训练阶段yolov7主干部分结构图

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~

训练阶段yolov7主干部分结构图相关推荐

为什么极度随机树比随机森林更随机？这个极度随机的特性有什么好处？在训练阶段、极度随机数比随机森林快还是慢？
为什么极度随机树比随机森林更随机?这个极度随机的特性有什么好处?在训练阶段.极度随机数比随机森林快还是慢? ExtRa Trees是Extremely Randomized Trees的缩写,意思就是 ...
Fast-RCNN解析：训练阶段代码导读
转载自:http://blog.csdn.net/linj_m/article/details/48930179#0-tsina-1-35514-397232819ff9a47a7b7e80a4061 ...
HRBU 2021年暑期训练阶段二Day3
目录 A - Shuffle'm Up 题目链接: 题意: 做法: B - Prime Path 题目链接: 题意: 做法: C - Function Run Fun 题目链接: 题意: 做法: D ...
【模型训练】YOLOv7反光衣检测
[YOLOv7&yolov5&yolov3]反光衣检测 1.YOLOv7反光衣检测模型训练 2.模型验证 3.模型和数据集下载网盘链接 1.本项目采用YOLOv7算法实现对反光衣的检测 ...
HRBU 2021年暑期训练阶段三Day1
目录 A - Similar Strings 题目链接: 题意: 做法: B - card card card 题目链接: 题意: 做法: C - String 题目链接: 题意: 做法: D - C ...
【模型训练】YOLOv7自行车检测
[YOLOv7&yolov5&yolov3]自行车检测 1.模型训练 2.模型验证 3.模型和数据集下载网盘链接 1.本项目采用YOLOv7算法实现对自行车检测识别,在1000多张自行 ...
【模型训练】YOLOv7道路裂缝检测
[YOLOv7&yolov5&yolov3]道路裂缝检测 1.模型训练 2.模型验证 3.模型和数据集下载网盘链接 1.本项目采用YOLOv7算法实现对道路.桥梁水泥地面裂缝的识别,在 ...
【模型训练】YOLOv7吸烟行为检测
YOLOv7吸烟行为检测 1.YOLOv7算法吸烟行为检测模型训练 2.YOLOv7模型模型评估 3.模型和数据集下载 1.本项目采用YOLOv7算法实现对吸烟行为的检测,在一万多张吸烟数据集中训练得 ...
PLOS Biology脑电研究：不同训练阶段中选择性注意的两种机制
选择性注意可以通过注意增益与降低神经噪声来增强对感觉信息的处理.然而,这两种机制在多大程度上有助于改善注意过程中的知觉表现仍然存在争议.本文假设:采用哪种选择性注意机制取决于任务训练的持续时间.本研究 ...

训练阶段yolov7主干部分结构图

训练阶段yolov7主干部分结构图相关推荐

最新文章

热门文章