作者主页(文火冰糖的硅基工坊):文火冰糖(王文兵)的博客_文火冰糖的硅基工坊
目录
1、概述
1、概述
为了适应不同的应用场景,YOLO V5并不是采用单一规模的模型,而是采用多种规模的模型。不同的规模的模型,其速度、所需要的内存空间,mAP不尽相同。
GitHub - ultralytics/yolov5: YOLOv5 ???? in PyTorch > ONNX > CoreML > TFLite
2、不同模型性能比较
3、典型规模的模型:
规模的大小,主要是针对于特征提取层的深度神经网络的层数而言的。
- YOLOv5s:small
- YOLOv5m:middle
- YOLOv5l:large
- YOLOV5x:extra
4、模型规模的配置
(1)模型配置文件的路径
(2)模型配置文件的内容
# YOLOv5 ???? by Ultralytics, GPL-3.0 license
# Parameters
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 6, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 3, C3, [1024]],
[-1, 1, SPPF, [1024, 5]], # 9
]
# YOLOv5 v6.0 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
(3)不同规模模型的比较
YOLOv5n 微规模 | YOLOv5s 小规模 | YOLOv5m 中规模 | YOLOv5l 大规模 | YOLOv5x 超大规模 | |
depth_multiple | 0.33 | 0.33 | 0.67 | 1.00 | 1.33 |
width_multiple | 0.25 | 0.50 | 0.75 | 1.00 | 1.25 |
作者主页(文火冰糖的硅基工坊):文火冰糖(王文兵)的博客_文火冰糖的硅基工坊