ÀÚ·á°Ë»ö-Ç¥ÁØ

Ȩ > ÀڷḶ´ç > ÀÚ·á°Ë»ö > Ç¥ÁØ

ÀÚ·á °Ë»ö°á°ú

°Ë»öÆäÀÌÁö·Î
Ç¥ÁØÁ¾·ù Á¤º¸Åë½Å±â¼úº¸°í¼­(TTAR)
Ç¥ÁعøÈ£ TTAR-11.0075 ±¸ Ç¥ÁعøÈ£
Á¦°³Á¤ÀÏ 2020-10-28 ÃÑ ÆäÀÌÁö 17
ÇÑ±Û Ç¥Áظí ÀÓº£µðµå ½Ã½ºÅÛ¿¡¼­ È¿À²ÀûÀÎ ½Å°æ¸Á Ãß·ÐÀ» À§ÇÑ Áß°£ Ç¥Çö(±â¼úº¸°í¼­)
¿µ¹® Ç¥Áظí Intermediate Representation for Efficient Inference of Neural Networks in Embedded Systems (Technical Report)
ÇÑ±Û ³»¿ë¿ä¾à ÀÌ ±â¼úº¸°í¼­´Â ÀÚ¿ø »ç¿ëÀÌ Á¦ÇÑÀûÀÎ ÀÓº£µðµå ½Ã½ºÅÛ¿¡¼­ ½Å°æ¸Á ¸ðµ¨À» È¿À²ÀûÀ¸·Î ½ÇÇàÇϱâ À§ÇÑ ÄÚµå »ý¼º¿¡ °üÇÑ ¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇÑ ¹æ¹ýÀ» ´Ù·é´Ù. Á¦¾ÈÇÏ´Â ±â¼úÀº Ÿ±ê Çϵå¿þ¾î È¿À²ÀûÀÎ Äڵ带 »ý¼ºÇϱâ À§Çؼ­ Áß°£ Ç¥ÇöÀ» Á¤ÀÇÇϰí À̸¦ ÅëÇØ¼­ °¢ ´Ü°è¿¡¼­ ÃÖÀûÈ­ °úÁ¤À» ¼öÇàÇÑ´Ù. Á¤ÀÇÇÑ Áß°£ Ç¥ÇöÀº µÎ ´Ü°è·Î ±×·¡ÇÁ Áß°£ Ç¥Çö°ú ÅÙ¼­ Áß°£ Ç¥ÇöÀÌ ÀÖ´Ù.
¿µ¹® ³»¿ë¿ä¾à This technical report discusses methods for solving the problem of code generation to efficiently execute neural network models in resource-constrained embedded systems. In order to generate the target hardware efficient code, the intermediate representation is defined and the optimization process is performed at each stage. The intermediate representation consists of two types: graph intermediate representation and tensor intermediate representation.
°ü·Ã IPR È®¾à¼­ Á¢¼öµÈ IPR È®¾à¼­ ¾øÀ½
°ü·ÃÆÄÀÏ    TTAR-11.0075.pdf TTAR-11.0075.pdf
Ç¥ÁØÀÌ·Â
Ç¥Áظí Ç¥ÁعøÈ£ Á¦°³Á¤ÀÏ ±¸ºÐ À¯È¿
¿©ºÎ
IPR
È®¾à¼­
ÆÄÀÏ
ÀÓº£µðµå ½Ã½ºÅÛ¿¡¼­ È¿À²ÀûÀÎ ½Å°æ¸Á Ãß·ÐÀ» À§ÇÑ Áß°£ Ç¥Çö(±â¼úº¸°í¼­) TTAR-11.0075 2020-10-28 Á¦Á¤ À¯È¿ ¾øÀ½ TTAR-11.0075.pdf