Re-organize README (#338)

* update README

* upate readme

* upate readme

* update

* update

* update

* update

README.md

@@ -4,6 +4,10 @@
 
 ## <div align="center"><b><a href="README.md">English</a> | <a href="README_CN.md">简体中文</a></b></div>
 
+<div align="center">
+
+👀[**Demos**](#-demos-videos) **|** 🚩[**Updates**](#-updates) **|** ⚡[**Usage**](#-quick-inference) **|** 🏰[**Model Zoo**](docs/model_zoo.md) **|** 🔧[Install](#-dependencies-and-installation)  **|** 💻[Train](docs/Training.md) **|** ❓[FAQ](docs/FAQ.md) **|** 🎨[Contribution](docs/CONTRIBUTING.md)
+
 [![download](https://img.shields.io/github/downloads/xinntao/Real-ESRGAN/total.svg)](https://github.com/xinntao/Real-ESRGAN/releases)
 [![PyPI](https://img.shields.io/pypi/v/realesrgan)](https://pypi.org/project/realesrgan/)
 [![Open issue](https://img.shields.io/github/issues/xinntao/Real-ESRGAN)](https://github.com/xinntao/Real-ESRGAN/issues)
@@ -12,34 +16,47 @@
 [![python lint](https://github.com/xinntao/Real-ESRGAN/actions/workflows/pylint.yml/badge.svg)](https://github.com/xinntao/Real-ESRGAN/blob/master/.github/workflows/pylint.yml)
 [![Publish-pip](https://github.com/xinntao/Real-ESRGAN/actions/workflows/publish-pip.yml/badge.svg)](https://github.com/xinntao/Real-ESRGAN/blob/master/.github/workflows/publish-pip.yml)
 
-:fire: Update the **RealESRGAN AnimeVideo-v3** model **更新动漫视频的小模型**. Please see [[anime video models](docs/anime_video_model.md)] and [[comparisons](docs/anime_comparisons.md)] for more details.
+</div>
+
+🔥 **AnimeVideo-v3 model (动漫视频小模型)**. Please see [[*anime video models*](docs/anime_video_model.md)] and [[*comparisons*](docs/anime_comparisons.md)]<br>
+🔥 **RealESRGAN_x4plus_anime_6B** for anime images **(动漫插图模型)**. Please see [[*anime_model*](docs/anime_model.md)]
 
-1. [Colab Demo](https://colab.research.google.com/drive/1k2Zod6kSHEvraybHl50Lys0LerhyTMCo?usp=sharing) for Real-ESRGAN | [Colab Demo](https://colab.research.google.com/drive/1yNl9ORUxxlL4N0keJa2SEPB61imPQd1B?usp=sharing) for Real-ESRGAN (**anime videos**).
-2. Portable [Windows](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-windows.zip) / [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-ubuntu.zip) / [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-macos.zip) **executable files for Intel/AMD/Nvidia GPU**. You can find more information [here](#Portable-executable-files). The ncnn implementation is in [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan).
+1. You can try in our website: [ARC Demo](https://arc.tencent.com/en/ai-demos/imgRestore) (now only support RealESRGAN_x4plus_anime_6B)
+1. [Colab Demo](https://colab.research.google.com/drive/1k2Zod6kSHEvraybHl50Lys0LerhyTMCo?usp=sharing) for Real-ESRGAN **|** [Colab Demo](https://colab.research.google.com/drive/1yNl9ORUxxlL4N0keJa2SEPB61imPQd1B?usp=sharing) for Real-ESRGAN (**anime videos**)
+1. Portable [Windows](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-windows.zip) / [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-ubuntu.zip) / [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-macos.zip) **executable files for Intel/AMD/Nvidia GPU**. You can find more information [here](#portable-executable-files-ncnn). The ncnn implementation is in [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan)
+1. You can watch enhanced animations in [Tencent Video](https://v.qq.com/s/topic/v_child/render/fC4iyCAM.html). 欢迎观看[腾讯视频动漫修复](https://v.qq.com/s/topic/v_child/render/fC4iyCAM.html)
 
 Real-ESRGAN aims at developing **Practical Algorithms for General Image/Video Restoration**.<br>
 We extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data.
 
-:art: Real-ESRGAN needs your contributions. Any contributions are welcome, such as new features/models/typo fixes/suggestions/maintenance, *etc*. See [CONTRIBUTING.md](docs/CONTRIBUTING.md). All contributors are list [here](README.md#hugs-acknowledgement).
+🌌 Thanks for your valuable feedbacks/suggestions. All the feedbacks are updated in [feedback.md](docs/feedback.md).
 
-:question: Frequently Asked Questions can be found in [FAQ.md](docs/FAQ.md).
+---
 
-:milky_way: Thanks for your valuable feedbacks/suggestions. All the feedbacks are updated in [feedback.md](docs/feedback.md).
+If Real-ESRGAN is helpful, please help to ⭐ this repo or recommend it to your friends 😊 <br>
+Other recommended projects:<br>
+▶️ [GFPGAN](https://github.com/TencentARC/GFPGAN): A practical algorithm for real-world face restoration <br>
+▶️ [BasicSR](https://github.com/xinntao/BasicSR): An open-source image and video restoration toolbox<br>
+▶️ [facexlib](https://github.com/xinntao/facexlib): A collection that provides useful face-relation functions.<br>
+▶️ [HandyView](https://github.com/xinntao/HandyView): A PyQt5-based image viewer that is handy for view and comparison <br>
+▶️ [HandyFigure](https://github.com/xinntao/HandyFigure): Open source of paper figures <br>
 
 ---
 
-If Real-ESRGAN is helpful in your photos/projects, please help to :star: this repo or recommend it to your friends. Thanks:blush: <br>
-Other recommended projects:<br>
-:arrow_forward: [GFPGAN](https://github.com/TencentARC/GFPGAN): A practical algorithm for real-world face restoration <br>
-:arrow_forward: [BasicSR](https://github.com/xinntao/BasicSR): An open-source image and video restoration toolbox<br>
-:arrow_forward: [facexlib](https://github.com/xinntao/facexlib): A collection that provides useful face-relation functions.<br>
-:arrow_forward: [HandyView](https://github.com/xinntao/HandyView): A PyQt5-based image viewer that is handy for view and comparison. <br>
+### 📖 Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
+
+> [[Paper](https://arxiv.org/abs/2107.10833)] &emsp; [[YouTube Video](https://www.youtube.com/watch?v=fxHWoDSSvSc)] &emsp; [[B站讲解](https://www.bilibili.com/video/BV1H34y1m7sS/)] &emsp; [[Poster](https://xinntao.github.io/projects/RealESRGAN_src/RealESRGAN_poster.pdf)] &emsp; [[PPT slides](https://docs.google.com/presentation/d/1QtW6Iy8rm8rGLsJ0Ldti6kP-7Qyzy6XL/edit?usp=sharing&ouid=109799856763657548160&rtpof=true&sd=true)]<br>
+> [Xintao Wang](https://xinntao.github.io/), Liangbin Xie, [Chao Dong](https://scholar.google.com.hk/citations?user=OSDCB0UAAAAJ), [Ying Shan](https://scholar.google.com/citations?user=4oXBp9UAAAAJ&hl=en) <br>
+> [Tencent ARC Lab](https://arc.tencent.com/en/ai-demos/imgRestore); Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
+
+<p align="center">
+  <img src="assets/teaser.jpg">
+</p>
 
 ---
 
 <!---------------------------------- Updates --------------------------->
-<details>
-<summary>🚩<b>Updates</b></summary>
+## 🚩 Updates
 
 - ✅ Update the **RealESRGAN AnimeVideo-v3** model. Please see [anime video models](docs/anime_video_model.md) and [comparisons](docs/anime_comparisons.md) for more details.
 - ✅ Add small models for anime videos. More details are in [anime video models](docs/anime_video_model.md).
@@ -52,72 +69,62 @@ Other recommended projects:<br>
 - ✅ [The inference code](inference_realesrgan.py) supports: 1) **tile** options; 2) images with **alpha channel**; 3) **gray** images; 4) **16-bit** images.
 - ✅ The training codes have been released. A detailed guide can be found in [Training.md](docs/Training.md).
 
-</details>
+---
 
-<!---------------------------------- Projects that use Real-ESRGAN --------------------------->
-<details>
-<summary>🧩<b>Projects that use Real-ESRGAN</b></summary>
+<!---------------------------------- Demo videos --------------------------->
+## 👀 Demos Videos
 
-&nbsp;&nbsp;&nbsp;&nbsp;👋 If you develop/use Real-ESRGAN in your projects, welcome to let me know.
+#### Bilibili
 
-- NCNN-Android: [RealSR-NCNN-Android](https://github.com/tumuyan/RealSR-NCNN-Android) by [tumuyan](https://github.com/tumuyan)
-- VapourSynth: [vs-realesrgan](https://github.com/HolyWu/vs-realesrgan) by [HolyWu](https://github.com/HolyWu)
-- NCNN: [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan)
-
-&nbsp;&nbsp;&nbsp;&nbsp;**GUI**
+- [大闹天宫片段](https://www.bilibili.com/video/BV1ja41117zb)
+- [Anime dance cut 动漫魔性舞蹈](https://www.bilibili.com/video/BV1wY4y1L7hT/)
+- [海贼王片段](https://www.bilibili.com/video/BV1i3411L7Gy/)
 
-- [Waifu2x-Extension-GUI](https://github.com/AaronFeng753/Waifu2x-Extension-GUI) by [AaronFeng753](https://github.com/AaronFeng753)
-- [Squirrel-RIFE](https://github.com/Justin62628/Squirrel-RIFE) by [Justin62628](https://github.com/Justin62628)
-- [Real-GUI](https://github.com/scifx/Real-GUI) by [scifx](https://github.com/scifx)
-- [Real-ESRGAN_GUI](https://github.com/net2cn/Real-ESRGAN_GUI) by [net2cn](https://github.com/net2cn)
-- [Real-ESRGAN-EGUI](https://github.com/WGzeyu/Real-ESRGAN-EGUI) by [WGzeyu](https://github.com/WGzeyu)
-- [anime_upscaler](https://github.com/shangar21/anime_upscaler) by [shangar21](https://github.com/shangar21)
-- [RealESRGAN-GUI](https://github.com/Baiyuetribe/paper2gui/blob/main/Video%20Super%20Resolution/RealESRGAN-GUI.md) by [Baiyuetribe](https://github.com/Baiyuetribe)
+#### YouTube
 
-</details>
+## 🔧 Dependencies and Installation
 
-<!---------------------------------- Demo videos --------------------------->
-<details open>
-<summary>👀<b>Demo videos</b></summary>
+- Python >= 3.7 (Recommend to use [Anaconda](https://www.anaconda.com/download/#linux) or [Miniconda](https://docs.conda.io/en/latest/miniconda.html))
+- [PyTorch >= 1.7](https://pytorch.org/)
 
-- [大闹天宫片段](https://www.bilibili.com/video/BV1ja41117zb)
+### Installation
 
-</details>
+1. Clone repo
 
-### :book: Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
+    ```bash
+    git clone https://github.com/xinntao/Real-ESRGAN.git
+    cd Real-ESRGAN
+    ```
 
-> [[Paper](https://arxiv.org/abs/2107.10833)] &emsp; [Project Page] &emsp; [[YouTube Video](https://www.youtube.com/watch?v=fxHWoDSSvSc)] &emsp; [[B站讲解](https://www.bilibili.com/video/BV1H34y1m7sS/)] &emsp; [[Poster](https://xinntao.github.io/projects/RealESRGAN_src/RealESRGAN_poster.pdf)] &emsp; [[PPT slides](https://docs.google.com/presentation/d/1QtW6Iy8rm8rGLsJ0Ldti6kP-7Qyzy6XL/edit?usp=sharing&ouid=109799856763657548160&rtpof=true&sd=true)]<br>
-> [Xintao Wang](https://xinntao.github.io/), Liangbin Xie, [Chao Dong](https://scholar.google.com.hk/citations?user=OSDCB0UAAAAJ), [Ying Shan](https://scholar.google.com/citations?user=4oXBp9UAAAAJ&hl=en) <br>
-> Tencent ARC Lab; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
+1. Install dependent packages
 
-<p align="center">
-  <img src="assets/teaser.jpg">
-</p>
+    ```bash
+    # Install basicsr - https://github.com/xinntao/BasicSR
+    # We use BasicSR for both training and inference
+    pip install basicsr
+    # facexlib and gfpgan are for face enhancement
+    pip install facexlib
+    pip install gfpgan
+    pip install -r requirements.txt
+    python setup.py develop
+    ```
 
 ---
 
-We have provided a pretrained model (*RealESRGAN_x4plus.pth*) with upsampling X4.<br>
-**Note that RealESRGAN may still fail in some cases as the real-world degradations are really too complex.**<br>
-Moreover, it **may not** perform well on **human faces, text**, *etc*, which will be optimized later.
-<br>
+## ⚡ Quick Inference
 
-Real-ESRGAN will be a long-term supported project (in my current plan :smiley:). It will be continuously updated
-in my spare time.
+There are usually three ways to inference Real-ESRGAN.
 
-Here is a TODO list in the near future:
+1. [Online inference](#online-inference)
+1. [Portable executable files (NCNN)](#portable-executable-files-ncnn)
+1. [Python script](#python-script)
 
-- [ ] optimize for human faces
-- [ ] optimize for texts
-- [x] optimize for anime images
-- [ ] support more scales
-- [ ] support controllable restoration strength
+### Online inference
 
-If you have any good ideas or demands, please open an issue/discussion to let me know. <br>
-If you have some images that Real-ESRGAN could not well restored, please also open an issue/discussion. I will record it (but I cannot guarantee to resolve it:stuck_out_tongue:). If necessary, I will open a page to specially record these real-world cases that need to be solved, but the current technology is difficult to handle well.
-
----
+1. You can try in our website: [ARC Demo](https://arc.tencent.com/en/ai-demos/imgRestore) (now only support RealESRGAN_x4plus_anime_6B)
+1. [Colab Demo](https://colab.research.google.com/drive/1k2Zod6kSHEvraybHl50Lys0LerhyTMCo?usp=sharing) for Real-ESRGAN **|** [Colab Demo](https://colab.research.google.com/drive/1yNl9ORUxxlL4N0keJa2SEPB61imPQd1B?usp=sharing) for Real-ESRGAN (**anime videos**).
 
-### Portable executable files
+### Portable executable files (NCNN)
 
 You can download [Windows](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-windows.zip) / [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-ubuntu.zip) / [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-macos.zip) **executable files for Intel/AMD/Nvidia GPU**.
 
@@ -138,7 +145,7 @@ We have provided five models:
 
 You can use the `-n` argument for other models, for example, `./realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png -n realesrnet-x4plus`
 
-### Usage of executable files
+#### Usage of portable executable files
 
 1. Please refer to [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan#computer-usages) for more details.
 1. Note that it does not support all the functions (such as `outscale`) as the python script `inference_realesrgan.py`.
@@ -162,38 +169,30 @@ Usage: realesrgan-ncnn-vulkan.exe -i infile -o outfile [options]...
 
 Note that it may introduce block inconsistency (and also generate slightly different results from the PyTorch implementation), because this executable file first crops the input image into several tiles, and then processes them separately, finally stitches together.
 
----
-
-## :wrench: Dependencies and Installation
-
-- Python >= 3.7 (Recommend to use [Anaconda](https://www.anaconda.com/download/#linux) or [Miniconda](https://docs.conda.io/en/latest/miniconda.html))
-- [PyTorch >= 1.7](https://pytorch.org/)
-
-### Installation
+### Python script
 
-1. Clone repo
+#### Usage of python script
 
-    ```bash
-    git clone https://github.com/xinntao/Real-ESRGAN.git
-    cd Real-ESRGAN
-    ```
+1. You can use X4 model for **arbitrary output size** with the argument `outscale`. The program will further perform cheap resize operation after the Real-ESRGAN output.
 
-1. Install dependent packages
+```console
+Usage: python inference_realesrgan.py -n RealESRGAN_x4plus -i infile -o outfile [options]...
 
-    ```bash
-    # Install basicsr - https://github.com/xinntao/BasicSR
-    # We use BasicSR for both training and inference
-    pip install basicsr
-    # facexlib and gfpgan are for face enhancement
-    pip install facexlib
-    pip install gfpgan
-    pip install -r requirements.txt
-    python setup.py develop
-    ```
+A common command: python inference_realesrgan.py -n RealESRGAN_x4plus -i infile --outscale 3.5 --face_enhance
 
-## :zap: Quick Inference
+  -h                   show this help
+  -i --input           Input image or folder. Default: inputs
+  -o --output          Output folder. Default: results
+  -n --model_name      Model name. Default: RealESRGAN_x4plus
+  -s, --outscale       The final upsampling scale of the image. Default: 4
+  --suffix             Suffix of the restored image. Default: out
+  -t, --tile           Tile size, 0 for no tile during testing. Default: 0
+  --face_enhance       Whether to use GFPGAN to enhance face. Default: False
+  --fp32               Use fp32 precision during inference. Default: fp16 (half precision).
+  --ext                Image extension. Options: auto | jpg | png, auto means using the same extension as inputs. Default: auto
+```
 
-### Inference general images
+#### Inference general images
 
 Download pre-trained models: [RealESRGAN_x4plus.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth)
 
@@ -209,7 +208,7 @@ python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs --face_enhance
 
 Results are in the `results` folder
 
-### Inference anime images
+#### Inference anime images
 
 <p align="center">
   <img src="https://raw.githubusercontent.com/xinntao/public-figures/master/Real-ESRGAN/cmp_realesrgan_anime_1.png">
@@ -227,34 +226,7 @@ python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i inputs
 
 Results are in the `results` folder
 
-### Usage of python script
-
-1. You can use X4 model for **arbitrary output size** with the argument `outscale`. The program will further perform cheap resize operation after the Real-ESRGAN output.
-
-```console
-Usage: python inference_realesrgan.py -n RealESRGAN_x4plus -i infile -o outfile [options]...
-
-A common command: python inference_realesrgan.py -n RealESRGAN_x4plus -i infile --outscale 3.5 --face_enhance
-
-  -h                   show this help
-  -i --input           Input image or folder. Default: inputs
-  -o --output          Output folder. Default: results
-  -n --model_name      Model name. Default: RealESRGAN_x4plus
-  -s, --outscale       The final upsampling scale of the image. Default: 4
-  --suffix             Suffix of the restored image. Default: out
-  -t, --tile           Tile size, 0 for no tile during testing. Default: 0
-  --face_enhance       Whether to use GFPGAN to enhance face. Default: False
-  --fp32               Use fp32 precision during inference. Default: fp16 (half precision).
-  --ext                Image extension. Options: auto | jpg | png, auto means using the same extension as inputs. Default: auto
-```
-
-## :european_castle: Model Zoo
-
-Please see [docs/model_zoo.md](docs/model_zoo.md)
-
-## :computer: Training and Finetuning on your own dataset
-
-A detailed guide can be found in [Training.md](docs/Training.md).
+---
 
 ## BibTeX
 
@@ -265,11 +237,29 @@ A detailed guide can be found in [Training.md](docs/Training.md).
         date      = {2021}
     }
 
-## :e-mail: Contact
+## 📧 Contact
 
 If you have any question, please email `xintao.wang@outlook.com` or `xintaowang@tencent.com`.
 
-## :hugs: Acknowledgement
+<!---------------------------------- Projects that use Real-ESRGAN --------------------------->
+## 🧩 Projects that use Real-ESRGAN
+
+If you develop/use Real-ESRGAN in your projects, welcome to let me know.
+
+- NCNN-Android: [RealSR-NCNN-Android](https://github.com/tumuyan/RealSR-NCNN-Android) by [tumuyan](https://github.com/tumuyan)
+- VapourSynth: [vs-realesrgan](https://github.com/HolyWu/vs-realesrgan) by [HolyWu](https://github.com/HolyWu)
+- NCNN: [Real-ESRGAN-ncnn-vulkan](https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan)
+
+&nbsp;&nbsp;&nbsp;&nbsp;**GUI**
+
+- [Waifu2x-Extension-GUI](https://github.com/AaronFeng753/Waifu2x-Extension-GUI) by [AaronFeng753](https://github.com/AaronFeng753)
+- [Squirrel-RIFE](https://github.com/Justin62628/Squirrel-RIFE) by [Justin62628](https://github.com/Justin62628)
+- [Real-GUI](https://github.com/scifx/Real-GUI) by [scifx](https://github.com/scifx)
+- [Real-ESRGAN_GUI](https://github.com/net2cn/Real-ESRGAN_GUI) by [net2cn](https://github.com/net2cn)
+- [Real-ESRGAN-EGUI](https://github.com/WGzeyu/Real-ESRGAN-EGUI) by [WGzeyu](https://github.com/WGzeyu)
+- [anime_upscaler](https://github.com/shangar21/anime_upscaler) by [shangar21](https://github.com/shangar21)
+
+## 🤗 Acknowledgement
 
 Thanks for all the contributors.
 

docs/CONTRIBUTING.md

@@ -1,5 +1,7 @@
 # Contributing to Real-ESRGAN
 
+:art: Real-ESRGAN needs your contributions. Any contributions are welcome, such as new features/models/typo fixes/suggestions/maintenance, *etc*. See [CONTRIBUTING.md](docs/CONTRIBUTING.md). All contributors are list [here](README.md#hugs-acknowledgement).
+
 We like open-source and want to develop practical algorithms for general image restoration. However, individual strength is limited. So, any kinds of contributions are welcome, such as:
 
 - New features

docs/anime_video_model.md

@@ -1,7 +1,7 @@
 # Anime Video Models
 
 :white_check_mark: We add small models that are optimized for anime videos :-)<br>
-More comparisons can be found in [anime_comparisons.md](docs/anime_comparisons.md)
+More comparisons can be found in [anime_comparisons.md](anime_comparisons.md)
 
 - [How to Use](#how-to-use)
 - [PyTorch Inference](#pytorch-inference)
@@ -42,6 +42,7 @@ CUDA_VISIBLE_DEVICES=0 python inference_realesrgan_video.py -i inputs/video/onep
 # multi gpu and multi process inference
 CUDA_VISIBLE_DEVICES=0,1,2,3 python inference_realesrgan_video.py -i inputs/video/onepiece_demo.mp4 -n realesr-animevideov3 -s 2 --suffix outx2 --num_process_per_gpu 2
 ```
+
 ```console
 Usage:
 --num_process_per_gpu    The total number of process is num_gpu * num_process_per_gpu. The bottleneck of