From 02ef0c2553019468e832b759e14bad8d5bdcb4d1 Mon Sep 17 00:00:00 2001 From: wa22 Date: Thu, 23 May 2024 10:29:27 +0000 Subject: [PATCH] update --- README.md | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index f4e883691..4a7dfc781 100644 --- a/README.md +++ b/README.md @@ -20,12 +20,9 @@ Ao Wang, Hui Chen, Lihao Liu, Kai Chen, Zijia Lin, Jungong Han, and Guiguang Din Over the past years, YOLOs have emerged as the predominant paradigm in the field of real-time object detection owing to their effective balance between computational cost and detection performance. Researchers have explored the architectural designs, optimization objectives, data augmentation strategies, and others for YOLOs, achieving notable progress. However, the reliance on the non-maximum suppression (NMS) for post-processing hampers the end-to-end deployment of YOLOs and adversely impacts the inference latency. Besides, the design of various components in YOLOs lacks the comprehensive and thorough inspection, resulting in noticeable computational redundancy and limiting the model's capability. It renders the suboptimal efficiency, along with considerable potential for performance improvements. In this work, we aim to further advance the performance-efficiency boundary of YOLOs from both the post-processing and the model architecture. To this end, we first present the consistent dual assignments for NMS-free training of YOLOs, which brings the competitive performance and low inference latency simultaneously. Moreover, we introduce the holistic efficiency-accuracy driven model design strategy for YOLOs. We comprehensively optimize various components of YOLOs from both the efficiency and accuracy perspectives, which greatly reduces the computational overhead and enhances the capability. The outcome of our effort is a new generation of YOLO series for real-time end-to-end object detection, dubbed YOLOv10. Extensive experiments show that YOLOv10 achieves the state-of-the-art performance and efficiency across various model scales. For example, our YOLOv10-S is 1.8$\times$ faster than RT-DETR-R18 under the similar AP on COCO, meanwhile enjoying 2.8$\times$ smaller number of parameters and FLOPs. Compared with YOLOv9-C, YOLOv10-B has 46\% less latency and 25\% fewer parameters for the same performance. -
- - ## Performance COCO -| Model | Test Size | #params | FLOPs | AP$^{val}$ | Latency | +| Model | Test Size | #Params | FLOPs | APval | Latency | |:---------------|:----:|:---:|:--:|:--:|:--:| | [YOLOv10-N]() | 640 | 2.3M | 6.7G | 38.5% | 1.84ms | | [YOLOv10-S]() | 640 | 7.2M | 21.6G | 46.3% | 2.49ms | @@ -68,7 +65,7 @@ yolo predict model=yolov10n/s/m/b/l/x.onnx # End-to-End TensorRT yolo export model=yolov10n/s/m/b/l/x.pt format=engine half=True simplify opset=13 workspace=16 # Or -trtexec --onnx=onnxs/yolov10n/s/m/b/l/x.onnx --saveEngine=engines/yolov10n/s/m/b/l/x.engine --fp16 +trtexec --onnx=yolov10n/s/m/b/l/x.onnx --saveEngine=yolov10n/s/m/b/l/x.engine --fp16 # Predict with TensorRT yolo predict model=yolov10n/s/m/b/l/x.engine ```