Please provide the following info (tick the boxes after creating this topic):
Software Version
DRIVE OS 6.0.10.0
DRIVE OS 6.0.8.1
DRIVE OS 6.0.6
DRIVE OS 6.0.5
DRIVE OS 6.0.4 (rev. 1)
DRIVE OS 6.0.4 SDK
other
Target Operating System
Linux
QNX
other
Hardware Platform
DRIVE AGX Orin Developer Kit (940-63710-0010-300)
DRIVE AGX Orin Developer Kit (940-63710-0010-200)
DRIVE AGX Orin Developer Kit (940-63710-0010-100)
DRIVE AGX Orin Developer Kit (940-63710-0010-D00)
DRIVE AGX Orin Developer Kit (940-63710-0010-C00)
DRIVE AGX Orin Developer Kit (not sure its number)
other
SDK Manager Version
2.1.0
other
Host Machine Version
native Ubuntu Linux 20.04 Host installed with SDK Manager
native Ubuntu Linux 20.04 Host installed with DRIVE OS Docker Containers
native Ubuntu Linux 18.04 Host installed with DRIVE OS Docker Containers
other
Issue Description
hello nvidia expert:
we use (multicast app ,see attachment) nvstream t
Multicast.zip (116.1 KB)
o transfer 7 camera images and (our camera has isp so we do not use on-board isp , we use raw camera images) use cuda convert yuv image to RGB pixel format , after that we use the RGB image as inference input . if we stand along run multicast and our inference program ,both works. but if we push buffer from the multicast nvsci buffer to our inference program , the fps will down to 2 and the DDR bandwidth usage also stays low , can you check our code for nvstream usage(only cuda consumer is used)?
Error String
< Please provide just the error messages here >
Logs
Provide logs in text box instead of image
Please paste the complete application log here. If there are multiple logs, please use multiple text box