训练阶段yolov7主干部分结构图

news/2024/11/23 4:24:03/

通过分析yaml文件，并将训练阶段的yolov7结构转onnx可视化以后，用Visio画了一下主干和SPPCSPC的结构图，其他结构部分后面有时间了再细画。【注意这里强调了是训练阶段，不是预测阶段，预测阶段的结构图和训练是不一样的，因为预测阶段采用了重参化结构，可以看我另一篇将RepVGG重构的文章】

根据项目中 yolov7-main\cfg\training\yolov7.yaml绘制主干结构。下面的注释内容是每次for循环得到的输出通道列表【如何读取yaml文件生成自己的网络结构，在我另一篇文章有写】。

backbone:# [from, number, module, args][[-1, 1, Conv, [32, 3, 1]],  # 0 conv1(3,32,3,s=1)[-1, 1, Conv, [64, 3, 2]],  # 1-P1/2 conv2(32,64,3,s=2)[-1, 1, Conv, [64, 3, 1]],  # conv3(64,64,3,1)[-1, 1, Conv, [128, 3, 2]],  # 3-P2/4  conv4(64,128,k=3,s=2)[-1, 1, Conv, [64, 1, 1]], # conv5(128,64,1,1) 此刻的out_channels=[32,64,64,128,64]*[-2, 1, Conv, [64, 1, 1]], # conv6(128,64,1,1)* 这个卷积层就是一个1*1的identity[-1, 1, Conv, [64, 3, 1]], # conv7(64,64,3,1)[-1, 1, Conv, [64, 3, 1]], # conv8(64,64,3,1)*[-1, 1, Conv, [64, 3, 1]], # conv9(64,64,3,1)[-1, 1, Conv, [64, 3, 1]], # conv10(64,64,3,1) 此刻的output_channels = [32,64,64,128,64,64,64,64,64,64]*[[-1, -3, -5, -6], 1, Concat, [1]], # 取出通道[64,64,64,64], 拼接后256通道 output_channels = [32,64,64,128,64,64,64,64,64,64,256][-1, 1, Conv, [256, 1, 1]],  # 11 conv11(256,256,1,1) output_channels = [32,64,64,128,64,64,64,64,64,64,256,256][-1, 1, MP, []], # maxpooling(k=2,s=2)通道数还是为256[-1, 1, Conv, [128, 1, 1]], # conv12(256,128,1,1) output_channels = [32,64,64,128,64,64,64,64,64,64,256,256,256,128]*[-3, 1, Conv, [128, 1, 1]], # conv13(256,128,1,1) [32,64,64,128,64,64,64,64,64,64,256,256,256,128,128][-1, 1, Conv, [128, 3, 2]], # conv14(128,128,3,2) [32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128]*[[-1, -3], 1, Concat, [1]],  # 16-P3/8  输出256 [32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256][-1, 1, Conv, [128, 1, 1]], # conv15(256,128,1,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128]*[-2, 1, Conv, [128, 1, 1]], # conv16(256,128,1,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128]*[-1, 1, Conv, [128, 3, 1]], # conv17(128,128,3,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128][-1, 1, Conv, [128, 3, 1]], # conv18(128,128,3,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128]*[-1, 1, Conv, [128, 3, 1]], # conv19(128,128,3,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128][-1, 1, Conv, [128, 3, 1]], # conv20(128,128,3,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128]*[[-1, -3, -5, -6], 1, Concat, [1]],# 512 [32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512][-1, 1, Conv, [512, 1, 1]],  # 24 conv21(512,512,1,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512][-1, 1, MP, []],# [32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512][-1, 1, Conv, [256, 1, 1]],# conv22(512,256,1,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256]*[-3, 1, Conv, [256, 1, 1]], # conv23(512,256,1,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256][-1, 1, Conv, [256, 3, 2]], # conv24(256,256,3,2)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256]*[[-1, -3], 1, Concat, [1]],  # 29-P4/16 512[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512][-1, 1, Conv, [256, 1, 1]],# conv25(512,256,1,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256]*[-2, 1, Conv, [256, 1, 1]],# conv26(512,256,1,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256]*[-1, 1, Conv, [256, 3, 1]],# conv27(256,256,3,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256][-1, 1, Conv, [256, 3, 1]],# conv28(256,256,3,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256]*[-1, 1, Conv, [256, 3, 1]],# conv29(256,256,3,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256][-1, 1, Conv, [256, 3, 1]],# conv30(256,256,3,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256]*[[-1, -3, -5, -6], 1, Concat, [1]],# 1024[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256,1024][-1, 1, Conv, [1024, 1, 1]],  # 37 conv31(1024,1024,1,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256,1024,1024][-1, 1, MP, []],# 1024 maxpooling(2,2)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256,1024,1024,1024][-1, 1, Conv, [512, 1, 1]],# conv32(1024,512,1,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256,1024,1024,1024,512]*[-3, 1, Conv, [512, 1, 1]],# conv33(1024,512,1,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256,1024,1024,1024,512,512][-1, 1, Conv, [512, 3, 2]],# conv34(512,512,3,2)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256,1024,1024,1024,512,512,512]*[[-1, -3], 1, Concat, [1]],  # 42-P5/32 1024 [32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256,1024,1024,1024,512,512,512,1024][-1, 1, Conv, [256, 1, 1]],# conv35(1024,256,1,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256,1024,1024,1024,512,512,512,1024,256]*[-2, 1, Conv, [256, 1, 1]],# conv36(1024,256,1,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256,1024,1024,1024,512,512,512,1024,256,256]*[-1, 1, Conv, [256, 3, 1]],# conv37(256,256,3,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256,1024,1024,1024,512,512,512,1024,256,256,256][-1, 1, Conv, [256, 3, 1]],# conv38(256,256,3,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256,1024,1024,1024,512,512,512,1024,256,256,256,256]*[-1, 1, Conv, [256, 3, 1]],# conv39(256,256,3,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256,1024,1024,1024,512,512,512,1024,256,256,256,256,256][-1, 1, Conv, [256, 3, 1]],# conv40(256,256,3,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256,1024,1024,1024,512,512,512,1024,256,256,256,256,256,256]*[[-1, -3, -5, -6], 1, Concat, [1]],# 1024[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256,1024,1024,1024,512,512,512,1024,256,256,256,256,256,256,1024][-1, 1, Conv, [1024, 1, 1]],  # 50conv41(1024,1024,1,1)[32,64,64,128,64,64,64,64,64,64,256,256,256,128,128,128,256,128,128,128,128,128,128,512,512,512,256,256,256,512,256,256,256,256,256,256,1024,1024,1024,512,512,512,1024,256,256,256,256,256,256,1024,1024]]

 网络结构图如下(这可是我一点点看着yaml文件和onnx自己画的哦)：可以看到在每个stage中，均有一个1 * 1大小的identity，就和ResNet是类似的，会会将4个部分进行拼接(通道层次上的拼接)，因此拼接后的通道数会变成4倍。同时每次concat后又会经过一个K=1，S=1的卷积，再分别有两个分支，其中一个分支是经过MaxPooling，另一个分支就是正常的卷积，再将两个分支进行拼接。

 SSPCSPC网络结构如下：可以看到该结构和SPP是有些相似的，都有1*1 5*5 9*9 13*13的池化层，同时与v3和v4一样，前后也均有卷积，不同的是有一个1*1的残差边。

这里我将SPPCSPC的onnx结构图也附上。

从onnx图上可以看到有个sigmoid和conv的相乘，其实这个过程就是SiLU激活函数的过程，只是因为转onnx的时候不支持SiLU激活函数，因此需要转化一下。大家就把那部分看为SiLU就可以啦。

转onnx代码如下：

yaml_file = '../cfg/training/yolov7.yaml'
model = Model(yaml_file)
x = torch.ones(1,3,640,640)
torch.onnx.export(model, x, 'yolov7.onnx', verbose=False,opset_version=11)

 

 如果对你有帮助，还请点个赞支持下~如果你需要原始的VISIO文件可以和我联系~


http://www.ppmy.cn/news/328083.html

相关文章

YOLOV6网络结构

YOLOV6网络结构

1.整体结构 由上图所示，从整体上来看，YOLOV6的网络结构与YOLOV4、YOLOV5是很相似的，尤其是backbone和neck，但是其中的实现模块是有变化的；但最大的不同在于Head部分，采用的是YOLOX的Head方式，将…
阅读更多...
YOLOV5网络结构

YOLOV5网络结构

YOLOv5代码注释版更新啦，注释的是最近的2021.07.14的版本，且注释更全 github: https://github.com/Laughing-q/yolov5_annotations YOLOV5网络结构 粗略图yolov5-1.0~4.0yolov5-5.0 详细图yolov5-3.0yolov5-4.0yolov5-5.0 github代码地址: ultralytics\…
阅读更多...
YOLOv7-tiny网络结构图及yaml文件 详细备注

YOLOv7-tiny网络结构图及yaml文件 详细备注

YOLOv7-tiny 整体网络结构图yolov7-tiny.yaml组件模块MXCBLSPPCSP结构图yaml构建代码 MCB结构图yaml文件表示common.py代码 参考 整体网络结构图 yolov7-tiny.yaml # parameters nc: 80 # number of classes depth_multiple: 1.0 # model depth multiple width_multiple: 1…
阅读更多...
YOLOv7 | 模型结构与正负样本分配解析

YOLOv7 | 模型结构与正负样本分配解析

如有错误，恳请指出。 Yolov7的原作者就是Yolov4的原作者。看论文的时候看到比较乱，这里可能会比较杂乱的记录一下我觉得有点启发的东西。对于yolov7的代码，我也没有仔细的看，只是大概的看了下其他博客提到的些细节。所以这里也不会…
阅读更多...
理解yolov6网络结构

理解yolov6网络结构

yolov6论文地址：https://arxiv.org/abs/2209.02976 先上一张yolov6的网络架构 图片来源于网络 BACKBONE yolov6使用了repVGG作为backbone 如果不了解repVGG的可以看原文 论文地址https://arxiv.org/pdf/2101.03697.pdf 这里简单过一下，repVGG其核心思…
阅读更多...
yolov7各个模型的网络结构图(最详细)

yolov7各个模型的网络结构图(最详细)

美团刚刚发出yolov6，AB大神就带着yolov7来了。。。。。这速度是真快。。 在 5-160 FPS 范围内速度和精度超过所有已知目标检测器。 在 后不到两个星期，提出 YOLOv4 的团队就发布了更新一代的版本。 YOLOv7 的论文被提交到了预印版论文平台 arXiv 上&am…
阅读更多...
pytorch构建YOLOV7网络结构

pytorch构建YOLOV7网络结构

文章目录 前言一、网络结构图二、各模块的实现1.BConv模块2.E-ELAN模块3.MPConv模块4.SPPCSPC模块5.CatConv模块6.RepConv模块 三、整体实现总结 前言 前不久，正宗的YOLOV7横空出世，引来了很多人的关注，因为这次是官方作者的又一力作&#x…
阅读更多...
YOLO系列 --- YOLOV7算法（四）：YOLO V7算法网络结构解析

YOLO系列 --- YOLOV7算法（四）：YOLO V7算法网络结构解析

YOLO系列 — YOLOV7算法（四）：YOLO V7算法网络结构解析 今天来讲讲YOLO V7算法网络结构吧~ 在train.py中大概95行的地方开始创建网络，如下图（YOLO V7下载的时间不同，可能代码有少许的改动，所以行…
阅读更多...
最新文章

Copyright @ 2022~2023