ÇѱÛÁ¦¸ñ(Korean Title) |
¿§Áö TPU ±â¹ÝÀÇ ÀÓº£µðµå ±â±âº° °æ·®ÈµÈ À̹ÌÁö ºÐ·ù ¸ðµ¨ ºñ±³ |
¿µ¹®Á¦¸ñ(English Title) |
Comparison of Lightweight Image Classification Model by Embedded Device Based on Edge TPU |
ÀúÀÚ(Author) |
ÃÖµ¿Çö
±è³²Çö
°í»ó±Ù
À̼ö¾È
Donghyeon Choi
Namhyeon Kim
Sangkeun Ko
Suan Lee
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 45 NO. 01 PP. 2162 ~ 2164 (2022. 06) |
Çѱ۳»¿ë (Korean Abstract) |
|
¿µ¹®³»¿ë (English Abstract) |
AIoT is emerging as it moves from the IT era of the tertiary industry to the fourth industrial revolution. AIoT equipment requires00 lightweight model of deep learning because of its limited performance. In this paper, a comparative study was conducted on the time required for inference of lightweight deep learning model on Edge TPU environment equipment optimized for artificial intelligence, and a significant speed difference could be confirmed. Using the results of this paper, it will help build an AIoT environment using Edge TPU. |
Å°¿öµå(Keyword) |
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|