This thread has been locked.
If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.
I am using the J784S4XEVM running the vision apps demo deep learning models (object detection, etc.). When I use a custom model it works with 2 camers but when I use more than 3 cameras i receive the following memory error during graph creation, only one core seems to be utilized.
What is the proper way to increase memory for C7x1 core in vision apps psdk v09?
[C7x_1 ] 26259.817745 s: VX_ZONE_ERROR:[tivxAlgiVisionAllocMem:194] Failed to Allocate memory record 5 @ space = 17 and size = 13285290 !!!
Grapy verify FAILURE!
[C7x_1 ] 26259.817774 s: VX_ZONE_ERROR:[tivxAlgiVisionCreate:358] tivxAlgiVisionAllocMem Failed
[C7x_1 ] 26259.817798 s: VX_ZONE_ERROR:[tivxKernelTIDLCreate:818] tivxAlgiVisionCreate returned NULL
For 2 cameras I see the following memory utilization:
CPU: c7x_1: HEAP: DDR_LOCAL_MEM: size = 134217728 B, free = 12087040 B ( 9 % unused)
CPU: c7x_1: HEAP: L3_MEM: size = 3145728 B, free = 131072 B ( 4 % unused)
CPU: c7x_1: HEAP: L2_MEM: size = 458752 B, free = 458752 B (100 % unused)
CPU: c7x_1: HEAP: L1_MEM: size = 16384 B, free = 0 B ( 0 % unused)
CPU: c7x_1: HEAP: DDR_SCRATCH_MEM: size = 134217728 B, free = 132117397 B ( 98 % unused)
CPU: c7x_1: HEAP: DDR_NON_CACHE_M: size = 134217728 B, free = 98252672 B ( 73 % unused)
CPU: c7x_1: HEAP: DDR_SCRATCH_NON: size = 134217728 B, free = 134194048 B ( 99 % unused)
Hi,
It seems that the memory is not sufficient in your case. Please refer the below documentation to increase the C7x heap and scratch memory (if required) and retest your usecase.
Regards,
Nikhil