The DL Streamer Pipeline Zoo is a catalog of optimized media and media analytics pipelines.

Last update: Dec 04, 2022

Related tags

Overview

Intel(R) Deep Learning Streamer Pipeline Zoo

The DL Streamer Pipeline Zoo is a catalog of media and media analytics pipelines optimized for Intel hardware. It includes tools for downloading pipelines and their dependencies and tools for measuring their performace.

Pipelines are organized according to the task they perform (what types of input they accept and what types of output they generate). Tasks and pipelines are defined in a platform and framework independent way to allow implementations in a variety of frameworks and for multiple platform targets.

Features Include:


Simple command line interface	A single entrypoint for downloading and running media analytics pipelines along with media and model dependencies
DL Streamer Pipeline Runner	Pipeline implementations and optimizations using the DL Streamer Pipeline Framework
Platform specific settings	Pipeline runner settings tuned for optimal performance on different platform types (e.g. core, xeon)
Measurement Settings	Settings for measuring different scenarios including single stream throughput and stream density. Settings can be customized and saved for reuse.
Containerized environment	Dockerfiles, build and run scripts for launching a reproducable environment

IMPORTANT:

The DL Streamer Pipeline Zoo is provided as a set of tools for system evaluation and benchmarking and is not intended for deployment into production environments without modification.

The project is pre-production and under active development. Please expect breaking changes and use tagged versions for stable functionality.

Getting Started

Prerequisites


Docker	The Pipeline Zoo requires Docker for it's build, development, and runtime environments. Please install the latest version for your platform.
bash	The Pipeline Zoo build and run scripts require bash and have been tested on systems using versions greater than or equal to: `GNU bash, version 4.3.48(1)-release (x86_64-pc-linux-gnu)`.

Installation

Clone Repository

git clone https://github.com/dlstreamer/pipeline-zoo.git pipeline-zoo

Build Pipeline Zoo Environment

./pipeline-zoo/tools/docker/build.sh

Output:

Successfully built 113352079483
Successfully tagged media-analytics-pipeline-zoo-bench:latest

Launch Pipeline Zoo
```
./pipeline-zoo/tools/docker/run.sh 
```

Pipline Zoo Commands

List Pipelines

Command:

pipebench list

Output:

+--------------------------------------------+-----------------------+----------------------------+------------+
| Pipeline                                   | Task                  | Models                     | Runners    |
+============================================+=======================+============================+============+
| decode-h265                                | decode-vpp            |                            | dlstreamer |
|                                            |                       |                            | mockrun    |
+--------------------------------------------+-----------------------+----------------------------+------------+
| decode-h264-bgra                           | decode-vpp            |                            | dlstreamer |
|                                            |                       |                            | mockrun    |
+--------------------------------------------+-----------------------+----------------------------+------------+
| od-h265-ssd-mobilenet-v1-coco              | object-detection      | ssd_mobilenet_v1_coco_INT8 | dlstreamer |
+--------------------------------------------+-----------------------+----------------------------+------------+
| od-h264-ssd-mobilenet-v1-coco              | object-detection      | ssd_mobilenet_v1_coco      | dlstreamer |
|                                            |                       |                            | mockrun    |
+--------------------------------------------+-----------------------+----------------------------+------------+
| oc-h265-full_frame-resnet-50-tf            | object-classification | full_frame                 | dlstreamer |
|                                            |                       | resnet-50-tf               | mockrun    |
+--------------------------------------------+-----------------------+----------------------------+------------+
| oc-h264-full_frame-resnet-50-tf            | object-classification | full_frame                 | dlstreamer |
|                                            |                       | resnet-50-tf               | mockrun    |
+--------------------------------------------+-----------------------+----------------------------+------------+
| oc-h264-ssd-mobilenet-v1-coco-resnet-50-tf | object-classification | ssd_mobilenet_v1_coco      | dlstreamer |
|                                            |                       | resnet-50-tf               | mockrun    |
+--------------------------------------------+-----------------------+----------------------------+------------+
| oc-h265-ssd-mobilenet-v1-coco-resnet-50-tf | object-classification | ssd_mobilenet_v1_coco      | dlstreamer |
|                                            |                       | resnet-50-tf               | mockrun    |
+--------------------------------------------+-----------------------+----------------------------+------------+

Download Pipeline

Command:

pipebench download od-h264-ssd-mobilenet-v1-coco

Example Output Tree:

- pipeline-zoo/
+ doc/
+ media/
+ models/
+ pipelines/
+ runners/
+ tools/
- workspace/
 - od-h264-ssd-mobilenet-v1-coco/
   - media/
     - video/
       + Pexels-Videos-1388365/
       + person-bicycle-car-detection/
   - models/
     - ssd_mobilenet_v1_coco/
       + FP16/
       + FP32/
       + ssd_mobilenet_v1_coco_2018_01_28/
     - ssd_mobilenet_v1_coco_INT8/
       + FP16-INT8/
   - runners/
     + dlstreamer/
     + mockrun/
   README.md
   dlstreamer.core.runner-settings.yml
   dlstreamer.density.core.runner-settings.yml
   dlstreamer.density.dgpu.runner-settings.yml
   dlstreamer.density.runner-settings.yml
   dlstreamer.density.xeon.runner-settings.yml
   dlstreamer.dgpu.runner-settings.yml
   dlstreamer.runner-settings.yml
   dlstreamer.xeon.runner-settings.yml
   media.list.yml
   mockrun.runner-settings.yml
   models.list.yml
   od-h264-ssd-mobilenet-v1-coco.pipeline.yml

Measure Single Stream Throughput

Command:

pipebench run od-h264-ssd-mobilenet-v1-coco

Example Output:

 Pipeline:
	od-h264-ssd-mobilenet-v1-coco

 Runner:
	dlstreamer
 	dlstreamer.runner-settings.yml

 Media:
	video/person-bicycle-car-detection

 Measurement:
	throughput
 	throughput.measurement-settings.yml

 Output Directory:
	/home/pipeline-zoo/workspace/od-h264-ssd-mobilenet-v1-coco/measurements/throughput/dlstreamer/run-0000

========================================================================
Iteration   Streams  Processes    Minimum   Average   Maximum      Total
========================================================================
     0000      0000       0001     0.0000    0.0000    0.0000     0.0000
======================================================================== 

========================================================================
Iteration   Streams  Processes    Minimum   Average   Maximum      Total
========================================================================
     0000      0001       0001   130.3469  130.3469  130.3469   130.3469
======================================================================== 

========================================================================
Iteration   Streams  Processes    Minimum   Average   Maximum      Total
========================================================================
     0000      0001       0001   128.9403  128.9403  128.9403   128.9403
======================================================================== 

========================================================================
Iteration   Streams  Processes    Minimum   Average   Maximum      Total
========================================================================
     0000      0001       0001   129.5578  129.5578  129.5578   129.5578
======================================================================== 

...

   
    
...

========================================================================
Iteration   Streams  Processes    Minimum   Average   Maximum      Total
========================================================================
     0000      0001       0001   126.2640  126.2640  126.2640   126.2640
======================================================================== 

========================================================================
Iteration   Streams  Processes    Minimum   Average   Maximum      Total
========================================================================
     0000      0001       0001   125.8236  125.8236  125.8236   125.8236
======================================================================== 

Pipeline                       Runner      Streams: 1
-----------------------------  ----------  ---------------------------------------------------------
od-h264-ssd-mobilenet-v1-coco  dlstreamer  Min: 125.8236 Max: 125.8236 Avg: 125.8236 Total: 125.8236

Measure Stream Density

Command:

 pipebench run --measure density od-h264-ssd-mobilenet-v1-coco

Example Output:

 Pipeline:
	od-h264-ssd-mobilenet-v1-coco

 Runner:
	dlstreamer
 	dlstreamer.density.runner-settings.yml

 Media:
	video/person-bicycle-car-detection

 Measurement:
	density
 	density.measurement-settings.yml

 Output Directory:
	/home/pipeline-zoo/workspace/od-h264-ssd-mobilenet-v1-coco/measurements/density/dlstreamer/run-0000

========================================================================
Iteration   Streams  Processes    Minimum   Average   Maximum      Total
========================================================================
      PRE      0001       0001   121.7170  121.7170  121.7170   121.7170
======================================================================== 

========================================================================
Iteration   Streams  Processes    Minimum   Average   Maximum      Total
========================================================================
      PRE      0001       0001   128.3342  128.3342  128.3342   128.3342
======================================================================== 

...

   
    
...

========================================================================
Iteration   Streams  Processes    Minimum   Average   Maximum      Total
========================================================================
     0001      0003       0003    30.0000   30.0038   30.0110    90.0115
======================================================================== 

========================================================================
Iteration   Streams  Processes    Minimum   Average   Maximum      Total
========================================================================
     0001      0003       0003    29.9868   29.9959   30.0115    89.9878
======================================================================== 

Pipeline                       Runner      Streams: 4                                              Streams: 3
-----------------------------  ----------  ------------------------------------------------------  -----------------------------------------------------
od-h264-ssd-mobilenet-v1-coco  dlstreamer  Min: 28.4167 Max: 28.5507 Avg: 28.4844 Total: 113.9374  Min: 29.9868 Max: 30.0115 Avg: 29.9959 Total: 89.9878

You might also like...

A machine learning library for spiking neural networks. Supports training with both torch and jax pipelines, and deployment to neuromorphic hardware.

Rockpool Rockpool is a Python package for developing signal processing applications with spiking neural networks. Rockpool allows you to build network

21 Dec 14, 2022

MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

4.7k Dec 29, 2022

Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.

Adversarial Training Against Location-Optimized Adversarial Patches arXiv | Paper | Code | Video | Slides Code for the paper: Sukrut Rao, David Stutz,

32 Dec 13, 2022

Official Pytorch implementation of 'GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network' (NeurIPS 2020)

Official implementation of GOCor This is the official implementation of our paper : GOCor: Bringing Globally Optimized Correspondence Volumes into You

71 Nov 18, 2022

Use AI to generate a optimized stock portfolio

Use AI, Modern Portfolio Theory, and Monte Carlo simulation's to generate a optimized stock portfolio that minimizes risk while maximizing returns. Ho

30 Dec 22, 2022

In-Place Activated BatchNorm for Memory-Optimized Training of DNNs

In-Place Activated BatchNorm In-Place Activated BatchNorm for Memory-Optimized Training of DNNs In-Place Activated BatchNorm (InPlace-ABN) is a novel

1.3k Dec 29, 2022

Optimized code based on M2 for faster image captioning training

Transformer Captioning This repository contains the code for Transformer-based image captioning. Based on meshed-memory-transformer, we further optimi

16 Dec 16, 2022

Supervised Contrastive Learning for Downstream Optimized Sequence Representations

SupCL-Seq 📖 Supervised Contrastive Learning for Downstream Optimized Sequence representations (SupCS-Seq) accepted to be published in EMNLP 2021, ext

18 Oct 21, 2022

Tutel MoE: An Optimized Mixture-of-Experts Implementation

Project Tutel Tutel MoE: An Optimized Mixture-of-Experts Implementation. Supported Framework: Pytorch Supported GPUs: CUDA(fp32 + fp16), ROCm(fp32) Ho

344 Dec 29, 2022

Comments

Bump protobuf from 3.19.4 to 3.19.5 in /tools/pipebench
Bumps protobuf from 3.19.4 to 3.19.5.

Release notes

Sourced from protobuf's releases.

Protocol Buffers v3.19.5

C++

Reduce memory consumption of MessageSet parsing

This release addresses a Security Advisory for C++ and Python users

Commits

b464cfb Updating changelog

40859fb Updating version.json and repo version numbers to: 19.5

3b175f1 Merge pull request #10543 from deannagarcia/3.19.x

c05b5f3 Add missing includes

0299c03 Apply patch

0a722f1 Update version.json with "lts": true (#10533)

d5eb60a Merge pull request #10530 from protocolbuffers/deannagarcia-patch-6

6cf1f78 Update version.json

97fc844 Merge pull request #10504 from deannagarcia/3.19.x

29d60a2 Add version file

Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

@dependabot rebase will rebase this PR

@dependabot recreate will recreate this PR, overwriting any edits that have been made to it

@dependabot merge will merge this PR after your CI passes on it

@dependabot squash and merge will squash and merge this PR after your CI passes on it

@dependabot cancel merge will cancel a previously requested merge and block automerging

@dependabot reopen will reopen this PR if it is closed

@dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually

@dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

@dependabot use these labels will set the current labels as the default for future PRs for this repo and language

@dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language

@dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language

@dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

You can disable automated security fix PRs for this repo from the Security Alerts page.

dependencies
opened by dependabot[bot] 0

Releases(v0.0.7)

v0.0.7(Jul 15, 2022)
Intel® Deep Learning Streamer (Intel® DL Streamer) Pipeline Zoo

The Intel® DL Streamer Pipeline Zoo is a catalog of media and media analytics pipelines optimized for Intel® hardware. It includes tools for downloading pipelines and their dependencies and tools for measuring their performance.

Pipelines are organized according to the task they perform (what types of input they accept and what types of output they generate). Tasks and pipelines are defined in a platform and framework independent way to allow implementations in a variety of frameworks and for multiple platform targets.

IMPORTANT:
The Intel® DL Streamer Pipeline Zoo is provided as a set of tools for system evaluation and benchmarking and is not intended for deployment into production environments without modification.
The project is pre-production and under active development. Please expect breaking changes and use tagged versions for stable functionality.

For the details of supported platforms, please refer to System Requirements section.

New in this Release

| Title | High-level description | |----------------|---------------------------------| | Alignment with Intel® DL Streamer Pipeline Framework 2022.1 | Pipeline Zoo now uses the 2022.1 image of Intel® DL Streamer Pipeline Framework as its base image | | Compatibility with OpenVINO™ Toolkit 2022.1 | Pipeline Zoo has been updated to use the 2022.1 version of the OpenVINO™ Toolkit | | New models added | New object detection and object classification pipelines were added. These are based on the following models:
* yolov4
* efficient-b0
* ssdlite-mobilenet-v2
| | Platform support updates | Pipeline Zoo has added full support for Alder Lake and Tiger Lake platforms | | Improved Benchmarking | Time to compute stream density on high density cores was significantly reduced |

Changed in this Release

Naming aligned with Intel® DL Streamer product version

Full Changelog: https://github.com/dlstreamer/pipeline-zoo/compare/v0.0.6...v0.0.7

System Requirements

Please refer to Intel® DL Streamer documentation.

Legal Information

No license (express or implied, by estoppel or otherwise) to any intellectual property rights is granted by this document.

Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

This document contains information on products, services and/or processes in development. All information provided here is subject to change without notice. Contact your Intel representative to obtain the latest forecast, schedule, specifications and roadmaps.

The products and services described may contain defects or errors which may cause deviations from published specifications. Current characterized errata are available on request.

Intel and the Intel logo are trademarks of Intel Corporation in the U.S. and/or other countries.

*Other names and brands may be claimed as the property of others.

© 2022 Intel Corporation.
Source code(tar.gz)
Source code(zip)
v0.0.6(Jan 25, 2022)
Intel(R) Deep Learning Streamer Pipeline Zoo

The DL Streamer Pipeline Zoo is a catalog of media and media analytics pipelines optimized for Intel hardware. It includes tools for downloading pipelines and their dependencies and tools for measuring their performace.

Pipelines are organized according to the task they perform (what types of input they accept and what types of output they generate). Tasks and pipelines are defined in a platform and framework independent way to allow implementations in a variety of frameworks and for multiple platform targets.

IMPORTANT:
The DL Streamer Pipeline Zoo is provided as a set of tools for system evaluation and benchmarking and is not intended for deployment into production environments without modification.
The project is pre-production and under active development. Please expect breaking changes and use tagged versions for stable functionality.

Features Include:

| -- | -- Simple command line interface | A single entrypoint for downloading and running media analytics pipelines along with media and model dependencies DL Streamer Pipeline Runner | Pipeline implementations and optimizations using the DL Streamer Pipeline Framework Platform specific settings | Pipeline runner settings tuned for optimal performance on different platform types (e.g. core, xeon) Measurement Settings | Settings for measuring different scenarios including single stream throughput and stream density. Settings can be customized and saved for reuse. Containerized environment | Dockerfiles, build and run scripts for launching a reproducable environment

Release v0.0.6

This release contains minor bug fixes and enhancements:

duration expands number of frames in media beyond 60 seconds if given (calculated at 30 fps)

added dog_bark media for object classification

What's Changed

Public staging by @nnshah1 in https://github.com/dlstreamer/pipeline-zoo/pull/1

New Contributors

@nnshah1 made their first contribution in https://github.com/dlstreamer/pipeline-zoo/pull/1

Full Changelog: https://github.com/dlstreamer/pipeline-zoo/compare/v0.0.5...v0.0.6
Source code(tar.gz)
Source code(zip)
v0.0.5(Dec 24, 2021)
Intel(R) Deep Learning Streamer Pipeline Zoo

The DL Streamer Pipeline Zoo is a catalog of media and media analytics pipelines optimized for Intel hardware. It includes tools for downloading pipelines and their dependencies and tools for measuring their performace.

Pipelines are organized according to the task they perform (what types of input they accept and what types of output they generate). Tasks and pipelines are defined in a platform and framework independent way to allow implementations in a variety of frameworks and for multiple platform targets.

IMPORTANT:
The DL Streamer Pipeline Zoo is provided as a set of tools for system evaluation and benchmarking and is not intended for deployment into production environments without modification.
The project is pre-production and under active development. Please expect breaking changes and use tagged versions for stable functionality.

Features Include:

| -- | -- Simple command line interface | A single entrypoint for downloading and running media analytics pipelines along with media and model dependencies DL Streamer Pipeline Runner | Pipeline implementations and optimizations using the DL Streamer Pipeline Framework Platform specific settings | Pipeline runner settings tuned for optimal performance on different platform types (e.g. core, xeon) Measurement Settings | Settings for measuring different scenarios including single stream throughput and stream density. Settings can be customized and saved for reuse. Containerized environment | Dockerfiles, build and run scripts for launching a reproducable environment

Initial Preview Release (v0.0.5)

The initial release contains support for the following tasks and pipelines using a DL Streamer Pipeline Runner:

Object Detection

od-h264-ssd-mobilenet-v1-coco

od-h265-ssd-mobilenet-v1-coco

Object Classification

oc-h264-full-frame-resnet-50-tf

oc-h265-full-frame-resnet-50-tf

oc-h264-ssd-mobilenet-v1-coco-resnet-50-tf -oc-h265-ssd-mobilenet-v1-coco-resnet-50-tf

Decode VPP

decode-h265

decode-h264-bgra

And provides settings tuned for performance on:

Xeon: Intel(R) Xeon(R) Gold 6336Y CPU @ 2.40GHz.

Core: 11th Gen Intel(R) Core(TM) i7-1185G7 @ 3.00GH

Source code(tar.gz)
Source code(zip)

Owner

GitHub Repository

A project to build an AI voice assistant using Python . The Voice assistant interacts with the humans to perform basic tasks.

AI_Personal_Voice_Assistant_Using_Python A project to build an AI voice assistant using Python . The Voice assistant interacts with the humans to perf

1 Oct 30, 2021

(Py)TOD: Tensor-based Outlier Detection, A General GPU-Accelerated Framework

(Py)TOD: Tensor-based Outlier Detection, A General GPU-Accelerated Framework Background: Outlier detection (OD) is a key data mining task for identify

127 Jan 05, 2023

BMN: Boundary-Matching Network

BMN: Boundary-Matching Network A pytorch-version implementation codes of paper: "BMN: Boundary-Matching Network for Temporal Action Proposal Generatio

260 Dec 06, 2022

ALFRED - A Benchmark for Interpreting Grounded Instructions for Everyday Tasks

ALFRED A Benchmark for Interpreting Grounded Instructions for Everyday Tasks Mohit Shridhar, Jesse Thomason, Daniel Gordon, Yonatan Bisk, Winson Han,

204 Dec 15, 2022

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

4.8k Jan 07, 2023

pytorch bert intent classification and slot filling

pytorch_bert_intent_classification_and_slot_filling 基于pytorch的中文意图识别和槽位填充说明基本思路就是：分类+序列标注（命名实体识别）同时训练。使用的预训练模型：hugging face上的chinese-bert-wwm-ext 依

33 Dec 15, 2022

StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation

StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation Demo video: CVPR 2021 Oral: Single Channel Manipulation: Localized or attribu

267 Dec 30, 2022

"NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search".

NAS-Bench-301 This repository containts code for the paper: "NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search". The

57 Nov 30, 2022

Unofficial PyTorch implementation of Neural Additive Models (NAM) by Agarwal, et al.

nam-pytorch Unofficial PyTorch implementation of Neural Additive Models (NAM) by Agarwal, et al. [abs, pdf] Installation You can access nam-pytorch vi

11 Mar 14, 2022

The official TensorFlow implementation of the paper Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition

Action Transformer A Self-Attention Model for Short-Time Human Action Recognition This repository contains the official TensorFlow implementation of t

20 Jan 03, 2023

A library for performing coverage guided fuzzing of neural networks

TensorFuzz: Coverage Guided Fuzzing for Neural Networks This repository contains a library for performing coverage guided fuzzing of neural networks,

195 Dec 28, 2022

This thesis is mainly concerned with state-space methods for a class of deep Gaussian process (DGP) regression problems

Doctoral dissertation of Zheng Zhao This thesis is mainly concerned with state-space methods for a class of deep Gaussian process (DGP) regression pro

21 Nov 14, 2022

A Python Package For System Identification Using NARMAX Models

SysIdentPy is a Python module for System Identification using NARMAX models built on top of numpy and is distributed under the 3-Clause BSD license. N

175 Dec 25, 2022

An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

Speech Resynthesis from Discrete Disentangled Self-Supervised Representations Implementation of the method described in the Speech Resynthesis from Di

253 Jan 06, 2023

The DL Streamer Pipeline Zoo is a catalog of optimized media and media analytics pipelines.

Related tags

Overview

Intel(R) Deep Learning Streamer Pipeline Zoo

Features Include:

Getting Started

Prerequisites

Installation

Pipline Zoo Commands

List Pipelines

Download Pipeline

Measure Single Stream Throughput

Measure Stream Density

You might also like...

A machine learning library for spiking neural networks. Supports training with both torch and jax pipelines, and deployment to neuromorphic hardware.

MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.

Official Pytorch implementation of 'GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network' (NeurIPS 2020)

Use AI to generate a optimized stock portfolio

In-Place Activated BatchNorm for Memory-Optimized Training of DNNs

Optimized code based on M2 for faster image captioning training

Supervised Contrastive Learning for Downstream Optimized Sequence Representations

Tutel MoE: An Optimized Mixture-of-Experts Implementation

Comments

Bump protobuf from 3.19.4 to 3.19.5 in /tools/pipebench

Protocol Buffers v3.19.5

C++

Releases(v0.0.7)

v0.0.7(Jul 15, 2022)

Intel® Deep Learning Streamer (Intel® DL Streamer) Pipeline Zoo

For the details of supported platforms, please refer to System Requirements section.

New in this Release

Changed in this Release

System Requirements

Legal Information

v0.0.6(Jan 25, 2022)

Intel(R) Deep Learning Streamer Pipeline Zoo

Features Include:

Release v0.0.6

What's Changed

New Contributors

v0.0.5(Dec 24, 2021)

Intel(R) Deep Learning Streamer Pipeline Zoo

Features Include:

Initial Preview Release (v0.0.5)

Owner

A project to build an AI voice assistant using Python . The Voice assistant interacts with the humans to perform basic tasks.

(Py)TOD: Tensor-based Outlier Detection, A General GPU-Accelerated Framework

BMN: Boundary-Matching Network

ALFRED - A Benchmark for Interpreting Grounded Instructions for Everyday Tasks

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

pytorch bert intent classification and slot filling

StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation

"NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search".

Unofficial PyTorch implementation of Neural Additive Models (NAM) by Agarwal, et al.

The official TensorFlow implementation of the paper Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition

A library for performing coverage guided fuzzing of neural networks

This thesis is mainly concerned with state-space methods for a class of deep Gaussian process (DGP) regression problems

A Python Package For System Identification Using NARMAX Models

An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

MoveNet Single Pose on DepthAI

Basics of 2D and 3D Human Pose Estimation.

Message Passing on Cell Complexes

SphereFace: Deep Hypersphere Embedding for Face Recognition

A very simple baseline to estimate 2D & 3D SMPL-compatible keypoints from a single color image.

Dynamic Multi-scale Filters for Semantic Segmentation (DMNet ICCV'2019)