# PU-GAN-A100

**Repository Path**: casesense/pu-gan-a100

## Basic Information

- **Project Name**: PU-GAN-A100
- **Description**: PU-GAN-A100
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2021-11-28
- **Last Updated**: 2023-06-11

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# PU-GAN项目的A100卡适配

注意，首先需要下载`PU-GAN`模型文件，并上传至目录`data/train`中。`PU-GAN`模型文件下载云盘地址如下：

> 链接：https://pan.baidu.com/s/11eOpm9lyB7Ch6MlsDU3qvg 
> 提取码：ts17 

PU-GAN项目运行的视频演示链接：https://www.bilibili.com/video/BV1fY411W7U2/ 

## 适配方法1

为了使PU-GAN项目能够在A100卡上运行，在本项目的 `Docker-A100`[目录下](./Docker-A100)，编写了新版的Dockerfile。

同时，由于新镜像是基于英伟达官方维护的A100适配版tf1.x Docker镜像`nvcr.io/nvidia/tensorflow:21.11-tf1-py3`制作的，cudart库及cuda_runtime.h头文件的路径与PU-GAN原项目所使用的环境不一致，因此在 `tf_ops/`目录下各个子目录中，对编译项目的Shell脚本文件（.sh）做了修改，添加了cudart路径`-L/usr/local/cuda-11.5/targets/x86_64-linux/lib/`，以及头文件路径`-I/usr/local/cuda-11.5/targets/x86_64-linux/include/`。

适配后的Docker使用方式参考[本说明](./Docker-A100)。

## 适配方法2

第2种方法是直接使用英伟达官方镜像运行PU-GAN项目，使用方法如下：

```
docker pull nvcr.io/nvidia/tensorflow:21.11-tf1-py3

docker run -it --rm \
    -e DISPLAY=unix$DISPLAY \
    -v $(pwd):/workspace/ \
    -v /tmp/.X11-unix:/tmp/.X11-unix \
    -w /workspace \
    --name pu-gan-runtime \
    --gpus all \
    --shm-size 8G \
    nvcr.io/nvidia/tensorflow:21.11-tf1-py3

bash bash_file.sh

cd tf_ops; bash compile.sh; cd ..

python pu_gan.py --phase train
```
---

原版README内容如下：

---


# PU-GAN: a Point Cloud Upsampling Adversarial Network
by [Ruihui Li](https://liruihui.github.io/), [Xianzhi Li](https://nini-lxz.github.io/), [Chi-Wing Fu](http://www.cse.cuhk.edu.hk/~cwfu/), [Daniel Cohen-Or](https://www.cs.tau.ac.il/~dcor/), [Pheng-Ann Heng](http://www.cse.cuhk.edu.hk/~pheng/). 

### Introduction 

This repository is for our ICCV 2019 paper '[PU-GAN: a Point Cloud Upsampling Adversarial Network](https://liruihui.github.io/publication/PU-GAN/)'. The code is modified from [3PU](https://github.com/yifita/3PU) and [PU-Net](https://github.com/yulequan/PU-Net). 

### Docker
A Dockerfile is provided to help you relief the pain of configurate training environment. 

See the instructions in [here](./Docker).

### Installation
This repository is based on Tensorflow and the TF operators from PointNet++. Therefore, you need to install tensorflow and compile the TF operators. 

For installing tensorflow, please follow the official instructions in [here](https://www.tensorflow.org/install/install_linux). The code is tested under TF1.11 (higher version should also work) and Python 3.6 on Ubuntu 16.04.

For compiling TF operators, please check `tf_xxx_compile.sh` under each op subfolder in `code/tf_ops` folder. Note that you need to update `nvcc`, `python` and `tensoflow include library` if necessary. 

### Note
When running the code, if you have `undefined symbol: _ZTIN10tensorflow8OpKernelE` error, you need to compile the TF operators. If you have already added the `-I$TF_INC/external/nsync/public -L$TF_LIB -ltensorflow_framework` but still have ` cannot find -ltensorflow_framework` error. Please use 'locate tensorflow_framework
' to locate the tensorflow_framework library and make sure this path is in `$TF_LIB`.

### Usage

1. Clone the repository:

   ```shell
   https://github.com/liruihui/PU-GAN.git
   cd PU-GAN
   ```
   
2. Compile the TF operators
   Follow the above information to compile the TF operators. 
   
3. Train the model:
    First, you need to download the training patches in HDF5 format from [GoogleDrive](https://drive.google.com/open?id=13ZFDffOod_neuF3sOM0YiqNbIJEeSKdZ) and put it in folder `data/train`.
    Then run:
   ```shell
   cd code
   python pu_gan.py --phase train
   ```

4. Evaluate the model:
    First, you need to download the pretrained model from [GoogleDrive](https://drive.google.com/open?id=12kWoB0-_tflq65RNpJEnNGTTwPXa6IOH), extract it and put it in folder 'model'.
    Then run:
   ```shell
   cd code
   python pu_gan.py --phase test
   ```
   You will see the input and output results in the folder `data/test/output`.
   
5. The training and testing mesh files can be downloaded from [GoogleDrive](https://drive.google.com/open?id=1BNqjidBVWP0_MUdMTeGy1wZiR6fqyGmC).

### Evaluation code
We provide the code to calculate the uniform metric in the evaluation code folder. In order to use it, you need to install the CGAL library. Please refer [this link](https://www.cgal.org/download/linux.html) and  [PU-Net](https://github.com/yulequan/PU-Net) to install this library.
Then:
   ```shell
   cd evaluation_code
   cmake .
   make
   ./evaluation Icosahedron.off Icosahedron.xyz
   ```
The second argument is the mesh, and the third one is the predicted points.

## Citation

If PU-GAN is useful for your research, please consider citing:

    @inproceedings{li2019pugan,
         title={PU-GAN: a Point Cloud Upsampling Adversarial Network},
         author={Li, Ruihui and Li, Xianzhi and Fu, Chi-Wing and Cohen-Or, Daniel and Heng, Pheng-Ann},
         booktitle = {{IEEE} International Conference on Computer Vision ({ICCV})},
         year = {2019}
     }


### Questions

Please contact 'lirh@cse.cuhk.edu.hk'