《博主简介》

小伙伴们好，我是阿旭。
专注于计算机视觉领域，包括目标检测、图像分类、图像分割和目标跟踪等项目开发，提供模型对比实验、答疑辅导等。

《------往期经典推荐------》

一、AI应用软件开发实战专栏【链接】

项目名称	项目名称
1.【人脸识别与管理系统开发】	2.【车牌识别与自动收费管理系统开发】
3.【手势识别系统开发】	4.【人脸面部活体检测系统开发】
5.【图片风格快速迁移软件开发】	6.【人脸表表情识别系统】
7.【YOLOv8多目标识别与自动标注软件开发】	8.【基于深度学习的行人跌倒检测系统】
9.【基于深度学习的PCB板缺陷检测系统】	10.【基于深度学习的生活垃圾分类目标检测系统】
11.【基于深度学习的安全帽目标检测系统】	12.【基于深度学习的120种犬类检测与识别系统】
13.【基于深度学习的路面坑洞检测系统】	14.【基于深度学习的火焰烟雾检测系统】
15.【基于深度学习的钢材表面缺陷检测系统】	16.【基于深度学习的舰船目标分类检测系统】
17.【基于深度学习的西红柿成熟度检测系统】	18.【基于深度学习的血细胞检测与计数系统】
19.【基于深度学习的吸烟/抽烟行为检测系统】	20.【基于深度学习的水稻害虫检测与识别系统】
21.【基于深度学习的高精度车辆行人检测与计数系统】	22.【基于深度学习的路面标志线检测与识别系统】
23.【基于深度学习的智能小麦害虫检测识别系统】	24.【基于深度学习的智能玉米害虫检测识别系统】
25.【基于深度学习的200种鸟类智能检测与识别系统】	26.【基于深度学习的45种交通标志智能检测与识别系统】
27.【基于深度学习的人脸面部表情识别系统】	28.【基于深度学习的苹果叶片病害智能诊断系统】
29.【基于深度学习的智能肺炎诊断系统】	30.【基于深度学习的葡萄簇目标检测系统】
31.【基于深度学习的100种中草药智能识别系统】	32.【基于深度学习的102种花卉智能识别系统】
33.【基于深度学习的100种蝴蝶智能识别系统】	34.【基于深度学习的水稻叶片病害智能诊断系统】
35.【基于与ByteTrack的车辆行人多目标检测与追踪系统】	36.【基于深度学习的智能草莓病害检测与分割系统】
37.【基于深度学习的复杂场景下船舶目标检测系统】	38.【基于深度学习的农作物幼苗与杂草检测系统】
39.【基于深度学习的智能道路裂缝检测与分析系统】	40.【基于深度学习的葡萄病害智能诊断与防治系统】
41.【基于深度学习的遥感地理空间物体检测系统】	42.【基于深度学习的无人机视角地面物体检测系统】
43.【基于深度学习的木薯病害智能诊断与防治系统】	44.【基于深度学习的野外火焰烟雾检测系统】
45.【基于深度学习的脑肿瘤智能检测系统】	46.【基于深度学习的玉米叶片病害智能诊断与防治系统】
47.【基于深度学习的橙子病害智能诊断与防治系统】	48.【基于深度学习的车辆检测追踪与流量计数系统】
49.【基于深度学习的行人检测追踪与双向流量计数系统】	50.【基于深度学习的反光衣检测与预警系统】
51.【基于深度学习的危险区域人员闯入检测与报警系统】	52.【基于深度学习的高密度人脸智能检测与统计系统】
53.【基于深度学习的CT扫描图像肾结石智能检测系统】	54.【基于深度学习的水果智能检测系统】
55.【基于深度学习的水果质量好坏智能检测系统】	56.【基于深度学习的蔬菜目标检测与识别系统】
57.【基于深度学习的非机动车驾驶员头盔检测系统】	58.【太基于深度学习的阳能电池板检测与分析系统】
59.【基于深度学习的工业螺栓螺母检测】	60.【基于深度学习的金属焊缝缺陷检测系统】
61.【基于深度学习的链条缺陷检测与识别系统】	62.【基于深度学习的交通信号灯检测识别】
63.【基于深度学习的草莓成熟度检测与识别系统】	64.【基于深度学习的水下海生物检测识别系统】
65.【基于深度学习的道路交通事故检测识别系统】	66.【基于深度学习的安检X光危险品检测与识别系统】
67.【基于深度学习的农作物类别检测与识别系统】	68.【基于深度学习的危险驾驶行为检测识别系统】
69.【基于深度学习的维修工具检测识别系统】	70.【基于深度学习的维修工具检测识别系统】
71.【基于深度学习的建筑墙面损伤检测系统】	72.【基于深度学习的煤矿传送带异物检测系统】
73.【基于深度学习的老鼠智能检测系统】	74.【基于深度学习的水面垃圾智能检测识别系统】
75.【基于深度学习的遥感视角船只智能检测系统】	76.【基于深度学习的胃肠道息肉智能检测分割与诊断系统】
77.【基于深度学习的心脏超声图像间隔壁检测分割与分析系统】	78.【基于深度学习的心脏超声图像间隔壁检测分割与分析系统】
79.【基于深度学习的果园苹果检测与计数系统】	80.【基于深度学习的半导体芯片缺陷检测系统】
81.【基于深度学习的糖尿病视网膜病变检测与诊断系统】	82.【基于深度学习的运动鞋品牌检测与识别系统】
83.【基于深度学习的苹果叶片病害检测识别系统】	84.【基于深度学习的医学X光骨折检测与语音提示系统】
85.【基于深度学习的遥感视角农田检测与分割系统】	86.【基于深度学习的运动品牌LOGO检测与识别系统】
87.【基于深度学习的电瓶车进电梯检测与语音提示系统】	88.【基于深度学习的遥感视角地面房屋建筑检测分割与分析系统】
89.【基于深度学习的医学CT图像肺结节智能检测与语音提示系统】	90.【基于深度学习的舌苔舌象检测识别与诊断系统】
91.【基于深度学习的蛀牙智能检测与语音提示系统】	92.【基于深度学习的皮肤癌智能检测与语音提示系统】
93.【基于深度学习的工业压力表智能检测与读数系统】	94.【基于深度学习的CT扫描图像肝脏肿瘤智能检测与分析系统】
95.【基于深度学习的CT扫描图像脑肿瘤智能检测与分析系统】	96.【基于深度学习的甲状腺结节智能检测分割与诊断系统】
97.【基于深度学习的车载视角路面病害检测系统】	98.【基于深度学习的宫腔镜病变智能检测与语音提示系统】
99.【基于深度学习的人群密集检测统计分析与报警系统】	100.【基于深度学习的路面积水智能检测分割与分析系统】
101.【基于深度学习的钢丝绳缺陷检测与语音提示系统】	102.【基于深度学习的无人机视角河道水面垃圾检测系统】
103.【基于深度学习的停车场车位智能检测识别系统】	104.【基于深度学习的无人机视角野外搜救人员检测与语音提示系统】
105.【基于深度学习的无人机视角路面病害检测识别系统】	106.【基于深度学习的无人机红外视角海上搜救人员检测与语音提示系统】
107.【基于深度学习的交警手势识别系统】	108.【基于深度学习的红外图像光伏板热斑缺陷检测与语音提示系统】
109.【基于深度学习的风力机缺陷检测与语音提示系统】	110.【基于深度学习的茶叶病害智能检测识别系统】
111.【基于深度学习的铁轨部件缺陷检测与语音提示系统】	112.【基于深度学习的无人机视角车辆检测系统】

二、机器学习实战专栏【链接】，已更新31期，欢迎关注，持续更新中~~
三、深度学习【Pytorch】专栏【链接】
四、【Stable Diffusion绘画系列】专栏【链接】
五、YOLOv8改进专栏【链接】，持续更新中~~
六、YOLO性能对比专栏【链接】，持续更新中~

《------正文------》

前言

本文主要介绍如何打印并且查看YOLO26网络模型的网络结构配置信息、每一层结构详细信息、以及参数量、计算量等模型相关信息。 该方法同样适用于改进后的模型网络结构信息及相关参数查看。可用于不同模型进行参数量、计算量等对比使用。

查看配置文件结构信息

在每次进行YOLO26模型训练前，都会打印相应的模型结构信息，如上图。但是如何自己能够直接打印出上述网络结构配置信息呢？，博主通过查看源码发现，信息是在源码DetectionModel类中，打印出来的。因此我们直接使用该类，传入我们自己的模型配置文件，运行该类即可，代码如下：

from ultralytics.nn.tasks import DetectionModel

# # 模型网络结构配置文件路径
yaml_path = 'ultralytics/cfg/models/26/yolo26n.yaml'
# # 改进的模型结构路径
# yaml_path = 'ultralytics/cfg/models/v8/yolo26n-CBAM.yaml'
# # 传入模型网络结构配置文件cfg, nc为模型检测类别数
DetectionModel(cfg=yaml_path,nc=80)

其中cfg参数为网络结构的yaml配置文件路径，nc表示自己训练模型的类别数量。
运行代码后，打印结果如下：

打印结果说明：
【注：这里使用的nc类别数为80，不同类别数量，参数量会略有差别】
可以看到模型配置文件一共有23行，params为每一层的参数量大小，module为每一层的结构名称，arguments为每一层结构需要传入的参数。最后一行summary为总的信息参数，模型一共有260层，参参数量（parameters）为：2572280，计算量GFLOPs为：6.1.

查看详细的网络结构

上面只是打印出了网络配置文件每一层相关的信息，如果我们想看更加细致的每一步信息，可以直接使用model.info()来进行查看，代码如下：

加载训练好的模型或者网络结构配置文件

from ultralytics import YOLO
# 加载训练好的模型或者网络结构配置文件
model = YOLO('best.pt')
# model = YOLO('ultralytics/cfg/models/26/yolo26n.yaml')

打印模型参数信息：

# 打印模型参数信息
print(model.info())

结果如下：

打印模型每一层结构信息：
在上面代码中加入detailed参数即可。

print(model.info(detailed=True))

打印信息如下：

layer                                    name                type  gradient  parameters               shape        mu     sigma
    0                     model.0.conv.weight              Conv2d      True         432       [16, 3, 3, 3]   0.00561      0.11        float32
    1                       model.0.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
    1                         model.0.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
    2                             model.0.act                SiLU     False           0                  []         -         -              -
    3                     model.1.conv.weight              Conv2d      True        4608      [32, 16, 3, 3]  0.000793    0.0481        float32
    4                       model.1.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
    4                         model.1.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
    5                 model.2.cv1.conv.weight              Conv2d      True        1024      [32, 32, 1, 1]  -0.00737    0.0986        float32
    6                   model.2.cv1.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
    6                     model.2.cv1.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
    7                 model.2.cv2.conv.weight              Conv2d      True        3072      [64, 48, 1, 1]   8.7e-06    0.0836        float32
    8                   model.2.cv2.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
    8                     model.2.cv2.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
    9             model.2.m.0.cv1.conv.weight              Conv2d      True        1152       [8, 16, 3, 3]  -0.00195    0.0484        float32
   10               model.2.m.0.cv1.bn.weight         BatchNorm2d      True           8                 [8]         1         0        float32
   10                 model.2.m.0.cv1.bn.bias         BatchNorm2d      True           8                 [8]         0         0        float32
   11             model.2.m.0.cv2.conv.weight              Conv2d      True        1152       [16, 8, 3, 3]  0.000551    0.0669        float32
   12               model.2.m.0.cv2.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
   12                 model.2.m.0.cv2.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
   13                     model.3.conv.weight              Conv2d      True       36864      [64, 64, 3, 3]  1.05e-05     0.024        float32
   14                       model.3.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
   14                         model.3.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
   15                 model.4.cv1.conv.weight              Conv2d      True        4096      [64, 64, 1, 1]    -0.003     0.072        float32
   16                   model.4.cv1.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
   16                     model.4.cv1.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
   17                 model.4.cv2.conv.weight              Conv2d      True       12288     [128, 96, 1, 1]  9.33e-05    0.0589        float32
   18                   model.4.cv2.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
   18                     model.4.cv2.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
   19             model.4.m.0.cv1.conv.weight              Conv2d      True        4608      [16, 32, 3, 3]  0.000497    0.0344        float32
   20               model.4.m.0.cv1.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
   20                 model.4.m.0.cv1.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
   21             model.4.m.0.cv2.conv.weight              Conv2d      True        4608      [32, 16, 3, 3] -0.000254    0.0481        float32
   22               model.4.m.0.cv2.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
   22                 model.4.m.0.cv2.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
   23                     model.5.conv.weight              Conv2d      True      147456    [128, 128, 3, 3] -7.69e-05     0.017        float32
   24                       model.5.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
   24                         model.5.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
   25                 model.6.cv1.conv.weight              Conv2d      True       16384    [128, 128, 1, 1] -0.000179    0.0513        float32
   26                   model.6.cv1.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
   26                     model.6.cv1.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
   27                 model.6.cv2.conv.weight              Conv2d      True       24576    [128, 192, 1, 1] -0.000338    0.0416        float32
   28                   model.6.cv2.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
   28                     model.6.cv2.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
   29             model.6.m.0.cv1.conv.weight              Conv2d      True        2048      [32, 64, 1, 1]   0.00224    0.0713        float32
   30               model.6.m.0.cv1.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
   30                 model.6.m.0.cv1.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
   31             model.6.m.0.cv2.conv.weight              Conv2d      True        2048      [32, 64, 1, 1]   -0.0002     0.072        float32
   32               model.6.m.0.cv2.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
   32                 model.6.m.0.cv2.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
   33             model.6.m.0.cv3.conv.weight              Conv2d      True        4096      [64, 64, 1, 1]  -0.00139    0.0721        float32
   34               model.6.m.0.cv3.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
   34                 model.6.m.0.cv3.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
   35         model.6.m.0.m.0.cv1.conv.weight              Conv2d      True        9216      [32, 32, 3, 3] -0.000845    0.0341        float32
   36           model.6.m.0.m.0.cv1.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
   36             model.6.m.0.m.0.cv1.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
   37         model.6.m.0.m.0.cv2.conv.weight              Conv2d      True        9216      [32, 32, 3, 3] -0.000381    0.0339        float32
   38           model.6.m.0.m.0.cv2.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
   38             model.6.m.0.m.0.cv2.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
   39         model.6.m.0.m.1.cv1.conv.weight              Conv2d      True        9216      [32, 32, 3, 3]  5.29e-05    0.0342        float32
   40           model.6.m.0.m.1.cv1.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
   40             model.6.m.0.m.1.cv1.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
   41         model.6.m.0.m.1.cv2.conv.weight              Conv2d      True        9216      [32, 32, 3, 3]  0.000267    0.0341        float32
   42           model.6.m.0.m.1.cv2.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
   42             model.6.m.0.m.1.cv2.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
   43                     model.7.conv.weight              Conv2d      True      294912    [256, 128, 3, 3]  8.58e-06     0.017        float32
   44                       model.7.bn.weight         BatchNorm2d      True         256               [256]         1         0        float32
   44                         model.7.bn.bias         BatchNorm2d      True         256               [256]         0         0        float32
   45                 model.8.cv1.conv.weight              Conv2d      True       65536    [256, 256, 1, 1] -0.000264     0.036        float32
   46                   model.8.cv1.bn.weight         BatchNorm2d      True         256               [256]         1         0        float32
   46                     model.8.cv1.bn.bias         BatchNorm2d      True         256               [256]         0         0        float32
   47                 model.8.cv2.conv.weight              Conv2d      True       98304    [256, 384, 1, 1]  1.15e-06    0.0295        float32
   48                   model.8.cv2.bn.weight         BatchNorm2d      True         256               [256]         1         0        float32
   48                     model.8.cv2.bn.bias         BatchNorm2d      True         256               [256]         0         0        float32
   49             model.8.m.0.cv1.conv.weight              Conv2d      True        8192     [64, 128, 1, 1]   0.00135     0.051        float32
   50               model.8.m.0.cv1.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
   50                 model.8.m.0.cv1.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
   51             model.8.m.0.cv2.conv.weight              Conv2d      True        8192     [64, 128, 1, 1]  -0.00153     0.051        float32
   52               model.8.m.0.cv2.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
   52                 model.8.m.0.cv2.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
   53             model.8.m.0.cv3.conv.weight              Conv2d      True       16384    [128, 128, 1, 1] -5.22e-05    0.0512        float32
   54               model.8.m.0.cv3.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
   54                 model.8.m.0.cv3.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
   55         model.8.m.0.m.0.cv1.conv.weight              Conv2d      True       36864      [64, 64, 3, 3]  0.000173    0.0241        float32
   56           model.8.m.0.m.0.cv1.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
   56             model.8.m.0.m.0.cv1.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
   57         model.8.m.0.m.0.cv2.conv.weight              Conv2d      True       36864      [64, 64, 3, 3] -0.000226    0.0241        float32
   58           model.8.m.0.m.0.cv2.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
   58             model.8.m.0.m.0.cv2.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
   59         model.8.m.0.m.1.cv1.conv.weight              Conv2d      True       36864      [64, 64, 3, 3]  0.000178    0.0241        float32
   60           model.8.m.0.m.1.cv1.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
   60             model.8.m.0.m.1.cv1.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
   61         model.8.m.0.m.1.cv2.conv.weight              Conv2d      True       36864      [64, 64, 3, 3] -2.65e-05    0.0241        float32
   62           model.8.m.0.m.1.cv2.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
   62             model.8.m.0.m.1.cv2.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
   63                 model.9.cv1.conv.weight              Conv2d      True       32768    [128, 256, 1, 1] -0.000108     0.036        float32
   64                   model.9.cv1.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
   64                     model.9.cv1.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
   65                         model.9.cv1.act            Identity     False           0                  []         -         -              -
   66                 model.9.cv2.conv.weight              Conv2d      True      131072    [256, 512, 1, 1]  9.26e-05    0.0255        float32
   67                   model.9.cv2.bn.weight         BatchNorm2d      True         256               [256]         1         0        float32
   67                     model.9.cv2.bn.bias         BatchNorm2d      True         256               [256]         0         0        float32
   68                               model.9.m           MaxPool2d     False           0                  []         -         -              -
   69                model.10.cv1.conv.weight              Conv2d      True       65536    [256, 256, 1, 1] -0.000111     0.036        float32
   70                  model.10.cv1.bn.weight         BatchNorm2d      True         256               [256]         1         0        float32
   70                    model.10.cv1.bn.bias         BatchNorm2d      True         256               [256]         0         0        float32
   71                model.10.cv2.conv.weight              Conv2d      True       65536    [256, 256, 1, 1]  -0.00023    0.0361        float32
   72                  model.10.cv2.bn.weight         BatchNorm2d      True         256               [256]         1         0        float32
   72                    model.10.cv2.bn.bias         BatchNorm2d      True         256               [256]         0         0        float32
   73       model.10.m.0.attn.qkv.conv.weight              Conv2d      True       32768    [256, 128, 1, 1] -0.000127    0.0513        float32
   74         model.10.m.0.attn.qkv.bn.weight         BatchNorm2d      True         256               [256]         1         0        float32
   74           model.10.m.0.attn.qkv.bn.bias         BatchNorm2d      True         256               [256]         0         0        float32
   75               model.10.m.0.attn.qkv.act            Identity     False           0                  []         -         -              -
   76      model.10.m.0.attn.proj.conv.weight              Conv2d      True       16384    [128, 128, 1, 1]  -0.00013    0.0512        float32
   77        model.10.m.0.attn.proj.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
   77          model.10.m.0.attn.proj.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
   78              model.10.m.0.attn.proj.act            Identity     False           0                  []         -         -              -
   79        model.10.m.0.attn.pe.conv.weight              Conv2d      True        1152      [128, 1, 3, 3]   -0.0054     0.194        float32
   80          model.10.m.0.attn.pe.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
   80            model.10.m.0.attn.pe.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
   81                model.10.m.0.attn.pe.act            Identity     False           0                  []         -         -              -
   82          model.10.m.0.ffn.0.conv.weight              Conv2d      True       32768    [256, 128, 1, 1]   -0.0002    0.0513        float32
   83            model.10.m.0.ffn.0.bn.weight         BatchNorm2d      True         256               [256]         1         0        float32
   83              model.10.m.0.ffn.0.bn.bias         BatchNorm2d      True         256               [256]         0         0        float32
   84          model.10.m.0.ffn.1.conv.weight              Conv2d      True       32768    [128, 256, 1, 1]  0.000212    0.0362        float32
   85            model.10.m.0.ffn.1.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
   85              model.10.m.0.ffn.1.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
   86                  model.10.m.0.ffn.1.act            Identity     False           0                  []         -         -              -
   87                                model.11            Upsample     False           0                  []         -         -              -
   88                                model.12              Concat     False           0                  []         -         -              -
   89                model.13.cv1.conv.weight              Conv2d      True       49152    [128, 384, 1, 1] -2.59e-05    0.0295        float32
   90                  model.13.cv1.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
   90                    model.13.cv1.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
   91                model.13.cv2.conv.weight              Conv2d      True       24576    [128, 192, 1, 1]  0.000164    0.0416        float32
   92                  model.13.cv2.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
   92                    model.13.cv2.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
   93            model.13.m.0.cv1.conv.weight              Conv2d      True        2048      [32, 64, 1, 1]   0.00378     0.073        float32
   94              model.13.m.0.cv1.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
   94                model.13.m.0.cv1.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
   95            model.13.m.0.cv2.conv.weight              Conv2d      True        2048      [32, 64, 1, 1]  -0.00286    0.0723        float32
   96              model.13.m.0.cv2.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
   96                model.13.m.0.cv2.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
   97            model.13.m.0.cv3.conv.weight              Conv2d      True        4096      [64, 64, 1, 1]  0.000587    0.0717        float32
   98              model.13.m.0.cv3.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
   98                model.13.m.0.cv3.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
   99        model.13.m.0.m.0.cv1.conv.weight              Conv2d      True        9216      [32, 32, 3, 3] -0.000176    0.0339        float32
  100          model.13.m.0.m.0.cv1.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
  100            model.13.m.0.m.0.cv1.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
  101        model.13.m.0.m.0.cv2.conv.weight              Conv2d      True        9216      [32, 32, 3, 3]  5.28e-05     0.034        float32
  102          model.13.m.0.m.0.cv2.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
  102            model.13.m.0.m.0.cv2.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
  103        model.13.m.0.m.1.cv1.conv.weight              Conv2d      True        9216      [32, 32, 3, 3]  0.000276    0.0338        float32
  104          model.13.m.0.m.1.cv1.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
  104            model.13.m.0.m.1.cv1.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
  105        model.13.m.0.m.1.cv2.conv.weight              Conv2d      True        9216      [32, 32, 3, 3]  0.000775    0.0338        float32
  106          model.13.m.0.m.1.cv2.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
  106            model.13.m.0.m.1.cv2.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
  107                                model.14            Upsample     False           0                  []         -         -              -
  108                                model.15              Concat     False           0                  []         -         -              -
  109                model.16.cv1.conv.weight              Conv2d      True       16384     [64, 256, 1, 1] -9.75e-05     0.036        float32
  110                  model.16.cv1.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
  110                    model.16.cv1.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
  111                model.16.cv2.conv.weight              Conv2d      True        6144      [64, 96, 1, 1]  2.59e-05    0.0592        float32
  112                  model.16.cv2.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
  112                    model.16.cv2.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
  113            model.16.m.0.cv1.conv.weight              Conv2d      True         512      [16, 32, 1, 1]   0.00212     0.102        float32
  114              model.16.m.0.cv1.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  114                model.16.m.0.cv1.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  115            model.16.m.0.cv2.conv.weight              Conv2d      True         512      [16, 32, 1, 1]   0.00287    0.0999        float32
  116              model.16.m.0.cv2.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  116                model.16.m.0.cv2.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  117            model.16.m.0.cv3.conv.weight              Conv2d      True        1024      [32, 32, 1, 1]   0.00347     0.104        float32
  118              model.16.m.0.cv3.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
  118                model.16.m.0.cv3.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
  119        model.16.m.0.m.0.cv1.conv.weight              Conv2d      True        2304      [16, 16, 3, 3] -0.000425    0.0483        float32
  120          model.16.m.0.m.0.cv1.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  120            model.16.m.0.m.0.cv1.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  121        model.16.m.0.m.0.cv2.conv.weight              Conv2d      True        2304      [16, 16, 3, 3]  -0.00143    0.0478        float32
  122          model.16.m.0.m.0.cv2.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  122            model.16.m.0.m.0.cv2.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  123        model.16.m.0.m.1.cv1.conv.weight              Conv2d      True        2304      [16, 16, 3, 3]  -0.00044    0.0481        float32
  124          model.16.m.0.m.1.cv1.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  124            model.16.m.0.m.1.cv1.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  125        model.16.m.0.m.1.cv2.conv.weight              Conv2d      True        2304      [16, 16, 3, 3] -0.000684    0.0485        float32
  126          model.16.m.0.m.1.cv2.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  126            model.16.m.0.m.1.cv2.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  127                    model.17.conv.weight              Conv2d      True       36864      [64, 64, 3, 3]  0.000129     0.024        float32
  128                      model.17.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
  128                        model.17.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
  129                                model.18              Concat     False           0                  []         -         -              -
  130                model.19.cv1.conv.weight              Conv2d      True       24576    [128, 192, 1, 1] -0.000114    0.0416        float32
  131                  model.19.cv1.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
  131                    model.19.cv1.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
  132                model.19.cv2.conv.weight              Conv2d      True       24576    [128, 192, 1, 1] -0.000339    0.0415        float32
  133                  model.19.cv2.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
  133                    model.19.cv2.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
  134            model.19.m.0.cv1.conv.weight              Conv2d      True        2048      [32, 64, 1, 1] -4.37e-05    0.0722        float32
  135              model.19.m.0.cv1.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
  135                model.19.m.0.cv1.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
  136            model.19.m.0.cv2.conv.weight              Conv2d      True        2048      [32, 64, 1, 1]   -0.0011    0.0725        float32
  137              model.19.m.0.cv2.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
  137                model.19.m.0.cv2.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
  138            model.19.m.0.cv3.conv.weight              Conv2d      True        4096      [64, 64, 1, 1]  8.43e-05    0.0717        float32
  139              model.19.m.0.cv3.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
  139                model.19.m.0.cv3.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
  140        model.19.m.0.m.0.cv1.conv.weight              Conv2d      True        9216      [32, 32, 3, 3]  0.000496    0.0336        float32
  141          model.19.m.0.m.0.cv1.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
  141            model.19.m.0.m.0.cv1.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
  142        model.19.m.0.m.0.cv2.conv.weight              Conv2d      True        9216      [32, 32, 3, 3]   0.00015    0.0341        float32
  143          model.19.m.0.m.0.cv2.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
  143            model.19.m.0.m.0.cv2.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
  144        model.19.m.0.m.1.cv1.conv.weight              Conv2d      True        9216      [32, 32, 3, 3] -0.000129    0.0341        float32
  145          model.19.m.0.m.1.cv1.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
  145            model.19.m.0.m.1.cv1.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
  146        model.19.m.0.m.1.cv2.conv.weight              Conv2d      True        9216      [32, 32, 3, 3] -0.000211     0.034        float32
  147          model.19.m.0.m.1.cv2.bn.weight         BatchNorm2d      True          32                [32]         1         0        float32
  147            model.19.m.0.m.1.cv2.bn.bias         BatchNorm2d      True          32                [32]         0         0        float32
  148                    model.20.conv.weight              Conv2d      True      147456    [128, 128, 3, 3]  -5.3e-06     0.017        float32
  149                      model.20.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
  149                        model.20.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
  150                                model.21              Concat     False           0                  []         -         -              -
  151                model.22.cv1.conv.weight              Conv2d      True       98304    [256, 384, 1, 1] -6.51e-05    0.0294        float32
  152                  model.22.cv1.bn.weight         BatchNorm2d      True         256               [256]         1         0        float32
  152                    model.22.cv1.bn.bias         BatchNorm2d      True         256               [256]         0         0        float32
  153                model.22.cv2.conv.weight              Conv2d      True       98304    [256, 384, 1, 1] -2.61e-05    0.0295        float32
  154                  model.22.cv2.bn.weight         BatchNorm2d      True         256               [256]         1         0        float32
  154                    model.22.cv2.bn.bias         BatchNorm2d      True         256               [256]         0         0        float32
  155          model.22.m.0.0.cv1.conv.weight              Conv2d      True       73728     [64, 128, 3, 3] -0.000181     0.017        float32
  156            model.22.m.0.0.cv1.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
  156              model.22.m.0.0.cv1.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
  157          model.22.m.0.0.cv2.conv.weight              Conv2d      True       73728     [128, 64, 3, 3] -4.27e-05    0.0241        float32
  158            model.22.m.0.0.cv2.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
  158              model.22.m.0.0.cv2.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
  159     model.22.m.0.1.attn.qkv.conv.weight              Conv2d      True       32768    [256, 128, 1, 1] -0.000304     0.051        float32
  160       model.22.m.0.1.attn.qkv.bn.weight         BatchNorm2d      True         256               [256]         1         0        float32
  160         model.22.m.0.1.attn.qkv.bn.bias         BatchNorm2d      True         256               [256]         0         0        float32
  161             model.22.m.0.1.attn.qkv.act            Identity     False           0                  []         -         -              -
  162    model.22.m.0.1.attn.proj.conv.weight              Conv2d      True       16384    [128, 128, 1, 1]  0.000286    0.0512        float32
  163      model.22.m.0.1.attn.proj.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
  163        model.22.m.0.1.attn.proj.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
  164            model.22.m.0.1.attn.proj.act            Identity     False           0                  []         -         -              -
  165      model.22.m.0.1.attn.pe.conv.weight              Conv2d      True        1152      [128, 1, 3, 3]  -0.00486      0.19        float32
  166        model.22.m.0.1.attn.pe.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
  166          model.22.m.0.1.attn.pe.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
  167              model.22.m.0.1.attn.pe.act            Identity     False           0                  []         -         -              -
  168        model.22.m.0.1.ffn.0.conv.weight              Conv2d      True       32768    [256, 128, 1, 1]  2.31e-06    0.0512        float32
  169          model.22.m.0.1.ffn.0.bn.weight         BatchNorm2d      True         256               [256]         1         0        float32
  169            model.22.m.0.1.ffn.0.bn.bias         BatchNorm2d      True         256               [256]         0         0        float32
  170        model.22.m.0.1.ffn.1.conv.weight              Conv2d      True       32768    [128, 256, 1, 1]  6.89e-05    0.0361        float32
  171          model.22.m.0.1.ffn.1.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
  171            model.22.m.0.1.ffn.1.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
  172                model.22.m.0.1.ffn.1.act            Identity     False           0                  []         -         -              -
  173            model.23.cv2.0.0.conv.weight              Conv2d      True        9216      [16, 64, 3, 3]  0.000251    0.0242        float32
  174              model.23.cv2.0.0.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  174                model.23.cv2.0.0.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  175            model.23.cv2.0.1.conv.weight              Conv2d      True        2304      [16, 16, 3, 3]   0.00189    0.0482        float32
  176              model.23.cv2.0.1.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  176                model.23.cv2.0.1.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  177                 model.23.cv2.0.2.weight              Conv2d      True          64       [4, 16, 1, 1]   -0.0287     0.153        float32
  177                   model.23.cv2.0.2.bias              Conv2d      True           4                 [4]         2         0        float32
  178            model.23.cv2.1.0.conv.weight              Conv2d      True       18432     [16, 128, 3, 3] -0.000184    0.0171        float32
  179              model.23.cv2.1.0.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  179                model.23.cv2.1.0.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  180            model.23.cv2.1.1.conv.weight              Conv2d      True        2304      [16, 16, 3, 3] -0.000105    0.0486        float32
  181              model.23.cv2.1.1.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  181                model.23.cv2.1.1.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  182                 model.23.cv2.1.2.weight              Conv2d      True          64       [4, 16, 1, 1]   -0.0153      0.15        float32
  182                   model.23.cv2.1.2.bias              Conv2d      True           4                 [4]         2         0        float32
  183            model.23.cv2.2.0.conv.weight              Conv2d      True       36864     [16, 256, 3, 3] -6.12e-06     0.012        float32
  184              model.23.cv2.2.0.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  184                model.23.cv2.2.0.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  185            model.23.cv2.2.1.conv.weight              Conv2d      True        2304      [16, 16, 3, 3]  -0.00112    0.0479        float32
  186              model.23.cv2.2.1.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  186                model.23.cv2.2.1.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  187                 model.23.cv2.2.2.weight              Conv2d      True          64       [4, 16, 1, 1]   0.00415     0.146        float32
  187                   model.23.cv2.2.2.bias              Conv2d      True           4                 [4]         2         0        float32
  188          model.23.cv3.0.0.0.conv.weight              Conv2d      True         576       [64, 1, 3, 3]   -0.0059     0.191        float32
  189            model.23.cv3.0.0.0.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
  189              model.23.cv3.0.0.0.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
  190          model.23.cv3.0.0.1.conv.weight              Conv2d      True        5120      [80, 64, 1, 1] -0.000175    0.0727        float32
  191            model.23.cv3.0.0.1.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  191              model.23.cv3.0.0.1.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  192          model.23.cv3.0.1.0.conv.weight              Conv2d      True         720       [80, 1, 3, 3]      0.02      0.19        float32
  193            model.23.cv3.0.1.0.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  193              model.23.cv3.0.1.0.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  194          model.23.cv3.0.1.1.conv.weight              Conv2d      True        6400      [80, 80, 1, 1]  -0.00191    0.0648        float32
  195            model.23.cv3.0.1.1.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  195              model.23.cv3.0.1.1.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  196                 model.23.cv3.0.2.weight              Conv2d      True        6400      [80, 80, 1, 1]  0.000251    0.0648        float32
  196                   model.23.cv3.0.2.bias              Conv2d      True          80                [80]     -11.5  1.92e-06        float32
  197          model.23.cv3.1.0.0.conv.weight              Conv2d      True        1152      [128, 1, 3, 3]   0.00123     0.192        float32
  198            model.23.cv3.1.0.0.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
  198              model.23.cv3.1.0.0.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
  199          model.23.cv3.1.0.1.conv.weight              Conv2d      True       10240     [80, 128, 1, 1] -0.000151    0.0506        float32
  200            model.23.cv3.1.0.1.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  200              model.23.cv3.1.0.1.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  201          model.23.cv3.1.1.0.conv.weight              Conv2d      True         720       [80, 1, 3, 3]   0.00242     0.192        float32
  202            model.23.cv3.1.1.0.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  202              model.23.cv3.1.1.0.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  203          model.23.cv3.1.1.1.conv.weight              Conv2d      True        6400      [80, 80, 1, 1]   0.00125    0.0645        float32
  204            model.23.cv3.1.1.1.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  204              model.23.cv3.1.1.1.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  205                 model.23.cv3.1.2.weight              Conv2d      True        6400      [80, 80, 1, 1]  0.000722    0.0644        float32
  205                   model.23.cv3.1.2.bias              Conv2d      True          80                [80]     -10.2         0        float32
  206          model.23.cv3.2.0.0.conv.weight              Conv2d      True        2304      [256, 1, 3, 3]   0.00326     0.189        float32
  207            model.23.cv3.2.0.0.bn.weight         BatchNorm2d      True         256               [256]         1         0        float32
  207              model.23.cv3.2.0.0.bn.bias         BatchNorm2d      True         256               [256]         0         0        float32
  208          model.23.cv3.2.0.1.conv.weight              Conv2d      True       20480     [80, 256, 1, 1]  0.000189    0.0361        float32
  209            model.23.cv3.2.0.1.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  209              model.23.cv3.2.0.1.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  210          model.23.cv3.2.1.0.conv.weight              Conv2d      True         720       [80, 1, 3, 3]  -0.00601     0.195        float32
  211            model.23.cv3.2.1.0.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  211              model.23.cv3.2.1.0.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  212          model.23.cv3.2.1.1.conv.weight              Conv2d      True        6400      [80, 80, 1, 1] -0.000445    0.0638        float32
  213            model.23.cv3.2.1.1.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  213              model.23.cv3.2.1.1.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  214                 model.23.cv3.2.2.weight              Conv2d      True        6400      [80, 80, 1, 1]  -0.00132    0.0645        float32
  214                   model.23.cv3.2.2.bias              Conv2d      True          80                [80]     -8.76         0        float32
  215                            model.23.dfl            Identity     False           0                  []         -         -              -
  216    model.23.one2one_cv2.0.0.conv.weight              Conv2d      True        9216      [16, 64, 3, 3]  0.000251    0.0242        float32
  217      model.23.one2one_cv2.0.0.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  217        model.23.one2one_cv2.0.0.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  218            model.23.one2one_cv2.0.0.act                SiLU     False           0                  []         -         -              -
  219    model.23.one2one_cv2.0.1.conv.weight              Conv2d      True        2304      [16, 16, 3, 3]   0.00189    0.0482        float32
  220      model.23.one2one_cv2.0.1.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  220        model.23.one2one_cv2.0.1.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  221         model.23.one2one_cv2.0.2.weight              Conv2d      True          64       [4, 16, 1, 1]   -0.0287     0.153        float32
  221           model.23.one2one_cv2.0.2.bias              Conv2d      True           4                 [4]         2         0        float32
  222    model.23.one2one_cv2.1.0.conv.weight              Conv2d      True       18432     [16, 128, 3, 3] -0.000184    0.0171        float32
  223      model.23.one2one_cv2.1.0.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  223        model.23.one2one_cv2.1.0.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  224    model.23.one2one_cv2.1.1.conv.weight              Conv2d      True        2304      [16, 16, 3, 3] -0.000105    0.0486        float32
  225      model.23.one2one_cv2.1.1.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  225        model.23.one2one_cv2.1.1.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  226         model.23.one2one_cv2.1.2.weight              Conv2d      True          64       [4, 16, 1, 1]   -0.0153      0.15        float32
  226           model.23.one2one_cv2.1.2.bias              Conv2d      True           4                 [4]         2         0        float32
  227    model.23.one2one_cv2.2.0.conv.weight              Conv2d      True       36864     [16, 256, 3, 3] -6.12e-06     0.012        float32
  228      model.23.one2one_cv2.2.0.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  228        model.23.one2one_cv2.2.0.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  229    model.23.one2one_cv2.2.1.conv.weight              Conv2d      True        2304      [16, 16, 3, 3]  -0.00112    0.0479        float32
  230      model.23.one2one_cv2.2.1.bn.weight         BatchNorm2d      True          16                [16]         1         0        float32
  230        model.23.one2one_cv2.2.1.bn.bias         BatchNorm2d      True          16                [16]         0         0        float32
  231         model.23.one2one_cv2.2.2.weight              Conv2d      True          64       [4, 16, 1, 1]   0.00415     0.146        float32
  231           model.23.one2one_cv2.2.2.bias              Conv2d      True           4                 [4]         2         0        float32
  232  model.23.one2one_cv3.0.0.0.conv.weight              Conv2d      True         576       [64, 1, 3, 3]   -0.0059     0.191        float32
  233    model.23.one2one_cv3.0.0.0.bn.weight         BatchNorm2d      True          64                [64]         1         0        float32
  233      model.23.one2one_cv3.0.0.0.bn.bias         BatchNorm2d      True          64                [64]         0         0        float32
  234          model.23.one2one_cv3.0.0.0.act                SiLU     False           0                  []         -         -              -
  235  model.23.one2one_cv3.0.0.1.conv.weight              Conv2d      True        5120      [80, 64, 1, 1] -0.000175    0.0727        float32
  236    model.23.one2one_cv3.0.0.1.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  236      model.23.one2one_cv3.0.0.1.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  237  model.23.one2one_cv3.0.1.0.conv.weight              Conv2d      True         720       [80, 1, 3, 3]      0.02      0.19        float32
  238    model.23.one2one_cv3.0.1.0.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  238      model.23.one2one_cv3.0.1.0.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  239  model.23.one2one_cv3.0.1.1.conv.weight              Conv2d      True        6400      [80, 80, 1, 1]  -0.00191    0.0648        float32
  240    model.23.one2one_cv3.0.1.1.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  240      model.23.one2one_cv3.0.1.1.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  241         model.23.one2one_cv3.0.2.weight              Conv2d      True        6400      [80, 80, 1, 1]  0.000251    0.0648        float32
  241           model.23.one2one_cv3.0.2.bias              Conv2d      True          80                [80]     -11.5  1.92e-06        float32
  242  model.23.one2one_cv3.1.0.0.conv.weight              Conv2d      True        1152      [128, 1, 3, 3]   0.00123     0.192        float32
  243    model.23.one2one_cv3.1.0.0.bn.weight         BatchNorm2d      True         128               [128]         1         0        float32
  243      model.23.one2one_cv3.1.0.0.bn.bias         BatchNorm2d      True         128               [128]         0         0        float32
  244  model.23.one2one_cv3.1.0.1.conv.weight              Conv2d      True       10240     [80, 128, 1, 1] -0.000151    0.0506        float32
  245    model.23.one2one_cv3.1.0.1.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  245      model.23.one2one_cv3.1.0.1.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  246  model.23.one2one_cv3.1.1.0.conv.weight              Conv2d      True         720       [80, 1, 3, 3]   0.00242     0.192        float32
  247    model.23.one2one_cv3.1.1.0.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  247      model.23.one2one_cv3.1.1.0.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  248  model.23.one2one_cv3.1.1.1.conv.weight              Conv2d      True        6400      [80, 80, 1, 1]   0.00125    0.0645        float32
  249    model.23.one2one_cv3.1.1.1.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  249      model.23.one2one_cv3.1.1.1.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  250         model.23.one2one_cv3.1.2.weight              Conv2d      True        6400      [80, 80, 1, 1]  0.000722    0.0644        float32
  250           model.23.one2one_cv3.1.2.bias              Conv2d      True          80                [80]     -10.2         0        float32
  251  model.23.one2one_cv3.2.0.0.conv.weight              Conv2d      True        2304      [256, 1, 3, 3]   0.00326     0.189        float32
  252    model.23.one2one_cv3.2.0.0.bn.weight         BatchNorm2d      True         256               [256]         1         0        float32
  252      model.23.one2one_cv3.2.0.0.bn.bias         BatchNorm2d      True         256               [256]         0         0        float32
  253  model.23.one2one_cv3.2.0.1.conv.weight              Conv2d      True       20480     [80, 256, 1, 1]  0.000189    0.0361        float32
  254    model.23.one2one_cv3.2.0.1.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  254      model.23.one2one_cv3.2.0.1.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  255  model.23.one2one_cv3.2.1.0.conv.weight              Conv2d      True         720       [80, 1, 3, 3]  -0.00601     0.195        float32
  256    model.23.one2one_cv3.2.1.0.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  256      model.23.one2one_cv3.2.1.0.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  257  model.23.one2one_cv3.2.1.1.conv.weight              Conv2d      True        6400      [80, 80, 1, 1] -0.000445    0.0638        float32
  258    model.23.one2one_cv3.2.1.1.bn.weight         BatchNorm2d      True          80                [80]         1         0        float32
  258      model.23.one2one_cv3.2.1.1.bn.bias         BatchNorm2d      True          80                [80]         0         0        float32
  259         model.23.one2one_cv3.2.2.weight              Conv2d      True        6400      [80, 80, 1, 1]  -0.00132    0.0645        float32
  259           model.23.one2one_cv3.2.2.bias              Conv2d      True          80                [80]     -8.76         0        float32
YOLO26n summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs
(260, 2572280, 2572280, 6.1192448)

可以看到，打印出了模型每一层网络结构的名字、参数量以及该层的结构形状。

本文方法同样适用于ultralytics框架的其他模型结构，使用方法相同，可用于不同模型进行参数量、计算量等对比使用。

为方便大家学习使用，本文涉及到的所有代码均已打包好。免费获取方式如下：

关注下方名片GZH:【阿旭算法与机器学习】，发送【知识点】即可免费获取

---

如果文章对你有帮助，麻烦动动你的小手，给点个赞，鼓励一下吧，谢谢~~~

好了，这篇文章就介绍到这里，喜欢的小伙伴感谢给点个赞和关注，更多精彩内容持续更新~~
关于本篇文章大家有任何建议或意见，欢迎在评论区留言交流！

---

好了，这篇文章就介绍到这里，喜欢的小伙伴感谢给点个赞和关注，更多精彩内容持续更新~~
关于本篇文章大家有任何建议或意见，欢迎在评论区留言交流！