🎉 Wow, yet another groundbreaking revelation: #DETRs are here to replace YOLOs! 🚀 Because who wouldn't want to swap their trusty speedster for a lumbering #Transformer under the exhilarating Apache 2.0 License? 😂 Spoiler: It's the tech equivalent of swapping roller skates for a unicycle in the 100m dash. 🏃‍♂️💨
https://blog.datameister.ai/detection-transformers-real-time-object-detection #YOLOs #TechRevolution #Apache2 #License #Humor #HackerNews #ngated
Detection Transformers: real-time object detection under an Apache 2.0 License

Real-time detection transformers as a superior alternative to YOLOs for object detection. Free to use and commercially adapt, powered by Datameister.

Datameister
Detection Transformers: real-time object detection under an Apache 2.0 License

Real-time detection transformers as a superior alternative to YOLOs for object detection. Free to use and commercially adapt, powered by Datameister.

Datameister
🌘 DETRs在實時物體檢測上擊敗YOLOs
➤ RT-DETR:第一個解決NMS問題的實時端到端物體檢測器
https://zhao-yian.github.io/RTDETR/
本文介紹了一種名為RT-DETR的實時端到端物體檢測器,它是第一個解決了NMS問題的實時端到端物體檢測器。RT-DETR通過設計高效的混合編碼器和不確定性最小的查詢選擇來提高速度和準確性。此外,RT-DETR通過調整解碼器層的數量來支持靈活的速度調整,而無需重新訓練。RT-DETR-R50 / R101在COCO上實現了53.1%/ 54.3%的AP,並在T4 GPU上實現了108/74 FPS,優於先前的YOLOs。RT-DETR-R50在精度上優於DINO-R50 2.2%AP,FPS大約是DINO-R50的21倍。NMS分析表明,當信心閾值為0.001且IoU閾值為0.7時,YOLOv8實現了最佳AP結果,但相應的NMS時間較長。
+ 這篇文章介紹了一種非常有用的物體檢測器,它在速度和準確性方面都優於先前的YOLOs。這將對實時物體檢測應用產生
#物體檢測 #實時檢測 #DETR #YOLOs
DETRs Beat YOLOs on Real-time Object Detection

DETRs Beat YOLOs on Real-time Object Detection