README.md 2.28 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
[![Codefresh build status]( https://g.codefresh.io/api/badges/pipeline/zasdfgbnm/aiqm%2Ftorchani%2Ftorchani?branch=master&type=cf-1)]( https://g.codefresh.io/repositories/aiqm/torchani/builds?filter=trigger:build;branch:master;service:5babc52a8a90dc40a407b05f~torchani)
Gao, Xiang's avatar
Gao, Xiang committed
4

Gao, Xiang's avatar
Gao, Xiang committed
5
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
6

Xiang Gao's avatar
Xiang Gao committed
7
8
<img src=https://raw.githubusercontent.com/aiqm/torchani/master/logo2.png width=500/>

Gao, Xiang's avatar
Gao, Xiang committed
9
10
# Install

11
TorchANI requires the latest preview version of PyTorch. You can install PyTorch by
Gao, Xiang's avatar
Gao, Xiang committed
12

Richard Xue's avatar
Richard Xue committed
13
14
15
```bash
conda install pytorch-nightly -c pytorch
```
16
17
If you updated TorchANI, you may also need to update PyTorch:

Richard Xue's avatar
Richard Xue committed
18
```bash
19
conda update pytorch-nightly -c pytorch
20
```
Gao, Xiang's avatar
Gao, Xiang committed
21

22
After installing the correct PyTorch, you can install TorchANI by:
Gao, Xiang's avatar
Gao, Xiang committed
23
24

```bash
25
pip install torchani
Gao, Xiang's avatar
Gao, Xiang committed
26
27
```

28
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
29

Gao, Xiang's avatar
Gao, Xiang committed
30
31
32
33
34
35
36
37
# 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.

38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
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
56
# Note to TorchANI developers
Gao, Xiang's avatar
Gao, Xiang committed
57
58
59
60
61

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
62
63
Code review is required before merging pull request.

Gao, Xiang's avatar
Gao, Xiang committed
64
To manually run unit tests, do `python setup.py test`