Skip to content

Commit e02da5c

Browse files
WenjiaoYueWenjiaoYue
authored
IO docs bug fix (#188)
Signed-off-by: Yue, Wenjiao <[email protected]>
1 parent 477725e commit e02da5c

File tree

12 files changed

+275
-399
lines changed

12 files changed

+275
-399
lines changed

‎README.md‎

Lines changed: 3 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -208,7 +208,7 @@ Intel® Neural Compressor validated 420+ [examples](./examples) for quantization
208208
</tr>
209209
<tr>
210210
<td colspan="4" align="center"><a href="./docs/source/distillation_quantization.md">Distillation for Quantization</a></td>
211-
<td colspan="5" align="center"><a href="neural_coder">Neural Coder</a></td>
211+
<td colspan="5" align="center"><a href="https://github.com/intel/neural-compressor/tree/master/neural_coder">Neural Coder</a></td>
212212
</tr>
213213

214214
</tbody>
@@ -219,9 +219,8 @@ Intel® Neural Compressor validated 420+ [examples](./examples) for quantization
219219
</thead>
220220
<tbody>
221221
<tr>
222-
<td colspan="3" align="center"><a href="./docs/source/adaptor.md">Adaptor</a></td>
223-
<td colspan="3" align="center"><a href="./docs/source/tuning_strategies.md">Strategy</a></td>
224-
<td colspan="3" align="center"><a href="./docs/source/reference_examples.md">Reference Example</a></td>
222+
<td colspan="6" align="center"><a href="./docs/source/adaptor.md">Adaptor</a></td>
223+
<td colspan="6" align="center"><a href="./docs/source/tuning_strategies.md">Strategy</a></td>
225224
</tr>
226225
</tbody>
227226
</table>

‎docs/Makefile‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -19,11 +19,11 @@ help:
1919

2020
html:
2121
# cp README.md to docs, modify response-link
22-
cp -f "../README.md" "./source/getting_started.md"
22+
cp -f "../README.md" "./source/Welcome.md"
2323
cp -f "../SECURITY.md" "./source/SECURITY.md"
24-
cp -f "./source/getting_started.md" "./source/getting_started.md.tmp"
25-
sed 's/.md/.html/g; s/.\/docs\/source\//.\//g; s/.\/neural_coder\/extensions\/screenshots/imgs/g; s/.\/docs\/source\/_static/..\/\/_static/g; s/.\/examples/https:\/\/github.com\/intel\/neural-compressor\/tree\/master\/examples/g; s/.md/.html/g; ' "./source/getting_started.md.tmp" > "./source/getting_started.md"
26-
rm -f "./source/getting_started.md.tmp"
24+
cp -f "./source/Welcome.md" "./source/Welcome.md.tmp"
25+
sed 's/.md/.html/g; s/.\/docs\/source\//.\//g; s/.\/neural_coder\/extensions\/screenshots/imgs/g; s/.\/docs\/source\/_static/..\/\/_static/g; ' "./source/Welcome.md.tmp" > "./source/Welcome.md"
26+
rm -f "./source/Welcome.md.tmp"
2727

2828
# make sure other png can display normal
2929
$(SPHINXBUILD) -b html "$(SOURCEDIR)" "$(BUILDDIR)/html" $(SPHINXOPTS) $(O)

‎docs/source/SECURITY.md‎

Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
Security Policy
2+
===============
3+
4+
## Report a Vulnerability
5+
6+
Please report security issues or vulnerabilities to the [Intel® Security Center].
7+
8+
For more information on how Intel® works to resolve security issues, see
9+
[Vulnerability Handling Guidelines].
10+
11+
[Intel® Security Center]:https://www.intel.com/security
12+
13+
[Vulnerability Handling Guidelines]:https://www.intel.com/content/www/us/en/security-center/vulnerability-handling-guidelines.html

‎docs/source/Welcome.md‎

Lines changed: 249 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,249 @@
1+
<div align="center">
2+
3+
Intel® Neural Compressor
4+
===========================
5+
<h3> An open-source Python library supporting popular model compression techniques on all mainstream deep learning frameworks (TensorFlow, PyTorch, ONNX Runtime, and MXNet)</h3>
6+
7+
[![python](https://img.shields.io/badge/python-3.7%2B-blue)](https://github.com/intel/neural-compressor)
8+
[![version](https://img.shields.io/badge/release-1.14-green)](https://github.com/intel/neural-compressor/releases)
9+
[![license](https://img.shields.io/badge/license-Apache%202-blue)](https://github.com/intel/neural-compressor/blob/master/LICENSE)
10+
[![coverage](https://img.shields.io/badge/coverage-90%25-green)](https://github.com/intel/neural-compressor)
11+
[![Downloads](https://static.pepy.tech/personalized-badge/neural-compressor?period=total&units=international_system&left_color=grey&right_color=green&left_text=downloads)](https://pepy.tech/project/neural-compressor)
12+
</div>
13+
14+
---
15+
<div align="left">
16+
17+
Intel® Neural Compressor, formerly known as Intel® Low Precision Optimization Tool, is an open-source Python library that runs on Intel CPUs and GPUs, which delivers unified interfaces across multiple deep-learning frameworks for popular network compression technologies such as quantization, pruning, and knowledge distillation. This tool supports automatic accuracy-driven tuning strategies to help the user quickly find out the best quantized model. It also implements different weight-pruning algorithms to generate a pruned model with predefined sparsity goal. It also supports knowledge distillation to distill the knowledge from the teacher model to the student model.
18+
Intel® Neural Compressor is a critical AI software component in the [Intel® oneAPI AI Analytics Toolkit](https://software.intel.com/content/www/us/en/develop/tools/oneapi/ai-analytics-toolkit.html).
19+
20+
21+
**Visit the Intel® Neural Compressor online document website at: <https://intel.github.io/neural-compressor>.**
22+
23+
## Installation
24+
25+
### Prerequisites
26+
27+
Python version: 3.7, 3.8, 3.9, 3.10
28+
29+
### Install on Linux
30+
- Release binary install
31+
```Shell
32+
# install stable basic version from pip
33+
pip install neural-compressor
34+
# Or install stable full version from pip (including GUI)
35+
pip install neural-compressor-full
36+
```
37+
- Nightly binary install
38+
```Shell
39+
git clone https://github.com/intel/neural-compressor.git
40+
cd neural-compressor
41+
pip install -r requirements.txt
42+
# install nightly basic version from pip
43+
pip install -i https://test.pypi.org/simple/ neural-compressor
44+
# Or install nightly full version from pip (including GUI)
45+
pip install -i https://test.pypi.org/simple/ neural-compressor-full
46+
```
47+
More installation methods can be found at [Installation Guide](./installation_guide.html). Please check out our [FAQ](./faq.html) for more details.
48+
49+
## Getting Started
50+
### Quantization with Python API
51+
52+
```shell
53+
# A TensorFlow Example
54+
pip install tensorflow
55+
# Prepare fp32 model
56+
wget https://storage.googleapis.com/intel-optimized-tensorflow/models/v1_6/mobilenet_v1_1.0_224_frozen.pb
57+
```
58+
```python
59+
import tensorflow as tf
60+
from neural_compressor.experimental import Quantization, common
61+
quantizer = Quantization()
62+
quantizer.model = './mobilenet_v1_1.0_224_frozen.pb'
63+
dataset = quantizer.dataset('dummy', shape=(1, 224, 224, 3))
64+
quantizer.calib_dataloader = common.DataLoader(dataset)
65+
quantizer.fit()
66+
```
67+
### Quantization with [JupyterLab Extension](./neural_coder/extensions/neural_compressor_ext_lab/README.html)
68+
Search for ```jupyter-lab-neural-compressor``` in the Extension Manager in JupyterLab and install with one click:
69+
70+
<a target="_blank" href="imgs/extmanager.png">
71+
<img src="imgs/extmanager.png" alt="Extension" width="35%" height="35%">
72+
</a>
73+
74+
### Quantization with [GUI](./bench.html)
75+
```shell
76+
# An ONNX Example
77+
pip install onnx==1.12.0 onnxruntime==1.12.1 onnxruntime-extensions
78+
# Prepare fp32 model
79+
wget https://github.com/onnx/models/raw/main/vision/classification/resnet/model/resnet50-v1-12.onnx
80+
# Start GUI
81+
inc_bench
82+
```
83+
<a target="_blank" href="./_static/imgs/INC_GUI.gif">
84+
<img src="./_static/imgs/INC_GUI.gif" alt="Architecture">
85+
</a>
86+
87+
## System Requirements
88+
89+
### Validated Hardware Environment
90+
#### Intel® Neural Compressor supports CPUs based on [Intel 64 architecture or compatible processors](https://en.wikipedia.org/wiki/X86-64):
91+
92+
* Intel Xeon Scalable processor (formerly Skylake, Cascade Lake, Cooper Lake, and Icelake)
93+
* Future Intel Xeon Scalable processor (code name Sapphire Rapids)
94+
95+
#### Intel® Neural Compressor supports GPUs built on Intel's Xe architecture:
96+
97+
* [Intel® Data Center GPU Flex Series](https://www.intel.com/content/www/us/en/products/docs/discrete-gpus/data-center-gpu/flex-series/overview.html)
98+
99+
#### Intel® Neural Compressor quantized ONNX models support multiple hardware vendors through ONNX Runtime:
100+
101+
* Intel CPU, AMD/ARM CPU, and NVidia GPU. Please refer to the validated model [list](./validated_model_list.html#Validated-ONNX-QDQ-INT8-models-on-multiple-hardware-through-ONNX-Runtime).
102+
103+
### Validated Software Environment
104+
105+
* OS version: CentOS 8.4, Ubuntu 20.04
106+
* Python version: 3.7, 3.8, 3.9, 3.10
107+
108+
<table class="docutils">
109+
<thead>
110+
<tr>
111+
<th>Framework</th>
112+
<th>TensorFlow</th>
113+
<th>Intel TensorFlow</th>
114+
<th>PyTorch</th>
115+
<th>Intel® Extension for PyTorch*</th>
116+
<th>ONNX Runtime</th>
117+
<th>MXNet</th>
118+
</tr>
119+
</thead>
120+
<tbody>
121+
<tr align="center">
122+
<th>Version</th>
123+
<td class="tg-7zrl"><a href=https://github.com/tensorflow/tensorflow/tree/v2.10.0>2.10.0</a><br>
124+
<a href=https://github.com/tensorflow/tensorflow/tree/v2.9.1>2.9.1</a><br>
125+
<a href=https://github.com/tensorflow/tensorflow/tree/v2.8.2>2.8.2</a><br>
126+
<td class="tg-7zrl"><a href=https://github.com/Intel-tensorflow/tensorflow/tree/v2.10.0>2.10.0</a><br>
127+
<a href=https://github.com/Intel-tensorflow/tensorflow/tree/v2.9.1>2.9.1</a><br>
128+
<a href=https://github.com/Intel-tensorflow/tensorflow/tree/v2.8.0>2.8.0</a><br>
129+
<td class="tg-7zrl"><a href=https://download.pytorch.org/whl/torch_stable.html>1.12.1+cpu</a><br>
130+
<a href=https://download.pytorch.org/whl/torch_stable.html>1.11.0+cpu</a><br>
131+
<a href=https://download.pytorch.org/whl/torch_stable.html>1.10.0+cpu</a></td>
132+
<td class="tg-7zrl"><a href=https://github.com/intel/intel-extension-for-pytorch/tree/v1.12.0>1.12.0</a><br>
133+
<a href=https://github.com/intel/intel-extension-for-pytorch/tree/1.11.0>1.11.0</a><br>
134+
<a href=https://github.com/intel/intel-extension-for-pytorch/tree/v1.10.0>1.10.0</a></td>
135+
<td class="tg-7zrl"><a href=https://github.com/microsoft/onnxruntime/tree/v1.12.1>1.12.1</a><br>
136+
<a href=https://github.com/microsoft/onnxruntime/tree/v1.11.0>1.11.0</a><br>
137+
<a href=https://github.com/microsoft/onnxruntime/tree/v1.10.0>1.10.0</a></td>
138+
<td class="tg-7zrl"><a href=https://github.com/apache/incubator-mxnet/tree/1.8.0>1.8.0</a><br>
139+
<a href=https://github.com/apache/incubator-mxnet/tree/1.7.0>1.7.0</a><br>
140+
<a href=https://github.com/apache/incubator-mxnet/tree/1.6.0>1.6.0</a></td>
141+
</tr>
142+
</tbody>
143+
</table>
144+
145+
> **Note:**
146+
> Set the environment variable ``TF_ENABLE_ONEDNN_OPTS=1`` to enable oneDNN optimizations if you are using TensorFlow v2.6 to v2.8. oneDNN is the default for TensorFlow v2.9.
147+
148+
### Validated Models
149+
Intel® Neural Compressor validated 420+ [examples](./examples) for quantization with a performance speedup geomean of 2.2x and up to 4.2x on VNNI while minimizing accuracy loss. Over 30 pruning and knowledge distillation samples are also available. More details for validated models are available [here](./validated_model_list.html).
150+
151+
<div style = "width: 77%; margin-bottom: 2%;">
152+
<a target="_blank" href="./_static/imgs/release_data.png">
153+
<img src="./_static/imgs/release_data.png" alt="Architecture" width=800 height=500>
154+
</a>
155+
</div>
156+
157+
## Documentation
158+
159+
<table class="docutils">
160+
<thead>
161+
<tr>
162+
<th colspan="9">Overview</th>
163+
</tr>
164+
</thead>
165+
<tbody>
166+
<tr>
167+
<td colspan="3" align="center"><a href="./design.html">Architecture</a></td>
168+
<td colspan="2" align="center"><a href="https://github.com/intel/neural-compressor/tree/master/examples">Examples</a></td>
169+
<td colspan="2" align="center"><a href="./bench.html">GUI</a></td>
170+
<td colspan="2" align="center"><a href="https://intel.github.io/neural-compressor/api-documentation/apis.html">APIs</a></td>
171+
</tr>
172+
<tr>
173+
<td colspan="5" align="center"><a href="https://software.intel.com/content/www/us/en/develop/documentation/get-started-with-ai-linux/top.html">Intel oneAPI AI Analytics Toolkit</a></td>
174+
<td colspan="4" align="center"><a href="https://github.com/oneapi-src/oneAPI-samples/tree/master/AI-and-Analytics">AI and Analytics Samples</a></td>
175+
</tr>
176+
</tbody>
177+
<thead>
178+
<tr>
179+
<th colspan="9">Basic API</th>
180+
</tr>
181+
</thead>
182+
<tbody>
183+
<tr>
184+
<td colspan="2" align="center"><a href="./transform.html">Transform</a></td>
185+
<td colspan="2" align="center"><a href="./dataset.html">Dataset</a></td>
186+
<td colspan="2" align="center"><a href="./metric.html">Metric</a></td>
187+
<td colspan="3" align="center"><a href="./objective.html">Objective</a></td>
188+
</tr>
189+
</tbody>
190+
<thead>
191+
<tr>
192+
<th colspan="9">Deep Dive</th>
193+
</tr>
194+
</thead>
195+
<tbody>
196+
<tr>
197+
<td colspan="2" align="center"><a href="./quantization.html">Quantization</a></td>
198+
<td colspan="1" align="center"><a href="./pruning.html">Pruning(Sparsity)</a></td>
199+
<td colspan="2" align="center"><a href="./distillation.html">Knowledge Distillation</a></td>
200+
<td colspan="2" align="center"><a href="./mixed_precision.html">Mixed Precision</a></td>
201+
<td colspan="2" align="center"><a href="./orchestration.html">Orchestration</a></td>
202+
</tr>
203+
<tr>
204+
<td colspan="2" align="center"><a href="./benchmark.html">Benchmarking</a></td>
205+
<td colspan="3" align="center"><a href="./distributed.html">Distributed Training</a></td>
206+
<td colspan="2" align="center"><a href="./model_conversion.html">Model Conversion</a></td>
207+
<td colspan="2" align="center"><a href="./tensorboard.html">TensorBoard</a></td>
208+
</tr>
209+
<tr>
210+
<td colspan="4" align="center"><a href="./distillation_quantization.html">Distillation for Quantization</a></td>
211+
<td colspan="5" align="center"><a href="https://github.com/intel/neural-compressor/tree/master/neural_coder">Neural Coder</a></td>
212+
</tr>
213+
214+
</tbody>
215+
<thead>
216+
<tr>
217+
<th colspan="9">Advanced Topics</th>
218+
</tr>
219+
</thead>
220+
<tbody>
221+
<tr>
222+
<td colspan="6" align="center"><a href="./adaptor.html">Adaptor</a></td>
223+
<td colspan="6" align="center"><a href="./tuning_strategies.html">Strategy</a></td>
224+
</tr>
225+
</tbody>
226+
</table>
227+
228+
## Selected Publications/Events
229+
* [Neural Compressor: an open-source Python library for network compression](https://cloud.tencent.com/developer/article/2165895) (Nov 2022)
230+
* [Running Fast Transformers on CPUs: Intel Approach Achieves Significant Speed Ups and SOTA Performance](https://medium.com/syncedreview/running-fast-transformers-on-cpus-intel-approach-achieves-significant-speed-ups-and-sota-448521704c5e) (Nov 2022)
231+
* [Personalized Stable Diffusion with Few-Shot Fine-Tuning](https://medium.com/intel-analytics-software/personalized-stable-diffusion-with-few-shot-fine-tuning-on-a-single-cpu-f01a3316b13) (Nov 2022)
232+
* [Meet the Innovation of Intel AI Software: Intel® Extension for TensorFlow*](https://www.intel.com/content/www/us/en/developer/articles/technical/innovation-of-ai-software-extension-tensorflow.html) (Oct 2022)
233+
* [PyTorch* Inference Acceleration with Intel® Neural Compressor](https://www.intel.com/content/www/us/en/developer/articles/technical/pytorch-inference-with-intel-neural-compressor.html#gs.gnq0cj) (Oct 2022)
234+
* Neural Coder, a new plug-in for Intel Neural Compressor was covered by [Twitter](https://twitter.com/IntelDevTools/status/1583629213697212416), [LinkedIn](https://www.linkedin.com/posts/intel-software_oneapi-ai-deeplearning-activity-6989377309917007872-Dbzg?utm_source=share&utm_medium=member_desktop), and [Intel Developer Zone](https://mp.weixin.qq.com/s/LL-4eD-R0YagFgODM23oQA) from Intel, and [Twitter](https://twitter.com/IntelDevTools/status/1583629213697212416/retweets) and [LinkedIn](https://www.linkedin.com/feed/update/urn:li:share:6990377841435574272/) from Hugging Face. (Oct 2022)
235+
* Intel Neural Compressor successfully landed on [GCP](https://console.cloud.google.com/marketplace/product/bitnami-launchpad/inc-tensorflow-intel?project=verdant-sensor-286207), [AWS](https://aws.amazon.com/marketplace/pp/prodview-yjyh2xmggbmga#pdp-support), and [Azure](https://azuremarketplace.microsoft.com/en-us/marketplace/apps/bitnami.inc-tensorflow-intel) marketplace. (Oct 2022)
236+
237+
> View our [full publication list](./publication_list.html).
238+
239+
## Additional Content
240+
241+
* [Release Information](./releases_info.html)
242+
* [Contribution Guidelines](./contributions.html)
243+
* [Legal Information](./legal_information.html)
244+
* [Security Policy](SECURITY.html)
245+
* [Intel® Neural Compressor Website](https://intel.github.io/neural-compressor)
246+
247+
## Hiring
248+
249+
We are actively hiring. Send your resume to [email protected] if you are interested in model compression techniques.

‎docs/source/_static/index.html‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
<meta http-equiv="refresh" content="0; URL='getting_started.html'" />
1+
<meta http-equiv="refresh" content="0; URL='Welcome.html'" />

‎docs/source/_templates/layout.html‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@
77
<div class="container">
88
<div class="header-container">
99
<div class="navbar-logo">
10-
<a href="https://intel.github.io/neural-compressor/README.html" alt="Intel homepage" class="intel-logo-rebrand">
10+
<a href="https://intel.github.io/neural-compressor/Welcome.html" alt="Intel homepage" class="intel-logo-rebrand">
1111
<span class="headTitleStyle"> Intel® Neural Compressor</span>
1212
</a>
1313
</div>

0 commit comments

Comments
 (0)