YOLOv8太卷啦 | YOLOv8官方仓库正式支持RT-DETR训练、测试以及推理

集智书童公众号

发布于 2023-09-04 10:36:51

2.3K0

发布于 2023-09-04 10:36:51

文章被收录于专栏：集智书童

RT-DETR由百度开发，是一款端到端目标检测器，在保持高精度的同时提供实时性能。它利用ViT的强大特性，通过解耦尺度内交互和跨尺度融合来有效处理多尺度特征。 RT-DETR具有很强的适应性，支持使用不同的解码器层灵活调整推理速度，而无需重新训练。该模型在具有TensorRT的CUDA等加速后端方面表现出色，优于许多其他实时目标检测器。

YOLOv8支持RT-DETR

1、使用方法

2、YOLOv8种RT-DETR精度

3、RT-DETR-L的YAML

# Ultralytics YOLO 🚀, AGPL-3.0 license
# RT-DETR-l object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/rtdetr

# Parameters
nc: 80  # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
  # [depth, width, max_channels]
  l: [1.00, 1.00, 1024]

backbone:
  # [from, repeats, module, args]
  - [-1, 1, HGStem, [32, 48]]  # 0-P2/4
  - [-1, 6, HGBlock, [48, 128, 3]]  # stage 1

  - [-1, 1, DWConv, [128, 3, 2, 1, False]]  # 2-P3/8
  - [-1, 6, HGBlock, [96, 512, 3]]   # stage 2

  - [-1, 1, DWConv, [512, 3, 2, 1, False]]  # 4-P3/16
  - [-1, 6, HGBlock, [192, 1024, 5, True, False]]  # cm, c2, k, light, shortcut
  - [-1, 6, HGBlock, [192, 1024, 5, True, True]]
  - [-1, 6, HGBlock, [192, 1024, 5, True, True]]  # stage 3

  - [-1, 1, DWConv, [1024, 3, 2, 1, False]]  # 8-P4/32
  - [-1, 6, HGBlock, [384, 2048, 5, True, False]]  # stage 4

head:
  - [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]]  # 10 input_proj.2
  - [-1, 1, AIFI, [1024, 8]]
  - [-1, 1, Conv, [256, 1, 1]]   # 12, Y5, lateral_convs.0

  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [7, 1, Conv, [256, 1, 1, None, 1, 1, False]]  # 14 input_proj.1
  - [[-2, -1], 1, Concat, [1]]
  - [-1, 3, RepC3, [256]]  # 16, fpn_blocks.0
  - [-1, 1, Conv, [256, 1, 1]]   # 17, Y4, lateral_convs.1

  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [3, 1, Conv, [256, 1, 1, None, 1, 1, False]]  # 19 input_proj.0
  - [[-2, -1], 1, Concat, [1]]  # cat backbone P4
  - [-1, 3, RepC3, [256]]    # X3 (21), fpn_blocks.1

  - [-1, 1, Conv, [256, 3, 2]]   # 22, downsample_convs.0
  - [[-1, 17], 1, Concat, [1]]  # cat Y4
  - [-1, 3, RepC3, [256]]    # F4 (24), pan_blocks.0

  - [-1, 1, Conv, [256, 3, 2]]   # 25, downsample_convs.1
  - [[-1, 12], 1, Concat, [1]]  # cat Y5
  - [-1, 3, RepC3, [256]]    # F5 (27), pan_blocks.1

  - [[21, 24, 27], 1, RTDETRDecoder, [nc]]  # Detect(P3, P4, P5)

方法概览

百度RT-DETR概述。RT-DETR模型架构图显示骨干{S3、S4、S5}的最后三个阶段作为编码器的输入。高效的混合编码器通过尺度内特征交互（AIFI）和跨尺度特征融合模块（CCFM）将多尺度特征转换为图像特征序列。IoU感知查询选择用于选择固定数量的图像特征以用作解码器的初始对象查询。最后，具有辅助预测头的解码器迭代地优化对象查询，以生成框和置信度分数（源）。