yolov5中commom.py代码解读

0.导入需要的包和基本配置

import ast
import contextlib
import json
import math                # 数学函数模块
import platform
import warnings
import zipfile
from collections import OrderedDict, namedtuple
from copy import copy      # 数据拷贝模块，分浅拷贝和深拷贝
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
from urllib.parse import urlparse

import cv2
import numpy as np          # numpy数组操作模块
import pandas as pd         # pandas数组操作模块
import requests             # Python的HTTP客户端库
import torch                # pytorch深度学习框架
import torch.nn as nn       # 专门为神经网络设计的模块化接口
from IPython.display import display
from PIL import Image       # 图像基础操作模块
from torch.cuda import amp  # 混合精度训练模块

from utils import TryExcept
from utils.dataloaders import exif_transpose, letterbox
from utils.general import (LOGGER, ROOT, Profile, check_requirements, check_suffix, check_version, colorstr,
                           increment_path, is_notebook, make_divisible, non_max_suppression, scale_boxes, xywh2xyxy,
                           xyxy2xywh, yaml_load)
from utils.plots import Annotator, colors, save_one_box
from utils.torch_utils import copy_attr, smart_inference_mode

1.conv

class Conv(nn.Module):
    # Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)
    default_act = nn.SiLU()  # default activation

    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
        ''' 在Focus、Bottleneck、BottleneckCSP、C3、SPP、DWConv、TransformerBlock等模块中调用
        Standard convolution : conv + BN + act
        :params c1: 输入的channel值
        :params c2: 输出的channel值
        :params k: 卷积的kernel_size
        :params s: 卷积的stride
        :params p: 卷积的padding，默认是None，可以通过autopad自行计算需要的padding值
        :params g: 卷积的groups数，1就是普通的卷积，>1就是深度可分离卷积
        :params act: 激活函数类型，True就是SiLU()/Swish，False就是不使用激活函数，类型是nn.Module就使用传进来的激活函数类型
        '''
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

    def forward(self, x):
        return self.act(self.bn(self.conv(x)))

    def forward_fuse(self, x):
        ''' 用于Model类的fuse函数
        融合 Conv + BN 加速推理，一般用于测试/验证阶段
        '''
        return self.act(self.conv(x))

2.Bottleneck

class Bottleneck(nn.Module):
    # Standard bottleneck  Conv + Conv + shortcut
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
        ''' 在BottleneckCSP和yolo.py的parse_model函数中被调用
        :params c1: 第一个卷积的输入channel
        :params c2: 第二个卷积的输入channel
        :params shortcut: bool值，是否有shortcut连接，默认True
        :params g: 卷积分组的个数，=1普通卷积，>1深度可分离卷积
        :params e: expansion ratio，e*c2就是第一个卷积的输出channel=第二个卷积的输入channel
        '''
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)      # 1x1
        self.cv2 = Conv(c_, c2, 3, 1, g=g) # 3x3
        self.add = shortcut and c1 == c2   # shortcut=Ture & c1==c2 才能做shortcut

    def forward(self, x):
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))

3 BottleneckCSP

C3

class C3(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
        ''' 在C3RT模块和yolo.py的parse_model函数中被调用
        :params c1: 整个C3的输入channel
        :params c2: 整个C3的输出channel
        :params n: 有n个子模块[Bottleneck/CrossConv]
        :params shortcut: bool值，子模块[Bottlenec/CrossConv]中是否有shortcut，默认True
        :params g: 子模块[Bottlenec/CrossConv]中的3x3卷积类型，=1普通卷积，>1深度可分离卷积
        :params e: expansion ratio，e*c2=中间其它所有层的卷积核个数=中间所有层的的输入输出channel
        '''
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.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)))
        # 实验性 CrossConv
        #self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])

    def forward(self, x):
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))