class TVLoss(nn.Module):
    def __init__(self,TVLoss_weight=1):
        super(TVLoss,self).__init__()
        self.TVLoss_weight = TVLoss_weight

    def forward(self,x):
        batch_size = x.size()[0]
        h_x = x.size()[2]
        w_x = x.size()[3]
        count_h = self._tensor_size(x[:,:,1:,:]) #channel * (h-1) * w
        count_w = self._tensor_size(x[:,:,:,1:]) #channel * h * (w-1)
        h_tv = torch.pow((x[:,:,1:,:]-x[:,:,:h_x-1,:]),2).sum()
        w_tv = torch.pow((x[:,:,:,1:]-x[:,:,:,:w_x-1]),2).sum()
        return self.TVLoss_weight*2*(h_tv/count_h+w_tv/count_w)/batch_size

    def _tensor_size(self,t): 
        return t.size()[1]*t.size()[2]*t.size()[3]

import dominate
from dominate.tags import meta, h3, table, tr, td, p, a, img, br
import os


class HTML:
    """This HTML class allows us to save images and write texts into a single HTML file.

     It consists of functions such as <add_header> (add a text header to the HTML file),
     <add_images> (add a row of images to the HTML file), and <save> (save the HTML to the disk).
     It is based on Python library 'dominate', a Python library for creating and manipulating HTML documents using a DOM API.
    """

    def __init__(self, web_dir, title, refresh=0):
        """Initialize the HTML classes

        Parameters:
            web_dir (str) -- a directory that stores the webpage. HTML file will be created at <web_dir>/index.html; images will be saved at <web_dir/images/
            title (str)   -- the webpage name
            refresh (int) -- how often the website refresh itself; if 0; no refreshing
        """
        self.title = title
        self.web_dir = web_dir
        self.img_dir = os.path.join(self.web_dir, 'images')
        if not os.path.exists(self.web_dir):
            os.makedirs(self.web_dir)
        if not os.path.exists(self.img_dir):
            os.makedirs(self.img_dir)

        self.doc = dominate.document(title=title)
        if refresh > 0:
            with self.doc.head:
                meta(http_equiv="refresh", content=str(refresh))

    def get_image_dir(self):
        """Return the directory that stores images"""
        return self.img_dir

    def add_header(self, text):
        """Insert a header to the HTML file

        Parameters:
            text (str) -- the header text
        """
        with self.doc:
            h3(text)

    def add_images(self, ims, txts, links, width=400):
        """add images to the HTML file

        Parameters:
            ims (str list)   -- a list of image paths
            txts (str list)  -- a list of image names shown on the website
            links (str list) --  a list of hyperref links; when you click an image, it will redirect you to a new page
        """
        self.t = table(border=1, style="table-layout: fixed;")  # Insert a table
        self.doc.add(self.t)
        with self.t:
            with tr():
                for im, txt, link in zip(ims, txts, links):
                    with td(style="word-wrap: break-word;", halign="center", valign="top"):
                        with p():
                            with a(href=os.path.join('images', link)):
                                img(style="width:%dpx" % width, src=os.path.join('images', im))
                            br()
                            p(txt)

    def save(self):
        """save the current content to the HMTL file"""
        html_file = '%s/index.html' % self.web_dir
        f = open(html_file, 'wt')
        f.write(self.doc.render())
        f.close()


if __name__ == '__main__':  # we show an example usage here.
    html = HTML('web/', 'test_html')
    html.add_header('hello world')

    ims, txts, links = [], [], []
    for n in range(4):
        ims.append('image_%d.png' % n)
        txts.append('text_%d' % n)
        links.append('image_%d.png' % n)
    html.add_images(ims, txts, links)
    html.save()

from utils import html
def save_web_images(self, webpage, data, images, epoch):
        if self.cfg.model.type == "Baseline":
            img_path_relative = (data["image_A_path"][0]).split("/")[-1]
            save_path = self.results_path / img_path_relative 
            save_path.parent.mkdir(exist_ok=True, parents=True)
            webpage.add_header(save_path.stem)
            txts = ['input','enhanced','GT','changemap','mask']
            ims, links = [], []
            width = 450
            str_epoch = '_'+str(epoch)
            root = str(save_path.parent)+'/'+str(save_path.stem)+str_epoch+".png" 
            self.to_pil(self.denorm(data["image_A"][0])).save(root)
            self.to_pil(self.denorm(images["fake_B"][0])).save(save_path.parent / f"{save_path.stem}_enhanced.png")
            self.to_pil(self.denorm(images["latent"][0]/3)).save(save_path.parent / f"{save_path.stem}_latent.png")
            self.to_pil(self.denorm(data["image_B"][0])).save(save_path.parent / f"{save_path.stem}_gt.png")
            self.to_pil((data["input_mask"])[0]).save(save_path.parent / f"{save_path.stem}_mask.png")
            ims.append(root)
            ims.append(save_path.parent / f"{save_path.stem}_enhanced.png")
            ims.append(save_path.parent / f"{save_path.stem}_gt.png")
            ims.append(save_path.parent / f"{save_path.stem}_latent.png")
            ims.append(save_path.parent / f"{save_path.stem}_mask.png")
            webpage.add_images(ims, txts, ims, width=width)
        else:
            raise "Unknown visualisation config"
web_dir = 'where images folder'
webpage = html.HTML(web_dir, 'Experiment = %s, Epoch = %s' % (cfg.model.type, cfg.model.load_epoch))

for images in results
    visualizer.save_web_images(webpage, data, images, epoch)

conf
    train.yaml
    test.yaml
data
    __init__.py           //最外层 get_dataset（dataset_name)
    datasets.py           //各种个样dataset（paired unpaired combaind..)
    transform.py          //制作dataset的时候，用到的数据变化 比如norm crop等
    utils.py              //读取 加载 图片类型转化 padding等data用到的工具

model
    vgg19.weight

models
    auxiliary.py          //作为特征提取或者vggloss 辅助网络
    discriminators.py     //组成鉴别器的不同组件 以及不同鉴别器
    generators.py         //组成生成器的不同组件 以及不同生成器
    losses.py             //比较复杂的loss 例如GAN perceptual loss
    engan.py              //实验的完整网络和对比网络 由G和D和loss共同构成
    utils.py              //初始化网络 初始化权重等 models部分用到的工具
outputs
    实验输出
utils
    metrics.py            //一些评价指标
    utils.py              //系统时间啊 get device啊
    visualize.py          //图片可视化和保存 

eval.py
train.py
test.py
README.md

pip install hydra-core

folder
├── conf
│   └── recoro_train.yaml
└── main.py

from omegaconf import DictConfig, OmegaConf
import hydra

@hydra.main(config_path="./conf", config_name="recoro_train")
def main(cfg: DictConfig):
    running_dir = str(hydra.utils.get_original_cwd())
    working_dir = str(Path.cwd())
    print(f"The current running directory is {running_dir}")
    print(f"The current working directory is {working_dir}")


if __name__ == "__main__":
    main()

The current running directory is C:\Users\xx\xx\xx\folder\
The current working directory is C:\Users\xx\xx\xx\folder\outputs\2023-02-08\22-47-06

import torch
print(torch.__version__)

filefolder = os.listdir(root)
filefolder.sort()
for f in filefolder:
    print(f)

import os
import shutil

os.remove(path) #删除文件
os.removedirs(path) #删除空文件夹

os.rmdir(path) #删除空文件夹
shutil.rmtree(path) #递归删除文件夹，即：删除非空文件夹

with open('./loss.txt','a+') as f:   
     for key in losssum:
         f.write(f"test_img : losses {key}: {losssum[key]/items}\n")  
f.close()

command = 'ffmpeg -i ./results/%s/'%(datasetname[i]) +'%06d.png ./results'+'/%s.mp4'%(datasetname[i])
print(command)
os.system(command)

import argparse

parser = argparse.ArgumentParser()
parser.add_argument("-in", "--inputA", help="this is parameter a", type=str, default="")
parser.add_argument("-out", "--outputB", help="this is parameter b",  type=str, default="")
args = parser.parse_args()
print(args.inputA)

python3 /Users/PeppaZhu/Desktop/studio_light/zoom_VB/test_V4_1NGF.py -in test_video_gfdebug/peppa_13test.mov -out peppa_13test_V4_4

#include <filesystem>
#include <iostream>

namespace fs = std::filesystem;
std::string path = "/Users/oliverzhu/Desktop/test_video/";
for (const auto &entry : fs::directory_iterator(path)){
        //将文件夹下所有文件名得到
        std::string inputpath = entry.path();
        std::string::size_type nPos1 = std::string::npos;
        std::string::size_type nPos2 = std::string::npos;
        nPos1 = inputpath.find_last_of("/");
        nPos2 = inputpath.find_last_of(".");
        //截取/开始 长度为nPos2-nPos1-1的字符串
        std::string strPath = inputpath.substr(nPos1 + 1, nPos2-nPos1-1);
        std::string input_path;
        std::string output_path;
        if (nPos2-nPos1 > 1)
        {
            // vaild input path
            input_path = inputpath;
            output_path = "/Users/oliverzhu/Desktop/results/" + strPath + ".mp4";
            std::cout << input_path << std::endl;
            std::cout << output_path << std::endl;
        }

        int32_t va; int32_t* vb; double vc; double* vd; uint8_t ve; uint8_t* vf; intptr_t vg;

        int32_t a = sizeof(&va); //8
int32_t b = sizeof(&vb); //8
int32_t d = sizeof(&vc); //8
int32_t e = sizeof(&vd); //8
int32_t f = sizeof(&ve); //8
int32_t g = sizeof(&vf); //8
int32_t h = sizeof(&vg); //8

int32_t va; int32_t* vb; double vc; double* vd; uint8_t ve; uint8_t* vf; intptr_t vg;

int32_t a = sizeof(va); //4
int32_t b = sizeof(vb); //8
int32_t d = sizeof(vc); //8
int32_t e = sizeof(vd); //8
int32_t f = sizeof(ve); //1
int32_t g = sizeof(vf); //8
int32_t h = sizeof(vg); //8
int32_t i = sizeof(*vb); //4

        uint8_t* aa;
aa = (uint8_t*)zltCMemoryBasic::zlt_calloc(sizeof(*aa) * bufSizeB * 12, 0);

        aa[0] = 1; aa[1] = 2;
uint8_t a = aa[0]; //1
uint8_t c = aa[1]; //2
uint8_t b = *aa; //1
uint8_t d = *(aa+1); //2