Intel Distribution of OpenVINO Toolkit: A Case Study of Semantic Segmentation

Kustikova, Valentina; Vasiliev, Evgeny; Khvatov, Alexander; Kumbrasiev, Pavel; Vikhrev, Ivan; Utkin, Konstantin; Dudchenko, Anton; Gladilov, Gleb

doi:10.1007/978-3-030-37334-4_2

Cited by 12 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, a PyTorch version of their framework Neural Network Compression Framework (NNCF) is available as a part of OpenVINO Training Extensions 1 . Targeting Open-VINO as well, Kustikova et al implement a solution for semantic segmentation of on-road images [19]. and another to benchmark inference performance of deep learning models on various types of hardware [20] (CPUs, integrated graphics and embedded devices) 2,3 .…”

Section: Related Workmentioning

confidence: 99%

Deploying a Smart Queuing System on Edge with Intel OpenVINO Toolkit

Dagli¹,

Eken

2021

Preprint

View full text Add to dashboard Cite

Recent increases in computational power and the development of specialized architecture led to the possibility to perform machine learning, especially inference, on the edge. OpenVINO is a toolkit based on Convolutional Neural Networks that facilitates fast-track development of computer vision algorithms and deep learning neural networks into vision applications, and enables their easy heterogeneous execution across hardware platforms. A smart queue management can be the key to the success of any sector.} In this paper, we focus on edge deployments to make the Smart Queuing System (SQS) accessible by all also providing ability to run it on cheap devices. This gives it the ability to run the queuing system deep learning algorithms on pre-existing computers which a retail store, public transportation facility or a factory may already possess thus considerably reducing the cost of deployment of such a system. SQS demonstrates how to create a video AI solution on the edge. We validate our results by testing it on multiple edge devices namely CPU, Integrated Edge Graphic Processing Unit (iGPU), Vision Processing Unit (VPU) and Field Programmable Gate Arrays (FPGAs). Experimental results show that deploying a SQS on edge is very promising.

show abstract

Section: Related Workmentioning

confidence: 99%

Deploying a Smart Queuing System on Edge with Intel OpenVINO Toolkit

Dagli¹,

Eken

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…A question was asked in the OpenVINO repository on GitHub how this operation can be optimized, and an Intel engineer proposed the solution to replace upscaling with a specific deconvolution layer, which gives absolutely the same result [21]. A step-by-step tutorial on how to create code to infer deep models using OpenVINO can be found in the article [3], which details the sequence of actions and provides the source code of tutorial for working with OpenVINO.…”

Section: Chosen Modelsmentioning

confidence: 99%

“…To solve the problems of efficient deep model inference on various hardware and embedding in existing software, the Intel R Distribution of OpenVINO TM toolkit [1] is used. The Intel R Distribution of OpenVINO TM toolkit shows significant acceleration of deep learning models in computer vision tasks [2,3] and is also used to accelerate deep learning models in other areas of research in production.…”

Section: Introductionmentioning

confidence: 99%

DL-inferencing for 3D Cephalometric Landmarks Regression task using OpenVINO

Vasiliev

Lachinov

Getmanskaya

2020

Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2

Self Cite

View full text Add to dashboard Cite

In this paper, we evaluate the performance of the Intel Distribution of OpenVINO toolkit in practical solving of the problem of automatic three-dimensional Cephalometric analysis using deep learning methods. This year, the authors proposed an approach to the detection of cephalometric landmarks from CT-tomography data, which is resistant to skull deformities and use convolutional neural networks (CNN). Resistance to deformations is due to the initial detection of 4 points that are basic for the parameterization of the skull shape. The approach was explored on CNN for three architectures. A record regression accuracy in comparison with analogs was obtained. This paper evaluates the perfor- mance of decision making for the trained CNN-models at the inference stage. For a comparative study, the computing environments PyTorch and Intel Distribution of OpenVINO were selected, and 2 of 3 CNN architectures: based on VGG for regression of cephalometric landmarks and an Hourglass-based model, with the RexNext backbone for the land- marks heatmap regression. The experimental dataset was consist of 20 CT of patients with acquired craniomaxillofacial deformities and was in- clude pre- and post-operative CT scans whose format is 800x800x496 with voxel spacing of 0.2x0.2x0.2 mm. Using OpenVINO showed a great increase in performance over the PyTorch, with inference speedup from 13 to 16 times for a Direct Regression model and from 3.5 to 3.8 times for a more complex and precise Hourglass model.

show abstract

“…Hence the performance is comparable with ASIC‐based custom architectures. In addition, with the development of high‐level design tools such as Vitis [ 23 ] , OpenVINO [ 24 ] , and OpenCL [ 25 ] , FPGA has a shorter development cycle. It simplifies the algorithm deployment and the implementation process of computing architecture.…”

Section: Introductionmentioning

confidence: 99%

A Review of FPGA‐Based Custom Computing Architecture for Convolutional Neural Network Inference

Peng

Yao

et al. 2021

Chinese J of Electronics

View full text Add to dashboard Cite

Convolutional neural network (CNN) has been widely adopted in many tasks. Its inference process is usually applied on edge devices where the computing resources and power consumption are limited. At present, the performance of general processors cannot meet the requirement for CNN models with high computation complexity and large number of parameters. Field‐programmable gate array (FPGA)‐based custom computing architecture is a promising solution to further enhance the CNN inference performance. The software/hardware co‐design can effectively reduce the computing overhead, and improve the inference performance while ensuring accuracy. In this paper, the mainstream methods of CNN structure design, hardware‐oriented model compression and FPGA‐based custom architecture design are summarized, and the improvement of CNN inference performance is demonstrated through an example. Challenges and possible research directions in the future are concluded to foster research efforts in this domain.

show abstract

Intel Distribution of OpenVINO Toolkit: A Case Study of Semantic Segmentation

Cited by 12 publications

References 8 publications

Deploying a Smart Queuing System on Edge with Intel OpenVINO Toolkit

Deploying a Smart Queuing System on Edge with Intel OpenVINO Toolkit

DL-inferencing for 3D Cephalometric Landmarks Regression task using OpenVINO

A Review of FPGA‐Based Custom Computing Architecture for Convolutional Neural Network Inference

Contact Info

Product

Resources

About