YOLOv5白皮书-第Y5周：yolo.py文件解读

news2024/11/28 16:29:18

🍨 本文为🔗365天深度学习训练营中的学习记录博客
🍖 原作者：K同学啊

一、环境

语言：Python3、Pytorch
开发环境
电脑系统：Windows 10
语言环境：Python 3.9.2
编译器：VS Code
显卡：3060
CUDA版本：Release 11.4, V11.4.48
本周任务：将YOLOv5s模型的C3修改成C2,并将C2插入到第2层与第3层之间

二、了解yolo.py文件

yolov5.py是构建和操作yolov5模型的文件
parse_model函数：在common.py中有许多模块，此函数负责将这些模块以及其他模块拼接起来，搭建模型
Detect模块：构建Detect层，将输入的特征图转换为需要的shape
Model模块：此模块包含了许多功能，包括特征可视化、打印模型信息等。

三、修改C3

C2就是上周修改后的代码，代码如下：

class C2(nn.Module):
    # CSP Bottleneck with 3 convolutions
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))

    def forward(self, x):
        return torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1)

当在common.py中修改具体代码后，需在yolo.py中进行相应的修改：

def parse_model(d, ch):  # model_dict, input_channels(3)
    # Parse a YOLOv5 model.yaml dictionary
    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
    anchors, nc, gd, gw, act, ch_mul = (
        d["anchors"],
        d["nc"],
        d["depth_multiple"],
        d["width_multiple"],
        d.get("activation"),
        d.get("channel_multiple"),
    )
    if act:
        Conv.default_act = eval(act)  # redefine default activation, i.e. Conv.default_act = nn.SiLU()
        LOGGER.info(f"{colorstr('activation:')} {act}")  # print
    if not ch_mul:
        ch_mul = 8
    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)

    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
    for i, (f, n, m, args) in enumerate(d["backbone"] + d["head"]):  # from, number, module, args
        m = eval(m) if isinstance(m, str) else m  # eval strings
        for j, a in enumerate(args):
            with contextlib.suppress(NameError):
                args[j] = eval(a) if isinstance(a, str) else a  # eval strings

        n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
        if m in {
            Conv,
            GhostConv,
            Bottleneck,
            GhostBottleneck,
            SPP,
            SPPF,
            DWConv,
            MixConv2d,
            Focus,
            CrossConv,
            BottleneckCSP,
            C3,
            C2,
            C3TR,
            C3SPP,
            C3Ghost,
            nn.ConvTranspose2d,
            DWConvTranspose2d,
            C3x,
        }:
            c1, c2 = ch[f], args[0]
            if c2 != no:  # if not output
                c2 = make_divisible(c2 * gw, ch_mul)

            args = [c1, c2, *args[1:]]
            if m in {BottleneckCSP, C3, C2, C3TR, C3Ghost, C3x}:
                args.insert(2, n)  # number of repeats
                n = 1
        elif m is nn.BatchNorm2d:
            args = [ch[f]]
        elif m is Concat:
            c2 = sum(ch[x] for x in f)
        # TODO: channel, gw, gd
        elif m in {Detect, Segment}:
            args.append([ch[x] for x in f])
            if isinstance(args[1], int):  # number of anchors
                args[1] = [list(range(args[1] * 2))] * len(f)
            if m is Segment:
                args[3] = make_divisible(args[3] * gw, ch_mul)
        elif m is Contract:
            c2 = ch[f] * args[0] ** 2
        elif m is Expand:
            c2 = ch[f] // args[0] ** 2
        else:
            c2 = ch[f]

        m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
        t = str(m)[8:-2].replace("__main__.", "")  # module type
        np = sum(x.numel() for x in m_.parameters())  # number params
        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
        LOGGER.info(f"{i:>3}{str(f):>18}{n_:>3}{np:10.0f}  {t:<40}{str(args):<30}")  # print
        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
        layers.append(m_)
        if i == 0:
            ch = []
        ch.append(c2)
    return nn.Sequential(*layers), sorted(save)

在此段代码中加入了C2,让模型知道并调用C2

接着将C2插入到第2层与第3层之间，即修改yolov5s.yaml文件

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]], # C3*1 = 3, C3*2 = 6, C3*3 = 9
    [-1, 3, C2, [128]], 
    [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
    [-1, 3, C3, [256]],
    [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
    [-1, 6, C3, [512]],
    [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
    [-1, 3, C3, [1024]], # 8
    [-1, 1, SPPF, [1024, 5]], # 9
  ]

模型结构如下：

                 from  n    params  module                                  arguments                     
  0                -1  1      3520  models.common.Conv                      [3, 32, 6, 2, 2]              
  1                -1  1     18560  models.common.Conv                      [32, 64, 3, 2]                
  2                -1  1     18816  models.common.C3                        [64, 64, 1]                   
  3                -1  1     18816  models.common.C2                        [64, 64, 1]                   
  4                -1  1     73984  models.common.Conv                      [64, 128, 3, 2]               
  5                -1  1     74496  models.common.C3                        [128, 128, 1]                 
  6                -1  1    295424  models.common.Conv                      [128, 256, 3, 2]              
  7                -1  2    460800  models.common.C3                        [256, 256, 2]                 
  8                -1  1   1180672  models.common.Conv                      [256, 512, 3, 2]              
  9                -1  1   1182720  models.common.C3                        [512, 512, 1]                 
 10                -1  1    656896  models.common.SPPF                      [512, 512, 5]                 
 11                -1  1    131584  models.common.Conv                      [512, 256, 1, 1]              
 12                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          
 13           [-1, 6]  1         0  models.common.Concat                    [1]                           
 14                -1  1    361984  models.common.C3                        [512, 256, 1, False]          
 15                -1  1     33024  models.common.Conv                      [256, 128, 1, 1]              
 16                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          
 17           [-1, 4]  1         0  models.common.Concat                    [1]                           
 18                -1  1     90880  models.common.C3                        [256, 128, 1, False]          
 19                -1  1    147712  models.common.Conv                      [128, 128, 3, 2]              
 20          [-1, 14]  1         0  models.common.Concat                    [1]                           
 21                -1  1    329216  models.common.C3                        [384, 256, 1, False]          
 22                -1  1    590336  models.common.Conv                      [256, 256, 3, 2]              
...
 24                -1  1   1313792  models.common.C3                        [768, 512, 1, False]          
 25      [17, 20, 23]  1    359805  models.yolo.Detect                      [80, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [256, 384, 768]]