README.md 4.17 KB
Newer Older
Xiang Gao's avatar
Xiang Gao committed
1
# <img src=https://raw.githubusercontent.com/aiqm/torchani/master/logo1.png width=180/>  Accurate Neural Network Potential on PyTorch
Gao, Xiang's avatar
Gao, Xiang committed
2

3
4
Build:

Gao, Xiang's avatar
Gao, Xiang committed
5
6
7
8
9
[![flake8](https://zasdfgbnm.visualstudio.com/torchani/_apis/build/status/flake8)](https://zasdfgbnm.visualstudio.com/torchani/_build/latest?definitionId=3)
[![docs](https://zasdfgbnm.visualstudio.com/torchani/_apis/build/status/docs)](https://zasdfgbnm.visualstudio.com/torchani/_build/latest?definitionId=4)
[![runnable submodules](https://zasdfgbnm.visualstudio.com/torchani/_apis/build/status/runnable-submodules)](https://zasdfgbnm.visualstudio.com/torchani/_build/latest?definitionId=5)
[![unit tests](https://zasdfgbnm.visualstudio.com/torchani/_apis/build/status/unit-tests)](https://zasdfgbnm.visualstudio.com/torchani/_build/latest?definitionId=6)
[![tools](https://zasdfgbnm.visualstudio.com/torchani/_apis/build/status/tools)](https://zasdfgbnm.visualstudio.com/torchani/_build/latest?definitionId=7)
10
11
[![CodeFactor](https://www.codefactor.io/repository/github/aiqm/torchani/badge/master)](https://www.codefactor.io/repository/github/aiqm/torchani/overview/master)
[![codecov](https://codecov.io/gh/aiqm/torchani/branch/master/graph/badge.svg)](https://codecov.io/gh/aiqm/torchani)
Gao, Xiang's avatar
Gao, Xiang committed
12
[![Total alerts](https://img.shields.io/lgtm/alerts/g/aiqm/torchani.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/aiqm/torchani/alerts/)
Gao, Xiang's avatar
Gao, Xiang committed
13

Gao, Xiang's avatar
Gao, Xiang committed
14
Deploy (these builds only succeed on tagged commits):
15
16

[![Build Status](https://zasdfgbnm.visualstudio.com/torchani/_apis/build/status/Deploy%20docs?branchName=master)](https://zasdfgbnm.visualstudio.com/torchani/_build/latest?definitionId=9?branchName=master)
Gao, Xiang's avatar
Gao, Xiang committed
17
[![Build Status](https://zasdfgbnm.visualstudio.com/torchani/_apis/build/status/Deploy%20PYPI?branchName=master)](https://zasdfgbnm.visualstudio.com/torchani/_build/latest?definitionId=10?branchName=master)
18

Gao, Xiang's avatar
Gao, Xiang committed
19
TorchANI is a pytorch implementation of ANI. It is currently under alpha release, which means, the API is not stable yet. If you find a bug of TorchANI, or have some feature request, feel free to open an issue on GitHub, or send us a pull request.
Gao, Xiang's avatar
Gao, Xiang committed
20

Xiang Gao's avatar
Xiang Gao committed
21
22
<img src=https://raw.githubusercontent.com/aiqm/torchani/master/logo2.png width=500/>

Gao, Xiang's avatar
Gao, Xiang committed
23
24
# Install

25
TorchANI requires the latest preview version of PyTorch. You can install PyTorch by the following commands (assuming cuda10):
Gao, Xiang's avatar
Gao, Xiang committed
26

Richard Xue's avatar
Richard Xue committed
27
```bash
28
29
pip install numpy torchvision_nightly
pip install torch_nightly -f https://download.pytorch.org/whl/nightly/cu100/torch_nightly.html
Richard Xue's avatar
Richard Xue committed
30
```
31

32
33
If you updated TorchANI, you may also need to update PyTorch:

Richard Xue's avatar
Richard Xue committed
34
```bash
35
pip install --upgrade torch_nightly -f https://download.pytorch.org/whl/nightly/cu100/torch_nightly.html
36
```
Gao, Xiang's avatar
Gao, Xiang committed
37

38
After installing the correct PyTorch, you can install TorchANI by:
Gao, Xiang's avatar
Gao, Xiang committed
39
40

```bash
41
pip install torchani
Gao, Xiang's avatar
Gao, Xiang committed
42
43
```

44
See also [PyTorch's official site](https://pytorch.org/get-started/locally/) for instructions of installing latest preview version of PyTorch.
Gao, Xiang's avatar
Gao, Xiang committed
45

46
47
Please install nightly PyTorch through `pip install` instead of `conda install`. If your PyTorch is installed through `conda install`, then `pip` would mistakenly recognize the package name as `torch` instead of `torch-nightly`, which would cause dependency issue when installing TorchANI.

Gao, Xiang's avatar
Gao, Xiang committed
48
49
50
51
52
53
54
55
# Paper

The original ANI-1 paper is:

* Smith JS, Isayev O, Roitberg AE. ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost. Chemical science. 2017;8(4):3192-203.

We are planning a seperate paper for TorchANI, it will be available when we are ready for beta release of TorchANI.

56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
See also: [isayev/ASE_ANI](https://github.com/isayev/ASE_ANI)

# Develop

To install TorchANI from GitHub:

```bash
git clone https://github.com/aiqm/torchani.git
cd torchani
pip install -e .
```

After TorchANI has been installed, you can build the documents by running `sphinx-build docs build`. But make sure you
install dependencies:
```bash
pip install sphinx sphinx-gallery pillow matplotlib sphinx_rtd_theme
```

Gao, Xiang's avatar
Gao, Xiang committed
74
# Note to TorchANI developers
Gao, Xiang's avatar
Gao, Xiang committed
75
76
77
78
79

Never commit to the master branch directly. If you need to change something, create a new branch, submit a PR on GitHub.

You must pass all the tests on GitHub before your PR can be merged.

Gao, Xiang's avatar
Gao, Xiang committed
80
81
Code review is required before merging pull request.

Gao, Xiang's avatar
Gao, Xiang committed
82
To manually run unit tests, do `python setup.py test`