Skip to content

Commit a5648e2

Browse files
committed
Update readme and docs for new standards in 0.4
1 parent c3029a5 commit a5648e2

File tree

6 files changed

+52
-328
lines changed

6 files changed

+52
-328
lines changed

README.md

+47-62
Original file line numberDiff line numberDiff line change
@@ -14,32 +14,33 @@ See the License for the specific language governing permissions and
1414
limitations under the License.
1515
-->
1616

17-
# ![icon for SparseZoo](https://raw.githubusercontent.com/neuralmagic/sparsezoo/main/docs/source/icon-sparsezoo.png) SparseZoo
17+
<h1><img src="https://raw.githubusercontent.com/neuralmagic/sparsezoo/main/docs/source/icon-sparsezoo.png" />&nbsp;&nbsp;SparseZoo</h1>
1818

19-
### Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes
19+
<h3>Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes</h3>
2020

2121
<p>
22-
<a href="https://docs.neuralmagic.com/sparsezoo/index.html">
23-
<img alt="Documentation" src="https://img.shields.io/website/http/docs.neuralmagic.com/sparsezoo/index.html.svg?down_color=red&down_message=offline&up_message=online&style=for-the-badge" height=25>
22+
<a href="https://docs.neuralmagic.com/sparsezoo">
23+
<img alt="Documentation" src="https://img.shields.io/badge/documentation-darkred?&style=for-the-badge&logo=read-the-docs" height=25>
2424
</a>
25-
<a href="https://github.com/neuralmagic/sparsezoo/actions/workflows/quality-check.yaml">
26-
<img alt="Quality Check" src="https://img.shields.io/github/workflow/status/neuralmagic/sparsezoo/Quality%20Checks/main?label=Quality%20Checks&style=for-the-badge" height=25>
25+
<a href="https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ/">
26+
<img src="https://img.shields.io/badge/slack-purple?style=for-the-badge&logo=slack" height=25>
2727
</a>
28-
<a href="https://github.com/neuralmagic/sparsezoo/actions/workflows/test-check.yaml?query=branch%3Amain">
29-
<img alt="Main" src="https://img.shields.io/github/workflow/status/neuralmagic/sparsezoo/Test%20Checks/main?label=Main&&style=for-the-badge" height=25>
28+
<a href="https://discuss.neuralmagic.com/">
29+
<img src="https://img.shields.io/badge/support%20forums-navy?style=for-the-badge&logo=discourse" height=25>
3030
</a>
31-
</p>
32-
<p>
33-
<a href="https://github.com/neuralmagic/sparsezoo/blob/main/LICENSE">
34-
<img alt="GitHub" src="https://img.shields.io/github/license/neuralmagic/sparsezoo.svg?color=purple&style=for-the-badge" height=25>
31+
<a href="https://github.com/neuralmagic/sparsezoo/actions/workflows/test-check.yaml">
32+
<img alt="Main" src="https://img.shields.io/github/workflow/status/neuralmagic/sparsezoo/Test%20Checks/main?label=build&style=for-the-badge" height=25>
3533
</a>
3634
<a href="https://github.com/neuralmagic/sparsezoo/releases">
3735
<img alt="GitHub release" src="https://img.shields.io/github/release/neuralmagic/sparsezoo.svg?style=for-the-badge" height=25>
3836
</a>
37+
<a href="https://github.com/neuralmagic/sparsezoo/blob/main/LICENSE">
38+
<img alt="GitHub" src="https://img.shields.io/github/license/neuralmagic/sparsezoo.svg?color=lightgray&style=for-the-badge" height=25>
39+
</a>
3940
<a href="https://github.com/neuralmagic/sparsezoo/blob/main/CODE_OF_CONDUCT.md">
4041
<img alt="Contributor Covenant" src="https://img.shields.io/badge/Contributor%20Covenant-v2.0%20adopted-ff69b4.svg?color=yellow&style=for-the-badge" height=25>
4142
</a>
42-
<a href="https://www.youtube.com/channel/UCo8dO_WMGYbWCRnj_Dxr4EA">
43+
<a href="https://www.youtube.com/channel/UCo8dO_WMGYbWCRnj_Dxr4EA">
4344
<img src="https://img.shields.io/badge/-YouTube-red?&style=for-the-badge&logo=youtube&logoColor=white" height=25>
4445
</a>
4546
<a href="https://medium.com/limitlessai">
@@ -58,27 +59,28 @@ It simplifies and accelerates your time-to-value in building performant deep lea
5859
Available via API and hosted in the cloud, the SparseZoo contains both baseline and models sparsified to different degrees of inference performance vs. baseline loss recovery.
5960
Recipe-driven approaches built around sparsification algorithms allow you to take the models as given, transfer-learn from the models onto private datasets, or transfer the recipes to your architectures.
6061

61-
This repository contains the Python API code to handle the connection and authentication to the cloud.
62+
The [GitHub repository](https://github.com/neuralmagic/sparsezoo) contains the Python API code to handle the connection and authentication to the cloud.
6263

64+
<img src="https://docs.neuralmagic.com/docs/source/infographics/sparsezoo.png" width="960px" />
6365

64-
## Sparsification
66+
## Highlights
6567

66-
Sparsification is the process of taking a trained deep learning model and removing redundant information from the overprecise and over-parameterized network resulting in a faster and smaller model.
67-
Techniques for sparsification are all encompassing including everything from inducing sparsity using [pruning](https://neuralmagic.com/blog/pruning-overview/) and [quantization](https://arxiv.org/abs/1609.07061) to enabling naturally occurring sparsity using [activation sparsity](http://proceedings.mlr.press/v119/kurtz20a.html) or [winograd/FFT](https://arxiv.org/abs/1509.09308).
68-
When implemented correctly, these techniques result in significantly more performant and smaller models with limited to no effect on the baseline metrics.
69-
For example, pruning plus quantization can give noticeable improvements in performance while recovering to nearly the same baseline accuracy.
68+
- [Available Models Listing](https://github.com/neuralmagic/sparsezoo/blob/main/docs/source/models.md)
69+
- [Available Recipes Listing](https://github.com/neuralmagic/sparsezoo/blob/main/docs/source/recipes.md)
7070

71-
The Deep Sparse product suite builds on top of sparsification enabling you to easily apply the techniques to your datasets and models using recipe-driven approaches. Recipes encode the directions for how to sparsify a model into a simple, easily editable format.
71+
A number of pre-trained baseline and sparsified models across domains and sub domains are available and constantly being added.
72+
For an up to date list, please consult the [available models listing](https://github.com/neuralmagic/sparsezoo/blob/main/docs/source/models.md).
7273

73-
- Download a sparsification recipe and sparsified model from the [SparseZoo](https://github.com/neuralmagic/sparsezoo).
74-
- Alternatively, create a recipe for your model using [Sparsify](https://github.com/neuralmagic/sparsify).
75-
- Apply your recipe with only a few lines of code using [SparseML](https://github.com/neuralmagic/sparseml).
76-
- Finally, for GPU-level performance on CPUs, deploy your sparse-quantized model with the [DeepSparse Engine](https://github.com/neuralmagic/deepsparse).
74+
## Installation
7775

76+
This repository is tested on Python 3.6+, and Linux/Debian systems.
77+
It is recommended to install in a [virtual environment](https://docs.python.org/3/library/venv.html) to keep your system in order.
7878

79-
**Full Deep Sparse product flow:**
79+
Install with pip using:
8080

81-
<img src="https://docs.neuralmagic.com/docs/source/sparsification/flow-overview.svg" width="960px">
81+
```bash
82+
pip install sparsezoo
83+
```
8284

8385
## Quick Tour
8486

@@ -215,54 +217,37 @@ sparsezoo download --domain cv --sub-domain classification \
215217

216218
For a more in-depth read, check out [SparseZoo documentation](https://docs.neuralmagic.com/sparsezoo/).
217219

218-
## Installation
219-
220-
This repository is tested on Python 3.6+, and Linux/Debian systems.
221-
It is recommended to install in a [virtual environment](https://docs.python.org/3/library/venv.html) to keep your system in order.
222-
223-
Install with pip using:
224-
225-
```bash
226-
pip install sparsezoo
227-
```
228-
229-
Then if you would like to explore any of the [scripts](https://github.com/neuralmagic/sparsezoo/blob/main/scripts/) or [notebooks](https://github.com/neuralmagic/sparsezoo/blob/main/notebooks/)
230-
clone the repository and install any additional dependencies as required.
220+
## Resources
231221

232-
## Available Models and Recipes
222+
### Learning More
233223

234-
A number of pre-trained baseline and sparsified models across domains and sub domains are available and constantly being added.
235-
For an up to date list, please consult the [available models listing](https://github.com/neuralmagic/sparsezoo/blob/main/docs/source/models.md).
236-
237-
## Resources and Learning More
224+
- Documentation: [SparseML](https://docs.neuralmagic.com/sparseml/), [SparseZoo](https://docs.neuralmagic.com/sparsezoo/), [Sparsify](https://docs.neuralmagic.com/sparsify/), [DeepSparse](https://docs.neuralmagic.com/deepsparse/)
225+
- Neural Magic: [Blog](https://www.neuralmagic.com/blog/), [Resources](https://www.neuralmagic.com/resources/)
238226

239-
- [SparseZoo Documentation](https://docs.neuralmagic.com/sparsezoo/)
240-
- [SparseML Documentation](https://docs.neuralmagic.com/sparseml/)
241-
- [Sparsify Documentation](https://docs.neuralmagic.com/sparsify/)
242-
- [DeepSparse Documentation](https://docs.neuralmagic.com/deepsparse/)
243-
- Neural Magic [Blog](https://www.neuralmagic.com/blog/), [Resources](https://www.neuralmagic.com/resources/), [Website](https://www.neuralmagic.com/)
227+
### Release History
244228

245-
## Contributing
229+
Official builds are hosted on PyPI
246230

247-
We appreciate contributions to the code, examples, and documentation as well as bug reports and feature requests! [Learn how here](https://github.com/neuralmagic/sparsezoo/blob/main/CONTRIBUTING.md).
231+
- stable: [sparsezoo](https://pypi.org/project/sparsezoo/)
232+
- nightly (dev): [sparsezoo-nightly](https://pypi.org/project/sparsezoo-nightly/)
248233

249-
## Join the Community
234+
Additionally, more information can be found via [GitHub Releases.](https://github.com/neuralmagic/sparsezoo/releases)
250235

251-
For user help or questions about SparseZoo, sign up or log in: **Deep Sparse Community** [Discourse Forum](https://discuss.neuralmagic.com/) and/or [Slack](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ). We are growing the community member by member and happy to see you there.
236+
### License
252237

253-
You can get the latest news, webinar and event invites, research papers, and other ML Performance tidbits by [subscribing](https://neuralmagic.com/subscribe/) to the Neural Magic community.
238+
The project is licensed under the [Apache License Version 2.0](https://github.com/neuralmagic/sparsezoo/blob/main/LICENSE).
254239

255-
For more general questions about Neural Magic, please email us at [[email protected]](mailto:[email protected]) or fill out this [form](http://neuralmagic.com/contact/).
240+
## Community
256241

257-
## License
242+
### Contribute
258243

259-
The project is licensed under the [Apache License Version 2.0](https://github.com/neuralmagic/sparsezoo/blob/main/LICENSE).
244+
We appreciate contributions to the code, examples, integrations, and documentation as well as bug reports and feature requests! [Learn how here](https://github.com/neuralmagic/sparsezoo/blob/main/CONTRIBUTING.md).
260245

261-
## Release History
246+
### Join
262247

263-
Official builds are hosted on PyPI
248+
For user help or questions about SparseZoo, sign up or log in: **Deep Sparse Community** [Discourse Forum](https://discuss.neuralmagic.com/) and/or [Slack](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ).
249+
We are growing the community member by member and happy to see you there.
264250

265-
- stable: [sparsezoo](https://pypi.org/project/sparsezoo/)
266-
- nightly (dev): [sparsezoo-nightly](https://pypi.org/project/sparsezoo-nightly/)
251+
You can get the latest news, webinar and event invites, research papers, and other ML Performance tidbits by [subscribing](https://neuralmagic.com/subscribe/) to the Neural Magic community.
267252

268-
Additionally, more information can be found via [GitHub Releases.](https://github.com/neuralmagic/sparsezoo/releases)
253+
For more general questions about Neural Magic, please fill out this [form](http://neuralmagic.com/contact/).

docs/conf.py

+1-1
Original file line numberDiff line numberDiff line change
@@ -53,7 +53,7 @@
5353
"sphinx_markdown_tables",
5454
"sphinx_multiversion",
5555
"sphinx_rtd_theme",
56-
"recommonmark",
56+
"m2r2",
5757
]
5858

5959
# Add any paths that contain templates here, relative to this directory.

docs/index.rst

+2-88
Original file line numberDiff line numberDiff line change
@@ -13,99 +13,12 @@
1313
See the License for the specific language governing permissions and
1414
limitations under the License.
1515
16-
===================
17-
SparseZoo |version|
18-
===================
19-
20-
Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes
21-
22-
.. raw:: html
23-
24-
<div style="margin-bottom:16px;">
25-
<a href="https://github.com/neuralmagic/sparsezoo/blob/main/LICENSE">
26-
<img alt="GitHub" src="https://img.shields.io/github/license/neuralmagic/sparsezoo.svg?color=purple&style=for-the-badge" height=25 style="margin-bottom:4px;">
27-
</a>
28-
<a href="https://docs.neuralmagic.com/sparsezoo/index.html">
29-
<img alt="Documentation" src="https://img.shields.io/website/http/docs.neuralmagic.com/sparsezoo/index.html.svg?down_color=red&down_message=offline&up_message=online&style=for-the-badge" height=25 style="margin-bottom:4px;">
30-
</a>
31-
<a href="https://github.com/neuralmagic/sparsezoo/releases">
32-
<img alt="GitHub release" src="https://img.shields.io/github/release/neuralmagic/sparsezoo.svg?style=for-the-badge" height=25 style="margin-bottom:4px;">
33-
</a>
34-
<a href="https://github.com/neuralmagic/sparsezoo/blob/main/CODE_OF_CONDUCT.md">
35-
<img alt="Contributor Covenant" src="https://img.shields.io/badge/Contributor%20Covenant-v2.0%20adopted-ff69b4.svg?color=yellow&style=for-the-badge" height=25 style="margin-bottom:4px;">
36-
</a>
37-
<a href="https://www.youtube.com/channel/UCo8dO_WMGYbWCRnj_Dxr4EA">
38-
<img src="https://img.shields.io/badge/-YouTube-red?&style=for-the-badge&logo=youtube&logoColor=white" height=25 style="margin-bottom:4px;">
39-
</a>
40-
<a href="https://medium.com/limitlessai">
41-
<img src="https://img.shields.io/badge/medium-%2312100E.svg?&style=for-the-badge&logo=medium&logoColor=white" height=25 style="margin-bottom:4px;">
42-
</a>
43-
<a href="https://twitter.com/neuralmagic">
44-
<img src="https://img.shields.io/twitter/follow/neuralmagic?color=darkgreen&label=Follow&style=social" height=25 style="margin-bottom:4px;">
45-
</a>
46-
</div>
47-
48-
Overview
49-
========
50-
51-
SparseZoo is a constantly-growing repository of highly sparse and sparse-quantized models with matching sparsification recipes for neural networks.
52-
It simplifies and accelerates your time-to-value in building performant deep learning models with a collection of inference-optimized models and recipes to prototype from.
53-
54-
Available via API and hosted in the cloud, the SparseZoo contains both baseline and models optimized to different degrees of inference performance vs. baseline loss recovery.
55-
Recipe-driven approaches built around sparsification algorithms allow you to take the models as given, transfer-learn from the models onto private datasets, or transfer the recipes to your architectures.
56-
57-
`This repository <https://github.com/neuralmagic/sparsezoo>`_ contains the Python API code to handle the connection and authentication to the cloud.
58-
59-
Sparsification
60-
==============
61-
62-
Sparsification is the process of taking a trained deep learning model and removing redundant information from the overprecise and over-parameterized network resulting in a faster and smaller model.
63-
Techniques for sparsification are all encompassing including everything from inducing sparsity using `pruning <https://neuralmagic.com/blog/pruning-overview/>`_ and `quantization <https://arxiv.org/abs/1609.07061>`_ to enabling naturally occurring sparsity using `activation sparsity <http://proceedings.mlr.press/v119/kurtz20a.html>`_ or `winograd/FFT <https://arxiv.org/abs/1509.09308>`_.
64-
When implemented correctly, these techniques result in significantly more performant and smaller models with limited to no effect on the baseline metrics.
65-
For example, pruning plus quantization can give noticeable improvements in performance while recovering to nearly the same baseline accuracy.
66-
67-
The Deep Sparse product suite builds on top of sparsification enabling you to easily apply the techniques to your datasets and models using recipe-driven approaches.
68-
Recipes encode the directions for how to sparsify a model into a simple, easily editable format.
69-
70-
- Download a sparsification recipe and sparsified model from the `SparseZoo <https://github.com/neuralmagic/sparsezoo>`_.
71-
- Alternatively, create a recipe for your model using `Sparsify <https://github.com/neuralmagic/sparsify>`_.
72-
- Apply your recipe with only a few lines of code using `SparseML <https://github.com/neuralmagic/sparseml>`_.
73-
- Finally, for GPU-level performance on CPUs, deploy your sparse-quantized model with the `DeepSparse Engine <https://github.com/neuralmagic/deepsparse>`_.
74-
75-
76-
**Full Deep Sparse product flow:**
77-
78-
.. raw:: html
79-
80-
<img src="https://docs.neuralmagic.com/docs/source/sparsification/flow-overview.svg" width="960px">
81-
82-
Resources and Learning More
83-
===========================
84-
85-
- `SparseML Documentation <https://docs.neuralmagic.com/sparseml>`_
86-
- `Sparsify Documentation <https://docs.neuralmagic.com/sparsify>`_
87-
- `DeepSparse Documentation <https://docs.neuralmagic.com/deepsparse>`_
88-
- `Neural Magic Blog <https://www.neuralmagic.com/blog>`_,
89-
`Resources <https://www.neuralmagic.com/resources>`_,
90-
`Website <https://www.neuralmagic.com>`_
91-
92-
Release History
93-
===============
94-
95-
Official builds are hosted on PyPI
96-
97-
- stable: `sparsezoo <https://pypi.org/project/sparsezoo>`_
98-
- nightly (dev): `sparsezoo-nightly <https://pypi.org/project/sparsezoo-nightly>`_
99-
100-
Additionally, more information can be found via
101-
`GitHub Releases <https://github.com/neuralmagic/sparsezoo/releases>`_.
16+
.. mdinclude:: ../README.md
10217

10318
.. toctree::
10419
:maxdepth: 3
10520
:caption: General
10621

107-
source/quicktour
108-
source/installation
10922
source/models
11023
source/recipes
11124

@@ -122,5 +35,6 @@ Additionally, more information can be found via
12235
Bugs, Feature Requests <https://github.com/neuralmagic/sparsezoo/issues>
12336
Support, General Q&A Forums <https://discuss.neuralmagic.com/>
12437
Deep Sparse Community Slack <https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ>
38+
Neural Magic GitHub <https://github.com/neuralmagic>
12539
Neural Magic Docs <https://docs.neuralmagic.com>
12640

docs/source/installation.md

-28
This file was deleted.

0 commit comments

Comments
 (0)