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|接辅导、项目定制
本次训练是在前文《YOLOv5白皮书-第Y2周:训练自己的数据集》的基础上进行的。
前言
文件位置:./models/yolo.Py
这个文件是YOLOv5网络模型的搭建文件,如果你想改进YOLOv5,那么这个文件是你必须进行修改的文件之一。文件内容看起来多,其实真正有用的代码不多的,重点理解好文中提到的一个函数两个类即可。
注:由于YOLOv5版本众多,同一个文件对于细节处你可能会看到不同的版本,不用担心这都是正常的,注意把握好整体架构即可。
任务:将YOLOv5s网络模型中的C3模块按照下图方式修改形成C2模块,并将C2模块插入第2层与第3层之间,且跑通YOLOv5s。
任务提示:
提示1:需要修改common.yaml、yolo.py、yolov5s.yaml 文件。
提示2:C2 模块与 C3模块是非常相似的两个模块,我们要插入C2 到模型当中,只需要找到哪里有 C3 模块,然后在其附近加上C2 即可。
1、需要了解的函数和类
1.1 导入需要的包和基本配置
import argparse # 解析命令行参数模块
import contextlib
import os
import platform
import sys # sys系统模块 包含了与Python解释器和它的环境有关的函数
from copy import deepcopy # 数据拷贝模块 深拷贝
from pathlib import Path # Path将str转换为Path对象,使字符串路径易于操作的模块FILE = Path(__file__).resolve()
ROOT = FILE.parents[1] # YOLOv5 root directory
if str(ROOT) not in sys.path:sys.path.append(str(ROOT)) # add ROOT to PATH
if platform.system() != 'Windows':ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relativefrom models.common import * # noqa
from models.experimental import * # noqa
from utils.autoanchor import check_anchor_order
from utils.general import LOGGER, check_version, check_yaml, make_divisible, print_args
from utils.plots import feature_visualization
from utils.torch_utils import (fuse_conv_and_bn, initialize_weights, model_info, profile, scale_img, select_device,time_sync)#导入thop包 用于计算FLOPS
try:import thop # for FLOPs computation
except ImportError:thop = None
- argparse 用于命令行参数解析
- contextlib 用于上下文管理
- os 和 platform 用于操作系统和平台相关的功能
- deepcopy 用于深拷贝对象
- Path 用于处理文件路径
- 尝试导入 thop 库,用于计算模型的浮点运算量
FILE 是当前文件的绝对路径
ROOT 是当前文件的父目录的父目录
1.2 parse_model函数
def parse_model(d, ch): # model_dict, input_channels(3)# Parse a YOLOv5 model.yaml dictionaryLOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}")anchors, nc, gd, gw, act = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'], d.get('activation')if act:Conv.default_act = eval(act) # redefine default activation, i.e. Conv.default_act = nn.SiLU()LOGGER.info(f"{colorstr('activation:')} {act}") # printna = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchorsno = na * (nc + 5) # number of outputs = anchors * (classes + 5)layers, save, c2 = [], [], ch[-1] # layers, savelist, ch outfor i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, argsm = eval(m) if isinstance(m, str) else m # eval stringsfor j, a in enumerate(args):with contextlib.suppress(NameError):args[j] = eval(a) if isinstance(a, str) else a # eval stringsn = n_ = max(round(n * gd), 1) if n > 1 else n # depth gainif m in {Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:c1, c2 = ch[f], args[0]if c2 != no: # if not outputc2 = make_divisible(c2 * gw, 8)args = [c1, c2, *args[1:]]if m in {BottleneckCSP, C3, C3TR, C3Ghost, C3x}:args.insert(2, n) # number of repeatsn = 1elif m is nn.BatchNorm2d:args = [ch[f]]elif m is Concat:c2 = sum(ch[x] for x in f)# TODO: channel, gw, gdelif m in {Detect, Segment}:args.append([ch[x] for x in f])if isinstance(args[1], int): # number of anchorsargs[1] = [list(range(args[1] * 2))] * len(f)if m is Segment:args[3] = make_divisible(args[3] * gw, 8)elif m is Contract:c2 = ch[f] * args[0] ** 2elif m is Expand:c2 = ch[f] // args[0] ** 2else:c2 = ch[f]m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # modulet = str(m)[8:-2].replace('__main__.', '') # module typenp = sum(x.numel() for x in m_.parameters()) # number paramsm_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number paramsLOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f} {t:<40}{str(args):<30}') # printsave.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelistlayers.append(m_)if i == 0:ch = []ch.append(c2)return nn.Sequential(*layers), sorted(save)
该函数将模型的模块拼接起来,搭建完成网络模型。如果要改动模型框架,需要修改此函数。
-
从配置信息中提取 anchors、nc(类别数)、gd(深度倍数)、gw(宽度倍数)和激活函数类型。
-
遍历配置中的 backbone 和 head,这两个部分描述了模型的骨干网络和检测头。
-
对于每个模块,根据其类型进行相应的处理:
3.1 如果是卷积层(如 Conv、Bottleneck 等),根据深度倍数和宽度倍数调整输出通道数,并创建相应的模块。
3.2 如果是BatchNorm2d,则根据输入通道数创建模块。
3.3 如果是 Concat,则根据输入通道数的总和创建模块。
3.4 如果是 Detect 或Segment,则根据输入通道数列表创建模块,并根据宽度倍数调整参数。
3.5 如果是 Contract 或Expand,则根据输入通道数和倍数调整输出通道数。 -
创建模块实例,并记录相关信息,如模块类型、参数数量等。
-
将构建好的模块添加到网络层序列中,并将需要保存输出的层索引记录下来。
-
最后返回构建好的模型和需要保存输出的层索引。
1.3 Detect类
class Detect(nn.Module):# YOLOv5 Detect head for detection modelsstride = None # strides computed during builddynamic = False # force grid reconstructionexport = False # export modedef __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layersuper().__init__()self.nc = nc # number of classesself.no = nc + 5 # number of outputs per anchorself.nl = len(anchors) # number of detection layersself.na = len(anchors[0]) // 2 # number of anchorsself.grid = [torch.empty(0) for _ in range(self.nl)] # init gridself.anchor_grid = [torch.empty(0) for _ in range(self.nl)] # init anchor gridself.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2)) # shape(nl,na,2)self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output convself.inplace = inplace # use inplace ops (e.g. slice assignment)def forward(self, x):z = [] # inference outputfor i in range(self.nl):x[i] = self.m[i](x[i]) # convbs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()if not self.training: # inferenceif self.dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)if isinstance(self, Segment): # (boxes + masks)xy, wh, conf, mask = x[i].split((2, 2, self.nc + 1, self.no - self.nc - 5), 4)xy = (xy.sigmoid() * 2 + self.grid[i]) * self.stride[i] # xywh = (wh.sigmoid() * 2) ** 2 * self.anchor_grid[i] # why = torch.cat((xy, wh, conf.sigmoid(), mask), 4)else: # Detect (boxes only)xy, wh, conf = x[i].sigmoid().split((2, 2, self.nc + 1), 4)xy = (xy * 2 + self.grid[i]) * self.stride[i] # xywh = (wh * 2) ** 2 * self.anchor_grid[i] # why = torch.cat((xy, wh, conf), 4)z.append(y.view(bs, self.na * nx * ny, self.no))return x if self.training else (torch.cat(z, 1), ) if self.export else (torch.cat(z, 1), x)def _make_grid(self, nx=20, ny=20, i=0, torch_1_10=check_version(torch.__version__, '1.10.0')):d = self.anchors[i].devicet = self.anchors[i].dtypeshape = 1, self.na, ny, nx, 2 # grid shapey, x = torch.arange(ny, device=d, dtype=t), torch.arange(nx, device=d, dtype=t)yv, xv = torch.meshgrid(y, x, indexing='ij') if torch_1_10 else torch.meshgrid(y, x) # torch>=0.7 compatibilitygrid = torch.stack((xv, yv), 2).expand(shape) - 0.5 # add grid offset, i.e. y = 2.0 * x - 0.5anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape)return grid, anchor_grid
-
stride:用于存储在构建期间计算的步幅(strides),在前向传播中使用。
-
dynamic 和 export:这两个属性都是布尔值,分别用于指示是否强制进行网格重构和导出模式。
-
init 方法:初始化函数,接受一些参数,包括 nc(类别数)、anchors(锚框)、ch(通道数)、inplace(是否使用原地操作)。
3.1 nc:类别数
3.2. no:每个锚框的输出数(类别数加上5)
3.3 nl:检测层的数量(锚框的数量)
3.4 na:每个检测层的锚框数量
3.5 grid 和 anchor_grid:用于存储网格和锚框网格的空列表
3.6 anchors:将锚框转换为张量并注册为缓冲区
3.7 m:输出卷积的模块列表 -
forward 方法:前向传播函数,接受输入张量 x,并返回输出张量。
4.1. 循环遍历每个检测层
4.2. 对输入进行卷积操作,并调整形状以适应后续处理
4.3. 如果不是训练模式,则进行推理操作
4.4. 根据是否是分割模式,对不同的输出进行不同的处理
4.5. 将处理后的输出添加到列表 z 中
4.6. 返回输出张量x(如果是训练模式)、合并后的检测结果张量(如果是导出模式)或者分别返回这两者(如果不是训练模式且不是导出模式) -
_make_grid 方法:用于生成网格和锚框网格。
5.1. 创建网格和锚框网格
5.2. 根据输入的尺寸和索引调整形状
5.3. 返回网格和锚框网格
1.4、BaseModel 类
class BaseModel(nn.Module):# YOLOv5 base modeldef forward(self, x, profile=False, visualize=False):return self._forward_once(x, profile, visualize) # single-scale inference, traindef _forward_once(self, x, profile=False, visualize=False):y, dt = [], [] # outputsfor m in self.model:if m.f != -1: # if not from previous layerx = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layersif profile:self._profile_one_layer(m, x, dt)x = m(x) # runy.append(x if m.i in self.save else None) # save outputif visualize:feature_visualization(x, m.type, m.i, save_dir=visualize)return xdef _profile_one_layer(self, m, x, dt):c = m == self.model[-1] # is final layer, copy input as inplace fixo = thop.profile(m, inputs=(x.copy() if c else x, ), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPst = time_sync()for _ in range(10):m(x.copy() if c else x)dt.append((time_sync() - t) * 100)if m == self.model[0]:LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s} module")LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f} {m.type}')if c:LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s} Total")def fuse(self): # fuse model Conv2d() + BatchNorm2d() layersLOGGER.info('Fusing layers... ')for m in self.model.modules():if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):m.conv = fuse_conv_and_bn(m.conv, m.bn) # update convdelattr(m, 'bn') # remove batchnormm.forward = m.forward_fuse # update forwardself.info()return selfdef info(self, verbose=False, img_size=640): # print model informationmodel_info(self, verbose, img_size)def _apply(self, fn):# Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffersself = super()._apply(fn)m = self.model[-1] # Detect()if isinstance(m, (Detect, Segment)):m.stride = fn(m.stride)m.grid = list(map(fn, m.grid))if isinstance(m.anchor_grid, list):m.anchor_grid = list(map(fn, m.anchor_grid))return self
BaseModel 类是 YOLOv5 模型的基类,包含了一些用于模型前向推断、性能评估和模型信息打印等方法。
-
forward(self, x, profile=False, visualize=False): 定义了模型的前向传播过程。根据参数 profile 和 visualize 的设置,选择是否进行性能分析和特征可视化。调用了 _forward_once 方法来执行单次前向传播。
-
_forward_once(self, x, profile=False, visualize=False): 单次前向传播过程。遍历模型中的每一层,根据保存输出的层索引记录下需要的特征。如果设置了 profile 参数,则调用 _profile_one_layer 方法进行性能分析。如果设置了 visualize 参数,则调用 feature_visualization 方法进行特征可视化。
-
_profile_one_layer(self, m, x, dt): 对单个模块进行性能分析。计算模块的 FLOPs(浮点运算量)和运行时间,并输出日志信息。
-
fuse(self): 将模型中的 Conv2d() 和 BatchNorm2d() 层融合为单个层。通过遍历模型中的每个模块,对满足条件的模块进行融合操作,并更新模型结构。
-
info(self, verbose=False, img_size=640): 打印模型的相关信息。调用了 model_info 方法来输出模型的结构、参数数量等信息。
-
_apply(self, fn): 应用给定的函数到模型的张量上,例如 to(), cpu(), cuda(), half()。在这个方法中,除了将函数应用到模型的张量参数上之外,还更新了 Detect 或 Segment 类型模块中的一些属性,如 stride、grid 和 anchor_grid。
1.5 DetectionModel类
class DetectionModel(BaseModel):# YOLOv5 detection modeldef __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classessuper().__init__()if isinstance(cfg, dict):self.yaml = cfg # model dictelse: # is *.yamlimport yaml # for torch hubself.yaml_file = Path(cfg).namewith open(cfg, encoding='ascii', errors='ignore') as f:self.yaml = yaml.safe_load(f) # model dict# Define modelch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channelsif nc and nc != self.yaml['nc']:LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")self.yaml['nc'] = nc # override yaml valueif anchors:LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')self.yaml['anchors'] = round(anchors) # override yaml valueself.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelistself.names = [str(i) for i in range(self.yaml['nc'])] # default namesself.inplace = self.yaml.get('inplace', True)# Build strides, anchorsm = self.model[-1] # Detect()if isinstance(m, (Detect, Segment)):s = 256 # 2x min stridem.inplace = self.inplaceforward = lambda x: self.forward(x)[0] if isinstance(m, Segment) else self.forward(x)m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))]) # forwardcheck_anchor_order(m)m.anchors /= m.stride.view(-1, 1, 1)self.stride = m.strideself._initialize_biases() # only run once# Init weights, biasesinitialize_weights(self)self.info()LOGGER.info('')def forward(self, x, augment=False, profile=False, visualize=False):if augment:return self._forward_augment(x) # augmented inference, Nonereturn self._forward_once(x, profile, visualize) # single-scale inference, traindef _forward_augment(self, x):img_size = x.shape[-2:] # height, widths = [1, 0.83, 0.67] # scalesf = [None, 3, None] # flips (2-ud, 3-lr)y = [] # outputsfor si, fi in zip(s, f):xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))yi = self._forward_once(xi)[0] # forward# cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1]) # saveyi = self._descale_pred(yi, fi, si, img_size)y.append(yi)y = self._clip_augmented(y) # clip augmented tailsreturn torch.cat(y, 1), None # augmented inference, traindef _descale_pred(self, p, flips, scale, img_size):# de-scale predictions following augmented inference (inverse operation)if self.inplace:p[..., :4] /= scale # de-scaleif flips == 2:p[..., 1] = img_size[0] - p[..., 1] # de-flip udelif flips == 3:p[..., 0] = img_size[1] - p[..., 0] # de-flip lrelse:x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale # de-scaleif flips == 2:y = img_size[0] - y # de-flip udelif flips == 3:x = img_size[1] - x # de-flip lrp = torch.cat((x, y, wh, p[..., 4:]), -1)return pdef _clip_augmented(self, y):# Clip YOLOv5 augmented inference tailsnl = self.model[-1].nl # number of detection layers (P3-P5)g = sum(4 ** x for x in range(nl)) # grid pointse = 1 # exclude layer counti = (y[0].shape[1] // g) * sum(4 ** x for x in range(e)) # indicesy[0] = y[0][:, :-i] # largei = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e)) # indicesy[-1] = y[-1][:, i:] # smallreturn ydef _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency# https://arxiv.org/abs/1708.02002 section 3.3# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.m = self.model[-1] # Detect() modulefor mi, s in zip(m.m, m.stride): # fromb = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85)b.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)b.data[:, 5:5 + m.nc] += math.log(0.6 / (m.nc - 0.99999)) if cf is None else torch.log(cf / cf.sum()) # clsmi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)Model = DetectionModel # retain YOLOv5 'Model' class for backwards compatibility
DetectionModel 类是基于 BaseModel 类构建的,用于实现 YOLOv5 目标检测模型。它继承了 BaseModel 类的一些方法,并根据 YOLOv5 模型的配置文件初始化模型。
-
init(self, cfg=‘yolov5s.yaml’, ch=3, nc=None, anchors=None): 初始化方法,接收模型的配置文件路径 cfg、输入通道数 ch、类别数 nc 和 anchors。首先根据配置文件初始化模型,然后根据传入的参数进行相应的修改,如修改输入通道数、类别数或 anchors。接着构建模型,解析配置文件并初始化模型的权重。最后打印模型的信息。
-
forward(self, x, augment=False, profile=False, visualize=False): 模型的前向传播方法。如果设置了 augment 参数,则执行增强推断,即对输入图像进行尺度变换和翻转操作,然后进行单次前向传播。如果未设置 augment 参数,则执行单次前向传播。根据参数 profile 和 visualize 的设置,选择是否进行性能分析和特征可视化。
-
_forward_augment(self, x): 执行增强推断的方法。根据预设的尺度因子和翻转方式,对输入图像进行处理,然后进行单次前向传播。最后对预测结果进行逆操作,将结果还原到原始图像尺寸。
-
_descale_pred(self, p, flips, scale, img_size): 对增强推断得到的预测结果进行逆操作,将预测框的坐标还原到原始图像尺寸。
-
_clip_augmented(self, y): 对增强推断得到的预测结果进行裁剪,去除多余的预测框。
-
_initialize_biases(self, cf=None): 初始化模型中的偏置项。根据目标检测中的一些规则,调整偏置项的值以适应目标检测任务。
2、代码修改
根据前言所述,C2 模块与 C3模块是非常相似的两个模块,我们要插入C2 到模型当中,只需要找到哪里有 C3 模块,然后在其附近加上C2 即可,如下图所示:
C2模块结构图:
算法修改示意图:
2.1 修改common.py
C2模块是在C3模块的基础上修改的,但C3模块不能去除,要保留的。C2模块的代码如下所示(为了方便比较,把C3模块代码也放进来了):
class C3(nn.Module):# CSP Bottleneck with 3 convolutionsdef __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):"""Initializes C3 module with options for channel count, bottleneck repetition, shortcut usage, groupconvolutions, and expansion."""super().__init__()c_ = int(c2 * e) # hidden channelsself.cv1 = Conv(c1, c_, 1, 1)self.cv2 = Conv(c1, c_, 1, 1)self.cv3 = Conv(2 * c_, c2, 1) # optional act=FReLU(c2)self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))def forward(self, x):"""Performs forward propagation using concatenated outputs from two convolutions and a Bottleneck sequence."""return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))# 原文件没有C2模块,这是在C3模块的基础上进行修改的,就是把C3模块的self.cv3去掉,主要是把forward(self, x)中的self.cv3去掉
class C2(nn.Module):# CSP Bottleneck with 2 convolutionsdef __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):"""Initializes C2 module with options for channel count, bottleneck repetition, shortcut usage, groupconvolutions, and expansion."""super().__init__()c_ = int(c2 * e) # hidden channelsself.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):"""Performs forward propagation using concatenated outputs from two convolutions and a Bottleneck sequence."""return torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1)
2.2 修改yolo.py
在parse_model函数中添加C2,如下所示:
if m in {Conv,GhostConv,Bottleneck,GhostBottleneck,SPP,SPPF,DWConv,MixConv2d,Focus,CrossConv,BottleneckCSP,C3,C2, #原代码中没有C2,现在添加了C2C3TR,C3SPP,C3Ghost,nn.ConvTranspose2d,DWConvTranspose2d,C3x,}:c1, c2 = ch[f], args[0]if c2 != no: # if not outputc2 = make_divisible(c2 * gw, ch_mul)#下面的代码中原来是没有C2,现在添加了C2(不是指小写的c2)args = [c1, c2, *args[1:]]if m in {BottleneckCSP, C3, C2, C3TR, C3Ghost, C3x}: #添加C2args.insert(2, n) # number of repeatsn = 1
在yolo.py的开头,还要把C2添加上去,如下所示:
from models.common import (C3,C2, #原来没有C2,现在添加C2C3SPP,C3TR,SPP,SPPF,Bottleneck,BottleneckCSP,C3Ghost,C3x,Classify,Concat,Contract,Conv,CrossConv,DetectMultiBackend,DWConv,DWConvTranspose2d,Expand,Focus,GhostBottleneck,GhostConv,Proto,
)
2.3 修改yolov5s.yaml
在backbone中,在第2层和第3层之间添加C2。
# YOLOv5 v6.0 backbone
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]], #2[-1, 3, C2, [128]], #原来没有这层的,现在加了C2,多了一层[-1, 1, Conv, [256, 3, 2]], # 3-P3/8[-1, 6, C3, [256]], #4[-1, 1, Conv, [512, 3, 2]], # 5-P4/16[-1, 9, C3, [512]], #6[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32[-1, 3, C3, [1024]], #8[-1, 1, SPPF, [1024, 5]], # 9]
因为训练数据的类别是[“banana”, “snake fruit”, “dragon fruit”, “pineapple”],只有4种,所以在yolov5s.yaml还要把nc修改为4,如下所示:
# Parameters
nc: 4 # number of classes,原文是80,因为要训练的数据集只有4种类别,所以把80修改为4
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
2.4 代码运行
开始用自己的数据集训练模型,在项目目录中打开cmd。
如果电脑有GPU,则在cmd中输入命令:
python train.py–img 900 --batch 2 --epoch 50 --data data/ab.yaml --cfg models/yolov5s.yaml --weights weights/yolov5s.pt --device ‘0’
如果电脑没有GPU,则在cmd中输入命令:
python train.py --img 900 --batch 2 --epoch 50 --data data/ab.yaml --cfg models/yolov5s.yaml --weights weights/yolov5s.pt --device cpu
就可以直接训练自己的数据集啦,训练结果如下所示:
3、总结
要知道在common.py中如何把C3模块修改成C2模块,并知道在yolo.py和yolov5s.yaml把C2输入到哪里。