Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Meng-Shiun Yu"'
Publikováno v:
IEEE Access, Vol 12, Pp 64193-64211 (2024)
In recent years, considerable research has focused on the use of custom hardware to accelerate deep learning on edge devices. However, the end-to-end flow of deep learning includes preprocessing and postprocessing. Deep learning hardware accelerators
Externí odkaz:
https://doaj.org/article/a9d4152c955543b58cb5ea8b0fb50374
Autor:
Meng-Shiun Yu, 余孟勳
97
This thesis presents a visual surveilance system for mobile robots using the omnidirectional and PTZ cameras. The omnidirectional camera has 360 degrees of viewing angle, and the PTZ camera can move horizontally and vertically to clearly obse
This thesis presents a visual surveilance system for mobile robots using the omnidirectional and PTZ cameras. The omnidirectional camera has 360 degrees of viewing angle, and the PTZ camera can move horizontally and vertically to clearly obse
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/46609298243646542320
Publikováno v:
International Workshop on OpenCL.
Publikováno v:
The Journal of Supercomputing. 77:10065-10096
With growing applications such as image recognition, speech recognition, ADAS, and AIoT, artificial intelligence (AI) frameworks are becoming popular in various industries. Currently, many choices for neural network frameworks exist for executing AI
Publikováno v:
The Journal of Supercomputing. 77:8622-8652
Deep learning compiler tool, Tensor Virtual Machine (TVM), has excellent deployment, compilation, and optimization capabilities supported by the industry following the vigorous growth in neural networks (NN). It has a unified intermediate representat
Publikováno v:
IWOCL
In recent years, many neural network frameworks have been proposed, such as TensorFlow, Caffe, Keras, and PyTorch. These frameworks have their file formats to store trained parameters, but these file formats are not compatible with each other. Theref
Publikováno v:
Proceedings of SICE Annual Conference 2010; 2010, p37-42, 6p