Performance Evaluation of Deep Learning frameworks on Computer Vision problems

Nara, Madhumitha; Mukesh, BN; Padala, Preethi; Kinnal, Bharath

doi:10.1109/icoei.2019.8862603

Cited by 4 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [19], the authors proposed a comparative study of GPU-accelerated deep learning software frameworks such as PyTorch and TensorFlow. Three different neural networks were implemented through MNIST, CIFAR10, and Fashion MNIST datasets to benchmark the performance of the framework.…”

Section: Deep Learning Framework Performance Evaluation Studymentioning

confidence: 99%

A Deep Learning Framework Performance Evaluation to Use YOLO in Nvidia Jetson Platform

Shin

Kim

2022

Applied Sciences

View full text Add to dashboard Cite

Deep learning-based object detection technology can efficiently infer results by utilizing graphics processing units (GPU). However, when using general deep learning frameworks in embedded systems and mobile devices, processing functionality is limited. This allows deep learning frameworks such as TensorFlow-Lite (TF-Lite) and TensorRT (TRT) to be optimized for different hardware. Therefore, this paper introduces a performance inference method that fuses the Jetson monitoring tool with TensorFlow and TRT source code on the Nvidia Jetson AGX Xavier platform. In addition, central processing unit (CPU) utilization, GPU utilization, object accuracy, latency, and power consumption of the deep learning framework were compared and analyzed. The model is You Look Only Once Version4 (YOLOv4), and the dataset uses Common Objects in Context (COCO) and PASCAL Visual Object Classes (VOC). We confirmed that using TensorFlow results in high latency. We also confirmed that TensorFlow-TensorRT (TF-TRT) and TRT using Tensor Cores provide the most efficiency. However, it was confirmed that TF-Lite showed the lowest performance because it utilizes a GPU limited to mobile devices. Through this paper, we think that when developing deep learning-related object detection technology on the Nvidia Jetson platform or desktop environment, services and research can be efficiently conducted through measurement results.

show abstract

Section: Deep Learning Framework Performance Evaluation Studymentioning

confidence: 99%

A Deep Learning Framework Performance Evaluation to Use YOLO in Nvidia Jetson Platform

Shin

Kim

2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Previous works [17,34,43,72,81,99] have compared the performance of DL frameworks on different applications (e.g., computer vision and image classification) and different hardware (e.g., CPU, GPU, and TPU). For detailed information about each DL framework, the readers can refer to [45].…”

Section: Deep Learning Frameworkmentioning

confidence: 99%

The Deep Learning Compiler: A Comprehensive Survey

Li,

Liu,

Liu

et al. 2020

Preprint

View full text Add to dashboard Cite

The difficulty of deploying various deep learning (DL) models on diverse DL hardware has boosted the research and development of DL compilers in the community. Several DL compilers have been proposed from both industry and academia such as Tensorflow XLA and TVM. Similarly, the DL compilers take the DL models described in different DL frameworks as input, and then generate optimized codes for diverse DL hardware as output. However, none of the existing survey has analyzed the unique design architecture of the DL compilers comprehensively. In this paper, we perform a comprehensive survey of existing DL compilers by dissecting the commonly adopted design in details, with emphasis on the DL oriented multi-level IRs, and frontend/backend optimizations. Specifically, we provide a comprehensive comparison among existing DL compilers from various aspects. In addition, we present detailed analysis on the design of multi-level IRs and illustrate the commonly adopted optimization techniques. Finally, several insights are highlighted as the potential research directions of DL compiler. This is the first survey paper focusing on the design architecture of DL compilers, which we hope can pave the road for future research towards DL compiler.

show abstract

“…With the advancement of a number of deep-learning frameworks, the choice of framework for any problem plays an important role in efficiency. [2] In this paper ,we have discussed various software tools used for deep learning. Software tools discussed in this paper are Keras, Pytorch , Tensorflow and Microsoft cognitive toolkit (CNTK) .…”

Section: Introductionmentioning

confidence: 99%

Review on Different Software Tools for Deep Learning

Meshram¹

2022

IJRASET

View full text Add to dashboard Cite

Deep Learning Applications are being applied in various domains in recent years. Training a deep learning model is a very time consuming task. But, many open source frameworks are available to simplify this task. In this review paper we have discussed the features of some popular open source software tools available for deep learning along with their advantages and disadvantages. Software tools discussed in this paper are Tensorflow, Keras, Pytorch, Microsoft Cognitive Toolkit (CNTK). Keywords: Deep Learning, Frameworks, Open Source, Tensorflow, Pytorch, Keras, CNTK

show abstract

Performance Evaluation of Deep Learning frameworks on Computer Vision problems

Cited by 4 publications

References 4 publications

A Deep Learning Framework Performance Evaluation to Use YOLO in Nvidia Jetson Platform

A Deep Learning Framework Performance Evaluation to Use YOLO in Nvidia Jetson Platform

The Deep Learning Compiler: A Comprehensive Survey

Review on Different Software Tools for Deep Learning

Contact Info

Product

Resources

About