Comments (1)
@LuminaDevelopment hi! Thanks for sharing details about your system and the inference time you're achieving with YOLOv8. Your setup with the RTX 4090 is quite powerful, and 9ms is an impressive inference speed! 🚀
Performance can vary based on several factors including the model variant used (e.g., YOLOv8n, YOLOv8x), the batch size, and the specific task (detection, segmentation, etc.). It might be interesting to see comparisons across different systems and setups from other users as well.
For those looking to benchmark their setup, the provided script is a great starting point. Just remember to adjust 'yolov8n.onnx'
based on the model file you have and potentially explore using different image sizes via the imgsz
parameter to see how it affects your inference times.
Feel free to share more insights or anything specific you find out during your benchmarks! 👍
from ultralytics.
Related Issues (20)
- yolov9 export paddle error HOT 4
- Loading engine file on GPU whenever call predict method on a frame of CSI camera even stream=True HOT 4
- UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED HOT 9
- Yaml file problem HOT 1
- Implementing a simple ReID process HOT 1
- Yolov8 Bad detections HOT 5
- Yolov8 SDK run OK in debug but after convert to exe its run as a loop (create unlimited train section) HOT 3
- Really bad Performance with YOLOv8 HOT 6
- yolo-world export onnx HOT 1
- Combine Segmentation and Detection model (Yolov7 & Yolov8) HOT 2
- training does not start HOT 1
- Using data augmentation on YOLOv8-pose HOT 3
- FPS drop while using Ultralytics HOT 2
- numpy.linalg.LinAlgError: 2-th leading minor of the array is not positive definite Error? HOT 4
- 버전 차이 질문 HOT 2
- model.engine speed is slowest than model.pt HOT 3
- Significant Drop in Performance when Switching between YOLOv8n-seg Models HOT 3
- How to crop detected object from image using YOLOv8 model without saving it. HOT 2
- validation on imgsz of 13792 HOT 3
- rtdetr weight problem HOT 5
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ultralytics.