This is speed test on Jetson Nano, pre-trained weight available on AlexeyAB / darknet github (https://github.com/AlexeyAB/darknet). This is diplayed with dropped frames for render:
Weights-files for different cfg-files:
– yolov3-tiny.cfg (34 MB COCO Yolo v3 tiny) – requires 1 GB GPU-RAM
– yolov3-tiny-prn.cfg (33.1% [email protected] – 3.5 BFlops – more)
My makefile :
GPU=1
CUDNN=1
CUDNN_HALF=1
OPENCV=1
AVX=0
OPENMP=0
LIBSO=0
ZED_CAMERA=0
using # For Jetson TX1, Tegra X1, DRIVE CX, DRIVE PX – uncomment:
# ARCH= -gencode arch=compute_53,code=[sm_53,compute_53]
PS : The encoding that allows the recording of the result requires a lot of resources, so this is not a benchmark but can be useful to compare the networks between them (15FPS without encoding ;))
coffe for me 😉 : https://www.paypal.me/Coffe4Antoine?locale.x=fr_FR
Related Post:
- Inteligência Artificial IOT com Jetson Nano
- NANO Tops XLM in Speed Test ?? Another EOS dApp Hack, Tether Losing Market Share $EOS $NANO $USDT
- Nano Transaction Speed Test on Natrium
- YCMOU | How To Find PRN No.| PRN No कस बघायचा | ycmou prn no पून्हा कस घ्यायच |PRN No फिर से कैसे ?.
- DCN V2:Improved Deep &Cross Network and Practical Lessons for Web-scale Learning to Rank Systems
- Cryptocurrency-predicting RNN intro – Deep Learning w/ Python, TensorFlow and Keras p.8
- Cryptocurrency-predicting RNN Model – Deep Learning w/ Python, TensorFlow and Keras p.11
- "EOS Deep Dive" Technical Analysis (EOS) : Sensei Tutums Eos Deep Dive 4.10.19
- Kawasaki STX-15F Jet Ski Acceleration and Top Speed Test
- HIGH SPEED R/C CAR POLICE CHASES! – BeamNG Drive Crash Test Compilation Gameplay
