptual loss: trunk [vgg], v[0.1], spatial [off]/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/tensor/creation.py:125: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations  if data.dtype == np.object:PerceptualVGG loaded pretrained weight.12/02/2024 11:46:23 - INFO - paddle.utils.download -   unique_endpoints {''}12/02/2024 11:46:23 - INFO - paddle.utils.download -   Found /home/aistudio/.cache/paddle/hapi/weights/lins_0.1_vgg.pdparamsLoading model from: /home/aistudio/.cache/paddle/hapi/weights/lins_0.1_vgg.pdparams12/02/2024 11:46:28 - INFO - root -   Epoch: 4, Iters: 64, Time: 0.036 lr: 0.00020 || G_GAN: 0.773 G_GAN_Feat: 9.242 G_VGG: 7.741 G_KL: 1.010 D_real: 0.663 D_fake: 0.648 G_featD: 0.400 featD_real: 0.355 featD_fake: 0.287 /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/framework.py:706: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations  elif dtype == np.bool:12/02/2024 11:46:31 - INFO - root -   Epoch: 4, Iters: 128, Time: 0.014 lr: 0.00020 || G_GAN: 0.787 G_GAN_Feat: 9.330 G_VGG: 7.891 G_KL: 1.002 D_real: 0.682 D_fake: 0.655 G_featD: 0.384 featD_real: 0.323 featD_fake: 0.311 12/02/2024 11:46:35 - INFO - root -   Epoch: 4, Iters: 192, Time: 0.014 lr: 0.00020 || G_GAN: 0.803 G_GAN_Feat: 9.168 G_VGG: 7.775 G_KL: 0.977 D_real: 0.718 D_fake: 0.651 G_featD: 0.373 featD_real: 0.340 featD_fake: 0.345 12/02/2024 11:46:38 - INFO - root -   Epoch: 4, Iters: 256, Time: 0.014 lr: 0.00020 || G_GAN: 0.816 G_GAN_Feat: 10.262 G_VGG: 7.874 G_KL: 0.986 D_real: 0.704 D_fake: 0.679 G_featD: 0.419 featD_real: 0.350 featD_fake: 0.274 ^CTraceback (most recent call last):  File "Global/train_domain_A.py", line 107, in     loss_D.backward()  File "", line 2, in backward  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/wrapped_decorator.py", line 25, in __impl__    return wrapped_func(*args, **kwargs)  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/framework.py", line 227, in __impl__    return func(*args, **kwargs)  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/varbase_patch_methods.py", line 239, in backward    framework._dygraph_tracer())KeyboardInterruptTrain A Over !Tarin B Start !CustomDatasetDataLoaderdataset [UnPairOldPhotos_SR] was createdstart load bigfile (0.09 GB) into memoryfind total 966 imagesload 0 images doneload all 966 images done-------------Filter the imgs whose size <256 in VOC---------------------Origin image num is [966], filtered result is [941]--------#training images = 96012/02/2024 11:46:46 - INFO - root -   ================ Training domainB_old_photos Loss (Thu Dec  2 11:46:46 2024) ================12/02/2024 11:46:46 - INFO - root -   Resuming from epoch 1 at iteration 0W1202 11:46:46.363127  1628 device_context.cc:404] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1W1202 11:46:46.367645  1628 device_context.cc:422] device: 0, cuDNN Version: 7.6.network import path: /home/aistudio/work/Old2Life/test_checkpoints/domainB_old_photos/latest_net_G.pdparams---------- G Networks reloaded -------------network import path: /home/aistudio/work/Old2Life/test_checkpoints/domainB_old_photos/latest_net_D.pdparams---------- D Networks reloaded -------------12/02/2024 11:46:51 - INFO - paddle.utils.download -   unique_endpoints {''}12/02/2024 11:46:51 - INFO - paddle.utils.download -   Found /home/aistudio/.cache/paddle/hapi/weights/vgg19-pt.pdparams---------- Optimizers initialized -------------optimizer import path: /home/aistudio/work/Old2Life/test_checkpoints/domainB_old_photos/latest_optimizer_D.pdparamsoptimizer import path: /home/aistudio/work/Old2Life/test_checkpoints/domainB_old_photos/latest_optimizer_G.pdparams---------- Optimizers reloaded ----------------------- Current LR is 0.00020000 -------------12/02/2024 11:47:00 - INFO - paddle.utils.download -   unique_endpoints {''}12/02/2024 11:47:00 - INFO - paddle.utils.download -   Found /home/aistudio/.cache/paddle/hapi/weights/InceptionV3.pdparamsSetting up [LPIPS] perceptual loss: trunk [vgg], v[0.1], spatial [off]/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/tensor/creation.py:125: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations  if data.dtype == np.object:PerceptualVGG loaded pretrained weight.12/02/2024 11:47:07 - INFO - paddle.utils.download -   unique_endpoints {''}12/02/2024 11:47:07 - INFO - paddle.utils.download -   Found /home/aistudio/.cache/paddle/hapi/weights/lins_0.1_vgg.pdparamsLoading model from: /home/aistudio/.cache/paddle/hapi/weights/lins_0.1_vgg.pdparams12/02/2024 11:47:10 - INFO - root -   Epoch: 2, Iters: 64, Time: 0.034 lr: 0.00020 || G_GAN: 0.759 G_GAN_Feat: 10.868 G_VGG: 10.703 G_KL: 2.009 D_real: 0.757 D_fake: 0.760 /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/framework.py:706: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations  elif dtype == np.bool:12/02/2024 11:47:13 - INFO - root -   Epoch: 2, Iters: 128, Time: 0.011 lr: 0.00020 || G_GAN: 0.758 G_GAN_Feat: 11.050 G_VGG: 11.088 G_KL: 1.911 D_real: 0.779 D_fake: 0.710 12/02/2024 11:47:16 - INFO - root -   Epoch: 2, Iters: 192, Time: 0.011 lr: 0.00020 || G_GAN: 0.770 G_GAN_Feat: 10.839 G_VGG: 10.811 G_KL: 1.864 D_real: 0.789 D_fake: 0.683 12/02/2024 11:47:19 - INFO - root -   Epoch: 2, Iters: 256, Time: 0.011 lr: 0.00020 || G_GAN: 0.768 G_GAN_Feat: 11.603 G_VGG: 10.854 G_KL: 1.830 D_real: 0.786 D_fake: 0.695 ^CTraceback (most recent call last):  File "Global/train_domain_B.py", line 144, in     performance.update(generated[:5], data['image'][:5]) if dist.get_rank()==0 else None  File "/home/aistudio/Old2Life-Paddle/Global/util/util.py", line 64, in update    self.FID.update(preds,gts)  File "/home/aistudio/Old2Life-Paddle/Global/util/FID.py", line 69, in update    preds, gts, self.batch_size, self.model, self.use_GPU, self.dims)  File "/home/aistudio/Old2Life-Paddle/Global/util/FID.py", line 153, in calculate_inception_val    use_gpu)  File "/home/aistudio/Old2Life-Paddle/Global/util/FID.py", line 133, in _get_activations_from_ims    pred = model(images)[0][0]  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 902, in __call__    outputs = self.forward(*inputs, **kwargs)  File "/home/aistudio/Old2Life-Paddle/Global/util/inception.py", line 129, in forward    x = block(x)  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 902, in __call__    outputs = self.forward(*inputs, **kwargs)  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/container.py", line 98, in forward    input = layer(input)  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 902, in __call__    outputs = self.forward(*inputs, **kwargs)  File "/home/aistudio/Old2Life-Paddle/Global/util/inception.py", line 641, in forward    branch_pool = self.branch_pool(branch_pool)  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 902, in __call__    outputs = self.forward(*inputs, **kwargs)  File "/home/aistudio/Old2Life-Paddle/Global/util/inception.py", line 746, in forward    y = self.bn(y)  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 902, in __call__    outputs = self.forward(*inputs, **kwargs)  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/nn.py", line 1342, in forward    mean_out, variance_out, *attrs)KeyboardInterruptTrain B Over!Train MAP Start !12/02/2024 11:47:23 - INFO - root -   ================ Training mapping_quality Loss (Thu Dec  2 11:47:23 2024) ================12/02/2024 11:47:23 - INFO - root -   Resuming from epoch 1 at iteration 0CustomDatasetDataLoaderdataset [PairOldPhotos] was createdstart load bigfile (0.09 GB) into memoryfind total 966 imagesload 0 images doneload all 966 images done-------------Filter the imgs whose size <256 in VOC---------------------Origin image num is [966], filtered result is [941]--------#training images = 928W1202 11:47:26.831796  1680 device_context.cc:404] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1W1202 11:47:26.836323  1680 device_context.cc:422] device: 0, cuDNN Version: 7.6.Mapping: You are using the mapping model without global restoration.network import path: /home/aistudio/work/Old2Life/checkpoints/domainA_SR_old_photos/latest_net_G.pdparamsnetwork import path: /home/aistudio/work/Old2Life/checkpoints/domainB_old_photos/latest_net_G.pdparamsnetwork import path: /home/aistudio/work/Old2Life/test_checkpoints/mapping_quality/latest_net_mapping_net.pdparamsL1Loss()12/02/2024 11:47:32 - INFO - paddle.utils.download -   unique_endpoints {''}12/02/2024 11:47:32 - INFO - paddle.utils.download -   Found /home/aistudio/.cache/paddle/hapi/weights/vgg19-pt.pdparams---------- Optimizers initialized -------------12/02/2024 11:47:41 - INFO - paddle.utils.download -   unique_endpoints {''}12/02/2024 11:47:41 - INFO - paddle.utils.download -   Found /home/aistudio/.cache/paddle/hapi/weights/InceptionV3.pdparamsSetting up [LPIPS] perceptual loss: trunk [vgg], v[0.1], spatial [off]/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/tensor/creation.py:125: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations  if data.dtype == np.object:PerceptualVGG loaded pretrained weight.12/02/2024 11:47:48 - INFO - paddle.utils.download -   unique_endpoints {''}12/02/2024 11:47:48 - INFO - paddle.utils.download -   Found /home/aistudio/.cache/paddle/hapi/weights/lins_0.1_vgg.pdparamsLoading model from: /home/aistudio/.cache/paddle/hapi/weights/lins_0.1_vgg.pdparams12/02/2024 11:47:53 - INFO - root -   Epoch: 2, Iters: 32, Time: 0.070 lr: 0.00020 || G_Feat_L2: 47.417 G_GAN: 2.736 G_GAN_Feat: 8.594 G_VGG: 10.082 D_real: 2.681 D_fake: 2.012 /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/framework.py:706: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations  elif dtype == np.bool:12/02/2024 11:47:57 - INFO - root -   Epoch: 2, Iters: 64, Time: 0.031 lr: 0.00020 || G_Feat_L2: 48.239 G_GAN: 45.647 G_GAN_Feat: 8.751 G_VGG: 10.735 D_real: 41.937 D_fake: 46.040 12/02/2024 11:48:01 - INFO - root -   Epoch: 2, Iters: 96, Time: 0.031 lr: 0.00020 || G_Feat_L2: 50.760 G_GAN: 8.463 G_GAN_Feat: 11.348 G_VGG: 11.035 D_real: 11.230 D_fake: 8.833 12/02/2024 11:48:05 - INFO - root -   Epoch: 2, Iters: 128, Time: 0.031 lr: 0.00020 || G_Feat_L2: 48.898 G_GAN: 13.146 G_GAN_Feat: 10.431 G_VGG: 10.061 D_real: 13.486 D_fake: 13.112 ^CTraceback (most recent call last):  File "Global/train_mapping.py", line 132, in     loss_D.backward()  File "", line 2, in backward  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/wrapped_decorator.py", line 25, in __impl__    return wrapped_func(*args, **kwargs)  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/framework.py", line 227, in __impl__    return func(*args, **kwargs)  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/varbase_patch_methods.py", line 239, in backward    framework._dygraph_tracer())KeyboardInterruptTrain MAP Over !

登录后复制        

三、测试评估

1.终端测试

查看测试指标
终端在Old2Life-Paddle目录下执行以下命令：

bash test_Sea.sh

登录后复制        

查看图片重建可视化效果
终端在Old2Life-Paddle目录下执行以下命令：

bash test_Elm.sh

登录后复制        

2.Notebook测试

!bash test_Sea.sh!bash test_Elm.sh

登录后复制        

必选参数解释

In [ ]

# Notebook测试代码# 获取图像的测试指标结果!bash test_Sea.sh# 获取图像重建的生成效果!bash test_Elm.sh

登录后复制    

四、成品效果展示

       

图2：上方为测试原图，下方为重建图片。

可以明显发现，通过模型重建后的图片在观感上不论是清晰度还是色彩的饱和度都更加的令人满意， 此效果是模型训练了20个epoch的结果，后续随着训练指标仍旧有所缓慢上升，原论文当中的结果是 进行训练了200个epoch的结果，我们有理由相信，我们所展示的效果不会是最佳效果，随着训练轮数 的上升，重建效果仍旧可以有所提升。

免责声明

游乐网为非赢利性网站，所展示的游戏/软件/文章内容均来自于互联网或第三方用户上传分享，版权归原作者所有，本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容，请联系youleyoucom@outlook.com。

同类文章