当前位置:网站首页>[yolov5.yaml parsing]
[yolov5.yaml parsing]
2022-07-05 11:42:00 【Network starry sky (LUOC)】
You can start with yolov5s.yaml You can see the structure of each layer in
# parameters
nc: 20 # number of classes
depth_multiple: 0.33 # model depth multiple Controls the depth of the model (BottleneckCSP Number )
width_multiple: 0.50 # layer channel multiple control Conv passageway channel Number ( Number of convolution nuclei )
# depth_multiple Express BottleneckCSP Scaling factor of the module , Will all BottleneckCSP Modular Bottleneck Multiply this parameter to get the final number .
# width_multiple Represents the scaling factor of the convolution channel , Is to configure backbone and head Partly Conv Channel settings , Multiply all by this factor .
# Through these two parameters, the model design with different complexity can be realized .
# anchors
anchors:
- [10,13, 16,30, 33,23] # P3/8 wh stride=8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 backbone
backbone:
# [from, number, module, args]
# from Indicates that the input of the current module comes from the output of that layer ,-1 Represents the output from the upper layer
# number Indicates the number of repetitions of this module ,1 Means there is only one ,3 It means repetition 3 Time
# module: Module name
# args:
[[-1, 1, Focus, [64, 3]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4 128 individual 3x3 Convolution kernel stride=2
[-1, 3, C3, [128]], # CSP Bottleneck with 3 convolutions
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 9, 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, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, C3, [1024, False]], # 9
]
# YOLOv5 head
# No distinction between authors neck modular , therefore head Part contains PANet+Detect part
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)
]
Or use named output :
YOLOv5 2021-6-29 torch 1.7.0+cpu CPU
from n params module arguments
0 -1 1 3520 models.common.Focus [3, 32, 3]
1 -1 1 18560 models.common.Conv [32, 64, 3, 2]
2 -1 1 18816 models.common.C3 [64, 64, 1]
3 -1 1 73984 models.common.Conv [64, 128, 3, 2]
4 -1 1 156928 models.common.C3 [128, 128, 3]
5 -1 1 295424 models.common.Conv [128, 256, 3, 2]
6 -1 1 625152 models.common.C3 [256, 256, 3]
7 -1 1 1180672 models.common.Conv [256, 512, 3, 2]
8 -1 1 656896 models.common.SPP [512, 512, [5, 9, 13]]
9 -1 1 1182720 models.common.C3 [512, 512, 1, False]
10 -1 1 131584 models.common.Conv [512, 256, 1, 1]
11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
12 [-1, 6] 1 0 models.common.Concat [1]
13 -1 1 361984 models.common.C3 [512, 256, 1, False]
14 -1 1 33024 models.common.Conv [256, 128, 1, 1]
15 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
16 [-1, 4] 1 0 models.common.Concat [1]
17 -1 1 90880 models.common.C3 [256, 128, 1, False]
18 -1 1 147712 models.common.Conv [128, 128, 3, 2]
19 [-1, 14] 1 0 models.common.Concat [1]
20 -1 1 296448 models.common.C3 [256, 256, 1, False]
21 -1 1 590336 models.common.Conv [256, 256, 3, 2]
22 [-1, 10] 1 0 models.common.Concat [1]
23 -1 1 1182720 models.common.C3 [512, 512, 1, False]
24 [17, 20, 23] 1 67425 Detect [20, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
Model Summary: 283 layers, 7114785 parameters, 7114785 gradients, 16.5 GFLOPs
边栏推荐
- The ninth Operation Committee meeting of dragon lizard community was successfully held
- Acid transaction theory
- pytorch-多层感知机MLP
- splunk配置163邮箱告警
- COMSOL--三维图形的建立
- 阻止浏览器后退操作
- An error is reported in the process of using gbase 8C database: 80000305, host IPS long to different cluster. How to solve it?
- How did the situation that NFT trading market mainly uses eth standard for trading come into being?
- Unity Xlua MonoProxy Mono代理类
- 汉诺塔问题思路的证明
猜你喜欢
pytorch-softmax回归
Advanced technology management - what is the physical, mental and mental strength of managers
XML parsing
【无标题】
石油化工企业安全生产智能化管控系统平台建设思考和建议
中非 钻石副石怎么镶嵌,才能既安全又好看?
全网最全的新型数据库、多维表格平台盘点 Notion、FlowUs、Airtable、SeaTable、维格表 Vika、飞书多维表格、黑帕云、织信 Informat、语雀
【yolov5.yaml解析】
CDGA|数据治理不得不坚持的六个原则
龙蜥社区第九次运营委员会会议顺利召开
随机推荐
How can edge computing be combined with the Internet of things?
redis主从中的Master自动选举之Sentinel哨兵机制
How did the situation that NFT trading market mainly uses eth standard for trading come into being?
[office] eight usages of if function in Excel
How to make your products as expensive as possible
Prevent browser backward operation
[LeetCode] Wildcard Matching 外卡匹配
解决readObjectStart: expect { or n, but found N, error found in #1 byte of ...||..., bigger context ..
11. (map data section) how to download and use OSM data
871. Minimum Number of Refueling Stops
OneForAll安装使用
What does cross-border e-commerce mean? What do you mainly do? What are the business models?
Install esxi 6.0 interactively
yolov5目标检测神经网络——损失函数计算原理
汉诺塔问题思路的证明
【pytorch 修改预训练模型:实测加载预训练模型与模型随机初始化差别不大】
7 themes and 9 technology masters! Dragon Dragon lecture hall hard core live broadcast preview in July, see you tomorrow
redis的持久化机制原理
Risc-v-qemu-virt in FreeRTOS_ Scheduling opportunity of GCC
Redis集群的重定向