compile.rst 2.83 KB
Newer Older
Zhang's avatar
v0.2.0  
Zhang committed
1
2
Install and Citations
=====================
Hang Zhang's avatar
docs  
Hang Zhang committed
3

Hang Zhang's avatar
v0.1.0  
Hang Zhang committed
4

Hang Zhang's avatar
Hang Zhang committed
5
6
Installation
------------
Hang Zhang's avatar
v0.1.0  
Hang Zhang committed
7

Hang Zhang's avatar
Hang Zhang committed
8
    * Install PyTorch 1.4.0 by following the `PyTorch instructions <http://pytorch.org/>`_.
Hang Zhang's avatar
Hang Zhang committed
9
 
Hang Zhang's avatar
Hang Zhang committed
10
    * PIP Install::
Hang Zhang's avatar
v0.1.0  
Hang Zhang committed
11

Hang Zhang's avatar
Hang Zhang committed
12
        pip install torch-encoding --pre
Hang Zhang's avatar
docs  
Hang Zhang committed
13

Hang Zhang's avatar
Hang Zhang committed
14
    * Install from source:: 
Hang Zhang's avatar
docs  
Hang Zhang committed
15

Hang Zhang's avatar
Hang Zhang committed
16
17
        git clone https://github.com/zhanghang1989/PyTorch-Encoding && cd PyTorch-Encoding
        python setup.py install
Hang Zhang's avatar
docs  
Hang Zhang committed
18

Hang Zhang's avatar
Hang Zhang committed
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36

Detailed Steps
--------------

This tutorial is a sucessful setup example for AWS EC2 p3 instance with ubuntu 16.04, CUDA 10.
We cannot guarantee it to work for all the machines, but the steps should be similar.
Assuming CUDA and cudnn are already sucessfully installed, otherwise please refer to other tutorials.

      * Install Anaconda from the `link <https://www.anaconda.com/distribution/>`_ .

      * Install ninja::
 
         wget https://github.com/ninja-build/ninja/releases/download/v1.8.2/ninja-linux.zip
         sudo unzip ninja-linux.zip -d /usr/local/bin/
         sudo update-alternatives --install /usr/bin/ninja ninja /usr/local/bin/ninja 1 --force

      * Install PyTorch::

Hang Zhang's avatar
Hang Zhang committed
37
         conda install pytorch torchvision cudatoolkit=10.0 -c pytorch
Hang Zhang's avatar
Hang Zhang committed
38
39
40
41
42

      * Install this package::

         pip install torch-encoding --pre

Zhang's avatar
v0.2.0  
Zhang committed
43
Citations
Hang Zhang's avatar
v0.1.0  
Hang Zhang committed
44
---------
Hang Zhang's avatar
v1.0.1  
Hang Zhang committed
45
46

    .. note::
47
48
49
50
51
52
53
54
        * Hang Zhang et al. "ResNeSt: Split-Attention Networks" *arXiv 2020*::

            @article{zhang2020resnest,
            title={ResNeSt: Split-Attention Networks},
            author={Zhang, Hang and Wu, Chongruo and Zhang, Zhongyue and Zhu, Yi and Zhang, Zhi and Lin, Haibin and Sun, Yue and He, Tong and Muller, Jonas and Manmatha, R. and Li, Mu and Smola, Alexander},
            journal={arXiv preprint arXiv:2004.08955},
            year={2020}
            }
Hang Zhang's avatar
v0.2.0  
Hang Zhang committed
55
56
57
58
59
60
61
62
63
64
65

        * Hang Zhang, Kristin Dana, Jianping Shi, Zhongyue Zhang, Xiaogang Wang, Ambrish Tyagi, Amit Agrawal. "Context Encoding for Semantic Segmentation"  *The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018*::

            @InProceedings{Zhang_2018_CVPR,
            author = {Zhang, Hang and Dana, Kristin and Shi, Jianping and Zhang, Zhongyue and Wang, Xiaogang and Tyagi, Ambrish and Agrawal, Amit},
            title = {Context Encoding for Semantic Segmentation},
            booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
            month = {June},
            year = {2018}
            }

Hang Zhang's avatar
v1.0.1  
Hang Zhang committed
66
67
68
69
70
71
72
73
74
75

        * Hang Zhang, Jia Xue, and Kristin Dana. "Deep TEN: Texture Encoding Network." *The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017*::

            @InProceedings{Zhang_2017_CVPR,
            author = {Zhang, Hang and Xue, Jia and Dana, Kristin},
            title = {Deep TEN: Texture Encoding Network},
            booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
            month = {July},
            year = {2017}
            }