YOLOv8n-Face on NVIDIA DeepStream SDK

preview_player
Показать описание
NVIDIA DeepStream SDK application for YOLO-Face models

Supported models:
- YOLOv8-Face
- YOLOv7-Face
- YOLOv5-Face

Performance:
- RTX 3080 8GB (FP16 mode): 780.55 FPS (1920x1080 video)

C and Python codes are available for testing

  1. Marcos Luciano
  2. NVIDIA
  3. DeepStream
  4. TensorRT
  5. ONNX
  6. YOLO
Рекомендации по теме
YOLOv8n-Face on NVIDIA 0:00:27

YOLOv8n-Face on NVIDIA DeepStream SDK

YOLOv8s-Pose on NVIDIA 0:00:17

YOLOv8s-Pose on NVIDIA DeepStream SDK

NVIDIA DeepStream Example; 0:00:45

NVIDIA DeepStream Example; a Face Anonymizer using Python Bindings

YOLOv8s-Seg on NVIDIA 0:00:49

YOLOv8s-Seg on NVIDIA DeepStream SDK

How to detect 0:00:48

How to detect objects with Nvidia Deepstream 4.0 and YOLO

Nvidia Deepstream SDK 0:03:13

Nvidia Deepstream SDK Like Video Analytics pipeline from scratch

Robust Multi-Sensor Facial 0:23:07

Robust Multi-Sensor Facial Recognition in Real Time using Nvidia DeepStream

Veronica can now 0:00:40

Veronica can now recognise people | Face Recognition | ArcFace | NVIDIA DeepStream

Object Detection with 0:09:45

Object Detection with YOLOv8 and DeepStream using Jetson Nano C++

Putin face-recognition with 0:00:24

Putin face-recognition with Deepstream

Nvidia DeepStream Analytics 0:01:37

Nvidia DeepStream Analytics Demo 3

Deepstream (Face detect) 0:07:58

Deepstream (Face detect) show real-time on web (browser)

Deepstream rtspsrc YOLO 0:00:45

Deepstream rtspsrc YOLO app demo

FastoCloud PRO: How 0:04:56

FastoCloud PRO: How to save images in computer vision streams (NVIDIA DeepStream YOLOV3_TINY)

NVIDIA DeepStream SDK 0:01:57

NVIDIA DeepStream SDK that stream analytics toolkit for multisensor processing

Face Tracking on 0:00:18

Face Tracking on NVIDIA Jetson Nano

Nvidia DeepStream - 0:00:34

Nvidia DeepStream - Using Custom Models

YOLOV7 Inference on 0:00:16

YOLOV7 Inference on Jetson Nano using DeepStream

DeepStream Multi Object 0:01:31

DeepStream Multi Object Tracking Demo

Practical application of 0:00:57

Practical application of face detection technology as showcased in NVIDIA Broadcast

[Nvidia Deepstream] Create 0:00:15

[Nvidia Deepstream] Create pipeline visualization graph in Python demo

PPE-Detection DeepStream | 0:00:37

PPE-Detection DeepStream | Part 2

Deepstream 6.1 on 0:01:13

Deepstream 6.1 on Ubuntu20 // YOLOv5 // YOLOv56 //YOLOv7 // YOLOv8

Smart city video 0:02:31

Smart city video ai application using nvidia DeepStream

Комментарии
Автор

Olá Marcos. Muito obrigado por partilhar o teu projeto, contudo Todas as vezes que tento rodar o código, me deparo sempre com o seguinte erro, e o video está congelado:

Traceback (most recent call last):
File “deepstream.py”, line 149, in tracker_src_pad_buffer_probe
parse_face_from_meta(frame_meta, obj_meta)
File “deepstream.py”, line 115, in parse_face_from_meta
circle_params.yc = yc
TypeError: (): incompatible function arguments. The following argument types are supported:
1. (self: pyds.NvOSD_CircleParams, arg0: int) → None

Invoked with: <pyds.NvOSD_CircleParams object at 0x7ff2601a7c70>, -395
Traceback (most recent call last):
File “deepstream.py”, line 149, in tracker_src_pad_buffer_probe
parse_face_from_meta(frame_meta, obj_meta)
File “deepstream.py”, line 115, in parse_face_from_meta
circle_params.yc = yc
TypeError: (): incompatible function arguments. The following argument types are supported:
1. (self: pyds.NvOSD_CircleParams, arg0: int) → None

The_JosephDream
welcome to shbcf.ru