CycleGAN（一）概览与运行

╰+攻爆jí腚メ 2022-03-01 08:58 431阅读 0赞

背景：

[源码作者：junyanz][junyanz]/**[pytorch-CycleGAN-and-pix2pix][]**

**源码地址**：[https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix][pytorch-CycleGAN-and-pix2pix]

参考：[https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix][pytorch-CycleGAN-and-pix2pix]

**目录**

一、下载

1.1 下载

1.2 安装好依赖项

二、训练与测试

2.1 下载数据集

2.2. 自备数据集

2.3 可视化

2.4 训练

2.5 测试

三、预训练模型

3.1 预训练模型

3.2 数据集

四、docker

--------------------

# 一、下载 #

## 1.1 下载 ##

git clone https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
    cd pytorch-CycleGAN-and-pix2pix

## 1.2 安装好依赖项 ##

PyTorch安装，见：[https://blog.csdn.net/weixin\_36474809/article/details/88715360][https_blog.csdn.net_weixin_36474809_article_details_88715360]

Install \[PyTorch\]([http://pytorch.org][http_pytorch.org] and) 0.4+ and other dependencies (e.g., torchvision, [visdom][] and [dominate][]).

*  For pip users, please type the command `pip install -r requirements.txt`

`但是对于我们而言，因为之前装好的python在env/bin/python，所以我们需要在上级文件夹输入`

env/bin/python -m pip install -r pytorch-CycleGAN-and-pix2pix/requirements.txt

# 二、训练与测试 #

## 2.1 下载数据集 ##

我们以map数据集为例子。

对我们而言，出现问题

[xingxiangrui@xxxxxxxx pytorch-CycleGAN-and-pix2pix]$ bash ./datasets/download_cyclegan_dataset.sh maps
    Specified [maps]
    WARNING: timestamping does nothing in combination with -O. See the manual
    for details.
    
    --2019-03-22 11:07:20--  https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/maps.zip
    Resolving people.eecs.berkeley.edu... 128.32.189.73
    Connecting to people.eecs.berkeley.edu|128.32.189.73|:443... connected.
    ERROR: certificate common name "iris.eecs.berkeley.edu" doesn't match requested host name "people.eecs.berkeley.edu".
    To connect to people.eecs.berkeley.edu insecurely, use '--no-check-certificate'.
    mkdir: cannot create directory './datasets/maps/': File exists
    Archive:  ./datasets/maps.zip
      End-of-central-directory signature not found.  Either this file is not
      a zipfile, or it constitutes one disk of a multi-part archive.  In the
      latter case the central directory and zipfile comment will be found on
      the last disk(s) of this archive.
    unzip:  cannot find zipfile directory in one of ./datasets/maps.zip or
            ./datasets/maps.zip.zip, and cannot find ./datasets/maps.zip.ZIP, period.

其他所有数据集均无法下载：例如下面网页之中apple2orange和horse2zebra等等

[https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/docs/datasets.md][https_github.com_junyanz_pytorch-CycleGAN-and-pix2pix_blob_master_docs_datasets.md]

数据集的下载出现问题，所以我们只好自备数据集。

## **2.2. 自备数据集** ##

作者有给出一个自制模型和数据集的方法：

准备一个文件夹try，里面包含四个文件夹trainA、trainB、testA、testB，每个文件夹内分别放有若干图片

复制到 pytorch-CycleGAN-and-pix2pix/datasets/ 下

[https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/docs/tips.md\#notes-on-colorization][https_github.com_junyanz_pytorch-CycleGAN-and-pix2pix_blob_master_docs_tips.md_notes-on-colorization]

## 2.3 可视化 ##

可视化用的是visdom.server

To view training results and loss plots, run `python -m visdom.server` and click the URL [http://localhost:8097][http_localhost_8097]

关于visdom.server的用法我们暂时还没确定清楚

## 2.4 训练 ##

#!./scripts/train_cyclegan.sh
    python train.py --dataroot ./datasets/maps --name maps_cyclegan --model cycle_gan

可以看出其中

*  \--dataroot 训练数据的根目录
 *  \--name 训练模型的名称
 *  \--model 训练的模型的类型

更多训练时的信息查看`./checkpoints/maps_cyclegan/web/index.html`

## 2.5 测试 ##

#!./scripts/test_cyclegan.sh
    python test.py --dataroot ./datasets/maps --name maps_cyclegan --model cycle_gan

测试结果存于`./results/maps_cyclegan/latest_test/index.html`

# 三、预训练模型 #

## 3.1 预训练模型 ##

*  You can download a pretrained model (e.g. horse2zebra) with the following script:

bash ./scripts/download_cyclegan_model.sh horse2zebra

*  The pretrained model is saved at `./checkpoints/{name}_pretrained/latest_net_G.pth`. Check [here][] for all the available CycleGAN models.

## 3.2 数据集 ##

*  To test the model, you also need to download the horse2zebra dataset:

bash ./datasets/download_cyclegan_dataset.sh horse2zebra

*  Then generate the results using

python test.py --dataroot datasets/horse2zebra/testA --name horse2zebra_pretrained --model test --no_dropout

*  The option `--model test` is used for generating results of CycleGAN only for one side. This option will automatically set `--dataset_mode single`, which only loads the images from one set. On the contrary, using `--model cycle_gan` requires loading and generating results in both directions, which is sometimes unnecessary. The results will be saved at `./results/`. Use `--results_dir {directory_path_to_save_result}` to specify the results directory.
 *  For your own experiments, you might want to specify `--netG`, `--norm`, `--no_dropout` to match the generator architecture of the trained model.

# 四、docker #

[https://baike.baidu.com/item/Docker/13344470?fr=aladdin][https_baike.baidu.com_item_Docker_13344470_fr_aladdin]

Docker 是一个[开源][Link 1]的应用容器引擎，让开发者可以打包他们的应用以及依赖包到一个可移植的容器中，然后发布到任何流行的 Linux 机器上，也可以实现[虚拟化][Link 2]。容器是完全使用[沙箱][Link 3]机制，相互之间不会有任何接口。

[https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/docs/docker.md][https_github.com_junyanz_pytorch-CycleGAN-and-pix2pix_blob_master_docs_docker.md]

[junyanz]: https://github.com/junyanz
[pytorch-CycleGAN-and-pix2pix]: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
[https_blog.csdn.net_weixin_36474809_article_details_88715360]: https://blog.csdn.net/weixin_36474809/article/details/88715360
[http_pytorch.org]: http://pytorch.org
[visdom]: https://github.com/facebookresearch/visdom
[dominate]: https://github.com/Knio/dominate
[https_github.com_junyanz_pytorch-CycleGAN-and-pix2pix_blob_master_docs_datasets.md]: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/docs/datasets.md
[https_github.com_junyanz_pytorch-CycleGAN-and-pix2pix_blob_master_docs_tips.md_notes-on-colorization]: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/docs/tips.md#notes-on-colorization
[http_localhost_8097]: http://localhost:8097
[here]: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/scripts/download_cyclegan_model.sh#L3
[https_baike.baidu.com_item_Docker_13344470_fr_aladdin]: https://baike.baidu.com/item/Docker/13344470?fr=aladdin
[Link 1]: https://baike.baidu.com/item/%E5%BC%80%E6%BA%90/246339
[Link 2]: https://baike.baidu.com/item/%E8%99%9A%E6%8B%9F%E5%8C%96/547949
[Link 3]: https://baike.baidu.com/item/%E6%B2%99%E7%AE%B1/393318
[https_github.com_junyanz_pytorch-CycleGAN-and-pix2pix_blob_master_docs_docker.md]: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/docs/docker.md