Unable to run yolov3 on jetson nano using tvm

Autonomous Machines Jetson & Embedded Systems Jetson Nano
#1

Hello everyone, I am trying to run yolov3 using the example -Compile YOLO-V2 and YOLO-V3 in DarkNet Model on jetson nano development board. But, in the first where we download cfg and weights file, convolution takes places but i get an like…

" Loading weights from /home/please/yolov3.weights…Done!
free(): invalid next size (fast)
Aborted (core dumped)"

I am stuck with for a long time. Kindly help me with this.

Thanks for everyone

#3

Moving to Jetson Nao forum for resolution.

#5

Hi,

Since Nano has limited memory, would you mind trying the YOLO tiny model to see if it works?

We also have a sample to run the darknet YOLO model with Deepstream and TensorRT.
It’s recommended to give it a try:

/opt/nvidia/deepstream/deepstream-6.0/sources/objectDetector_Yolo/

Thanks.