NVIDIA Jetson Nano & Yolo3(TensorRT) – PART2

https://github.com/opendatacam/opendatacam/blob/master/documentation/USE_WITHOUT_DOCKER.md
— memory issue https://github.com/opendatacam/opendatacam/issues/95

• Jetpack 4.2.1
• Default opencv 3.3.1 from jetpack
• Darknet with branch https://github.com/opendatacam/darknet/tree/opendatacam

test case (20200124) – latest version testing…

$ jetson_release

• NVIDIA Jetson NANO/TX1
• Jetpack 4.3 [L4T 32.3.1]
• CUDA GPU architecture 5.3
• Libraries:
• CUDA 10.0.326
• cuDNN 7.6.3.28-1+cuda10.0
• TensorRT 6.0.1.10-1+cuda10.0
• Visionworks 1.6.0.500n
• OpenCV 4.1.1 compiled CUDA: YES
• Jetson Performance: inactive

Step 1sudo apt-get update -y

Step 2sudo apt-get install -y libv4l-dev

./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg

./darknet detect cfg/yolov3-tiny.cfg yolov3-tiny.weights data/dog.jpg

./darknet detector demo cfg/coco.data cfg/yolov3-tiny.cfg yolov3-tiny.weights -ext_output -c 1

this method test result : Memory leck occurred