Commit bc0c045b authored by Benoit Rostykus's avatar Benoit Rostykus
Browse files

Initial commit for Open Source

parents
sudo: false
os:
- linux
- osx
language: d
d:
- ldc
- ldc-1.1.1
- dmd
- dmd-2.073.1
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright 2017 Netflix, Inc.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
Vectorflow is a lightweight neural network library for sparse data.
Copyright: 2017 Netflix, Inc.
to_float function has been adapted from D Phobos standard library std.conv
which is under Boost Licence 1.0:
Boost Software License - Version 1.0 - August 17th, 2003
Permission is hereby granted, free of charge, to any person or organization
obtaining a copy of the software and accompanying documentation covered by
this license (the "Software") to use, reproduce, display, distribute,
execute, and transmit the Software, and to prepare derivative works of the
Software, and to permit third-parties to whom the Software is furnished to
do so, all subject to the following:
The copyright notices in the Software and this entire statement, including
the above license grant, this restriction and the following disclaimer,
must be included in all copies of the Software, in whole or in part, and
all derivative works of the Software, unless such copies or derivative
works are solely in the form of machine-executable object code generated by
a source language processor.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.
osslifecycle=public
<img src="http://ae.nflximg.net/vectorflow/vectorflow_logo.png" width="200">
**Vectorflow** is a minimalist neural network library optimized for sparse data and single machine environments.
### Installation
#### dub package
The library is distributed as a [`dub`](https://code.dlang.org/) package. Add `vectorflow` to the `dependencies` section of your `dub.json`:
```
"vectorflow": "~>1.0.0"
```
The library itself doesn't have any dependency. All you need is a recent D compiler.
**`LDC` is the recommended compiler** for the fastest runtime speed.
Tested on:
- Linux, OSX
- LDC version: >= 1.1.1
- DMD version: >= 2.073.1
#### Setting up a D environment
If you're new to [D](http://dlang.org/), keep reading. You will need `dub` (the D package manager) and `LDC` (the LLVM-based D compiler).
##### macOs
```
brew install dub
brew install ldc
```
##### Ubuntu
`dub` can be downloaded [here](https://code.dlang.org/download) (or follow instructions [on this page](http://blog.ljdelight.com/installing-dlang-dmd-dub-on-ubuntu/)).
`LDC` can be installed by running:
```
snap install --classic --edge ldc2
```
### Examples
To run the RCV1 example (sparse logistic regression):
```
cd examples && ./compile_run.sh rcv1.d
```
### Tests
To run the tests:
```
dub test
```
### Documentation
`vectorflow` is using [ddoc](https://dlang.org/spec/ddoc.html).
One way of building and serving locally the documentation (you will need `libevent` for serving) is:
```
dub build -b ddox && dub run -b ddox
```
Or use your favorite DDOC compiler.
Please also refer to the repo wiki.
{
"name": "vectorflow",
"description": "Minimalist neural network library for sparse data",
"copyright": "Copyright: 2017 Netflix, Inc.",
"license": "Apache-2.0",
"authors": ["Netflix"],
"configurations": [
{
"name": "lib",
"targetName": "vectorflow",
"targetType": "library",
"excludedSourceFiles": [
"test/*.d",
"examples/*.d"
]
},
{
"name": "unittest",
"targetType": "library",
"sourcePaths": [
"test"
],
"importPaths": [
"test"
],
"excludedSourceFiles": [
"examples/*.d"
]
}
]
}
time dub run -q -b release --compiler=ldc2 --single $1
/+ dub.json:
{
"name": "mnist",
"dependencies": {"vectorflow": "*"}
}
+/
import std.stdio;
import std.algorithm;
import vectorflow;
import vectorflow.math : fabs, round;
static auto data_dir = "mnist_data/";
struct Obs {
float label;
float[] features;
}
auto load_data()
{
import std.file;
import std.typecons;
if(!exists(data_dir))
{
auto root_url = "http://yann.lecun.com/exdb/mnist/";
mkdir(data_dir);
import std.net.curl;
import std.process;
writeln("Downloading training set...");
download(
root_url ~ "train-images-idx3-ubyte.gz",
data_dir ~ "train.gz");
download(
root_url ~ "train-labels-idx1-ubyte.gz",
data_dir ~ "train_labels.gz");
writeln("Downloading test set...");
download(
root_url ~ "t10k-images-idx3-ubyte.gz",
data_dir ~ "test.gz");
download(
root_url ~ "t10k-labels-idx1-ubyte.gz",
data_dir ~ "test_labels.gz");
wait(spawnShell(`gunzip ` ~ data_dir ~ "train.gz"));
wait(spawnShell(`gunzip ` ~ data_dir ~ "train_labels.gz"));
wait(spawnShell(`gunzip ` ~ data_dir ~ "test.gz"));
wait(spawnShell(`gunzip ` ~ data_dir ~ "test_labels.gz"));
}
return tuple(load_data(data_dir ~ "train"), load_data(data_dir ~ "test"));
}
Obs[] load_data(string prefix)
{
import std.conv;
import std.bitmanip;
import std.exception;
import std.array;
auto fx = File(prefix, "rb");
auto fl = File(prefix ~ "_labels", "rb");
scope(exit)
{
fx.close();
fl.close();
}
T to_native(T)(T b)
{
return bigEndianToNative!T((cast(ubyte*)&b)[0..b.sizeof]);
}
Obs[] res;
int n;
fx.rawRead((&n)[0..1]);
enforce(to_native(n) == 2051, "Wrong MNIST magic number. Corrupted data");
foreach(_; 0..3)
fx.rawRead((&n)[0..1]);
foreach(_; 0..2)
fl.rawRead((&n)[0..1]);
if(prefix == data_dir ~ "train")
n = 60_000;
else
n = 10_000;
res.length = n;
ubyte[] pxls = new ubyte[28 * 28];
foreach(i; 0..n)
{
ubyte label;
fl.rawRead((&label)[0..1]);
fx.rawRead(pxls);
res[i] = Obs(label.to!float, pxls.to!(float[]));
}
return res;
}
void main(string[] args)
{
writeln("Hello world!");
auto nn = NeuralNet()
.stack(DenseData(28 * 28)) // MNIST is of dimension 28 * 28 = 784
.stack(Linear(200)) // one hidden layer
.stack(DropOut(0.3))
.stack(SeLU()) // non-linear activation
.stack(Linear(10)); // 10 classes for 10 digits
nn.initialize(0.0001);
auto data = load_data();
auto train = data[0];
auto test = data[1];
nn.learn(train, "multinomial",
new ADAM(
15, // number of passes
0.0001, // learning rate
200 // mini-batch-size
),
true, // verbose
4 // number of cores
);
// if you want to save the model locally, do this:
// nn.serialize("dump_model.vf");
// if you want to load a serialized from disk, do that:
// auto nn = NeuralNet.deserialize("mnist_model.vf");
double err = 0;
foreach(ref o; test)
{
auto pred = nn.predict(o);
float max_dp = -float.max;
ulong ind = 0;
foreach(i, f; pred)
if(f > max_dp)
{
ind = i;
max_dp = f;
}
if(fabs(o.label - ind) > 1e-3)
err++;
}
err /= test.length;
writeln("Classification error: ", err);
}
/+ dub.json:
{
"name": "rcv1",
"dependencies": {"vectorflow": "*"}
}
+/
import std.conv : to;
import std.stdio;
import std.algorithm;
import std.algorithm.searching : countUntil;
import std.algorithm.iteration : splitter;
import vectorflow;
import vectorflow.math : fabs, round;
import vectorflow.dataset : DataFileReader, MultiFilesReader;
import vectorflow.utils : to_long, to_float;
static auto data_dir = "rcv1_data/";
struct Obs {
float label;
SparseF[] features;
Obs dup()
{
return Obs(label, features.dup);
}
}
auto load_data()
{
// For details on the original dataset, see:
// Lewis, David D., et al. "Rcv1: A new benchmark collection for text
// categorization research." Journal of machine learning research
// 5.Apr (2004): 361-397.
import std.file;
import std.typecons;
if(!exists(data_dir))
{
auto root_url = "http://ae.nflximg.net/vectorflow/";
auto url_data = root_url ~ "lyrl2004_vectors_";
auto url_topics = root_url ~ "rcv1v2.topics.qrels.gz";
mkdir(data_dir);
import std.net.curl;
import std.process;
writeln("Downloading data...");
download(url_data ~ "test_pt0.dat.gz", data_dir ~ "test0.gz");
download(url_data ~ "test_pt1.dat.gz", data_dir ~ "test1.gz");
download(url_data ~ "test_pt2.dat.gz", data_dir ~ "test2.gz");
download(url_data ~ "test_pt3.dat.gz", data_dir ~ "test3.gz");
download(url_data ~ "train.dat.gz", data_dir ~ "train.gz");
download(url_topics, data_dir ~ "topics.gz");
wait(spawnShell(`gunzip ` ~ data_dir ~ "test0.gz"));
wait(spawnShell(`gunzip ` ~ data_dir ~ "test1.gz"));
wait(spawnShell(`gunzip ` ~ data_dir ~ "test2.gz"));
wait(spawnShell(`gunzip ` ~ data_dir ~ "test3.gz"));
wait(spawnShell(`gunzip ` ~ data_dir ~ "train.gz"));
wait(spawnShell(`gunzip ` ~ data_dir ~ "topics.gz"));
}
// Following Bottou's construction, we use `test{0,1,2,3}` as training set
// and `train` as test set and build a binary classification
// dataset to predict whether or not an article has the tag CCAT
auto labels = load_labels("CCAT");
writeln("Number of positives: ", labels.sum);
return tuple(
new MultiFilesReader!(Obs)(
[new RCV1Reader(data_dir ~ "test0", labels),
new RCV1Reader(data_dir ~ "test1", labels),
new RCV1Reader(data_dir ~ "test2", labels),
new RCV1Reader(data_dir ~ "test3", labels)]),
new RCV1Reader(data_dir ~ "train", labels));
}
bool[] load_labels(string cat_name)
{
auto labels = new bool[816_000];
labels[] = false;
auto f = File(data_dir ~ "topics", "r");
scope(exit) f.close();
char[] buff;
while(f.readln(buff))
{
auto toks = splitter(buff, " ");
if(toks.front == cat_name)
{
toks.popFront();
auto ind = to_long(toks.front);
labels[ind] = true;
}
}
return labels;
}
/*
Data reader : iterable of
`Obs` == (label, array of (feature_id == uint, feature_value == float))
*/
class RCV1Reader : DataFileReader!(Obs) {
private char[] buff;
private SparseF[] features_buff;
bool[] labels;
uint mask = (1 << 16) - 1;
this(string path, bool[] labels_)
{
super(path, false);
labels = labels_;
features_buff.length = 1_500;
_obs = Obs(0, null);
}
override bool read_next()
{
if(_f.eof)
return false;
_f.readln(buff);
auto lab_end = countUntil(buff, " ");
if(lab_end == -1)
return false;
auto label = labels[to_long(buff[0..lab_end])];
_obs.label = label;
ulong cnt = 0;
foreach(t; splitter(buff[lab_end+2..$], ' '))
{
auto feat_id_end = countUntil(t, ':');
if(feat_id_end < 1)
continue;
auto feat_id = to_long(t[0..feat_id_end]).to!uint & mask; // hashing trick
auto feat_val = to_float(t[feat_id_end+1..$]);
features_buff[cnt++] = SparseF(feat_id, feat_val);
}
_obs.features = features_buff[0..cnt];
return true;
}
override @property RCV1Reader save()
{
auto cp = new RCV1Reader(_path, labels);