YOLOv4-tiny Object Detection on NVIDIA GPU GTX1070
more info
http://microcontrollerkits.blogspot.c...
YOLOv4 --tiny-416 on NVIDIA GTX1070
Image ( 576x425) : 100-115 FPS.
Video ( 960x540) : 86-107 FPS.
Model
YOLOv4 ( TensorRT FP16 ) coco dataset
YOLOv4-tiny ( TensorRT FP16 ) coco dataset
Hardware
CPU : Intel i3-9100F 3.60GHz
GPU : NVIDIA GTX1070. ( Driver Version 470.141.03 )
Software
OS : Ubuntu 18.04.6 LTS
Python 3.6.9
CUDA v11.2.67
Python Library
numpy==1.19.4
opencv-python==4.5.1.48
tensorrt==7.2.2.3
pycuda==2019.1.2
Demos showcase how to convert pre-trained yolov3 and yolov4 models through ONNX to TensorRT engines. The code for these 2 demos has gone through some significant changes. More specifically, I have recently updated the implementation with a "yolo_layer" plugin to speed up the inference time of the yolov3/yolov4 models.
What is YOLO object detector?
When it comes to deep learning-based object detection, there are three primary object detectors you’ll encounter:
R-CNN and their variants, including the original R-CNN, Fast R- CNN, and Faster R-CNN
Single Shot Detector (SSDs)
YOLO
First introduced in 2015 by Redmon et al., their paper, You Only Look Once: Unified, Real-Time Object Detection, details an object detector capable of super real-time object detection, obtaining 45 FPS on a GPU.
You Only Look Once: Unified, Real-Time Object Detection
https://arxiv.org/pdf/1506.02640v3.pdf
We’ll be using YOLOv3 , YOLOv4 in this blog post, in particular, YOLO trained on the COCO dataset.
The COCO dataset consists of 80 labels.
TensorRT demos
https://github.com/jkjung-avt/tensorr...
You Only Look Once: Unified, Real-Time Object Detection
https://arxiv.org/pdf/1506.02640v3.pdf
YOLOv3: An Incremental Improvement
https://arxiv.org/pdf/1804.02767.pdf
YOLOv4: Optimal Speed and Accuracy of Object Detection
https://arxiv.org/pdf/2004.10934.pdf
DarkNet YOLO
https://github.com/AlexeyAB/darknet
YOLO Object Detection
https://pyimagesearch.com/2018/11/12/...
สอบถาม เพิ่มเติม :
อดุลย์ นันทะแก้ว 081-6452400
LINE : adunnan
Page : / softpowergroup
FaceBook : / adun.nantakaew
email : [email protected]
WebSite : https://softpower.tech