YOLOv5 白皮书-第Y5周：yolo.py文件解读

一、前言

本周任务：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。

二、导入需要的包和基本配置

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
YOLO-specific modules

Usage:
    $ python models/yolo.py --cfg yolov5s.yaml
"""

import argparse
import contextlib
import os
import platform
import sys
from copy import deepcopy
from pathlib import Path

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()))  # relative

from models.common import *
from models.experimental import *
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)

try:
    import thop  # for FLOPs computation
except ImportError:
    thop = None

三、 parse_model函数

这个函数用于将模型的模块拼接起来，搭建完成的网络模型。后续如果需要动模型框架的话，你需要对这个函数做相应的改动。

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 = 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}")  # print
    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, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:
            c1, c2 = ch[f], args[0]
            if c2 != no:  # if not output
                c2 = make_divisible(c2 * gw, 8)

            args = [c1, c2, *args[1:]]
            if m in {BottleneckCSP, C3, 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, 8)
        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)

四、Detect类

Detect模块是用来构建Detect层的，将输入featuremap通过一个卷积操作和公式计算到我们想要的shape,为后面的计算损失或者NMS作准备。

Detect模块代码：

class Detect(nn.Module):
    # YOLOv5 Detect head for detection models
    stride = None  # strides computed during build
    dynamic = False  # force grid reconstruction
    export = False  # export mode

    def __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layer
        super().__init__()
        self.nc = nc  # number of classes
        self.no = nc + 5  # number of outputs per anchor
        self.nl = len(anchors)  # number of detection layers
        self.na = len(anchors[0]) // 2  # number of anchors
        self.grid = [torch.empty(0) for _ in range(self.nl)]  # init grid
        self.anchor_grid = [torch.empty(0) for _ in range(self.nl)]  # init anchor grid
        self.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 conv
        self.inplace = inplace  # use inplace ops (e.g. slice assignment)

    def forward(self, x):
        z = []  # inference output
        for i in range(self.nl):
            x[i] = self.m[i](x[i])  # conv
            bs, _, 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:  # inference
                if 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]  # xy
                    wh = (wh.sigmoid() * 2) ** 2 * self.anchor_grid[i]  # wh
                    y = 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]  # xy
                    wh = (wh * 2) ** 2 * self.anchor_grid[i]  # wh
                    y = 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].device
        t = self.anchors[i].dtype
        shape = 1, self.na, ny, nx, 2  # grid shape
        y, 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 compatibility
        grid = torch.stack((xv, yv), 2).expand(shape) - 0.5  # add grid offset, i.e. y = 2.0 * x - 0.5
        anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape)
        return grid, anchor_grid

五、BaseModel类

这个模块是整个模型的搭建模块。且yolov5的作者将这个模块的功能写的很全，不光包含模型的搭建，还扩展了很多功能如：特征可视化，打印模型信息、TTA推理增强、融合Conv+Bn加速推理、模型搭载nms功能、autoshape函数：模型包含前处理、推理、后处理的模块(预处理+推理+nms)。感兴趣的可以仔细看看，不感兴趣的可以直接看init和forward两个函数即可。

BaseModel模块代码：

class BaseModel(nn.Module):
    # YOLOv5 base model
    def forward(self, x, profile=False, visualize=False):
        return self._forward_once(x, profile, visualize)  # single-scale inference, train

    def _forward_once(self, x, profile=False, visualize=False):
        y, dt = [], []  # outputs
        for m in self.model:
            if m.f != -1:  # if not from previous layer
                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
            if profile:
                self._profile_one_layer(m, x, dt)
            x = m(x)  # run
            y.append(x if m.i in self.save else None)  # save output
            if visualize:
                feature_visualization(x, m.type, m.i, save_dir=visualize)
        return x

    def _profile_one_layer(self, m, x, dt):
        c = m == self.model[-1]  # is final layer, copy input as inplace fix
        o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPs
        t = 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() layers
        LOGGER.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 conv
                delattr(m, 'bn')  # remove batchnorm
                m.forward = m.forward_fuse  # update forward
        self.info()
        return self

    def info(self, verbose=False, img_size=640):  # print model information
        model_info(self, verbose, img_size)

    def _apply(self, fn):
        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
        self = 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

六、调整模型

1. common.py中生成C2

复制c3生成c2

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

2. yolo.py的parse_model中增加c2

 if m in {
                Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
                BottleneckCSP, C2, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:
            c1, c2 = ch[f], args[0]
            if c2 != no:  # if not output
                c2 = make_divisible(c2 * gw, 8)

            args = [c1, c2, *args[1:]]
            if m in {BottleneckCSP, C2, C3, C3TR, C3Ghost, C3x}:
                args.insert(2, n)  # number of repeats
                n = 1

3. yolov5s.yaml中增加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]],
   [-1, 3, C2, [128]], # todo
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

4. 运行

python train.py --img 900 --batch 2 --epoch 100 --data paper_data/ab.yaml --cfg models/yolov5s.yaml --weights yolov5s.pt

(k39) PS E:\doc\1.学院\3.学习培训\21.365深度学习训练营\y2\yolov5-master> python train.py --img 900 --batch 2 --epoch 2 --data paper_data/ab.yaml --cfg models/yolov5s.yaml --weights yolov5s.pt  
train: weights=yolov5s.pt, cfg=models/yolov5s.yaml, data=paper_data/ab.yaml, hyp=data\hyps\hyp.scratch-low.yaml, epochs=2, batch_size=2, imgsz=900, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, noplots=False, evolve=None, bucket=, cache=None, image_weights=False, device=, multi_scale=False, single_cls=False, optimizer=SGD, sync_bn=False, workers=8, project=runs\train, name=exp, exist_ok=False, quad=False, cos_lr=False, label_smoothing=0.0, patience=100, freeze=[0], save_period=-1, seed=0, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest
github: skipping check (not a git repository), for updates see https://github.com/ultralytics/yolov5
YOLOv5  2022-12-7 Python-3.9.15 torch-1.13.0+cpu CPU

hyperparameters: lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.
0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0
ClearML: run 'pip install clearml' to automatically track, visualize and remotely train YOLOv5  in ClearML
Comet: run 'pip install comet_ml' to automatically track and visualize YOLOv5  runs in Comet
TensorBoard: Start with 'tensorboard --logdir runs\train', view at http://localhost:6006/
Overriding model.yaml nc=80 with nc=4

                 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  2    115712  models.common.C3                        [128, 128, 2]
  6                -1  1    295424  models.common.Conv                      [128, 256, 3, 2]
  7                -1  3    625152  models.common.C3                        [256, 256, 3]
  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]
 23          [-1, 10]  1         0  models.common.Concat                    [1]
 24                -1  1   1313792  models.common.C3                        [768, 512, 1, False]
 25      [17, 20, 23]  1     38097  models.yolo.Detect                      [4, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [256, 384, 768]]
YOLOv5s summary: 232 layers, 7226897 parameters, 7226897 gradients, 17.2 GFLOPs

Transferred 66/379 items from yolov5s.pt
WARNING  --img-size 900 must be multiple of max stride 32, updating to 928
optimizer: SGD(lr=0.01) with parameter groups 62 weight(decay=0.0), 65 weight(decay=0.0005), 65 bias
train: Scanning E:\doc\1.学院\3.学习培训\21.365深度学习训练营\y2\yolov5-master\paper_data\train... 180 images, 0 backgrounds, 0 corrupt: 100%|██████████| 180/180 [00:04<00:00, 36.18i
train: WARNING  Cache directory E:\doc\1.\3.\21.365\y2\yolov5-master\paper_data is not writeable: [WinError 183] : 'E:\\doc\\1.\\3.\\21.365\\y2\\yolov5-master\\paper_data\\train.cache.npy' -> 'E:\\doc\\1.\\3.\\21.365\\y2\\yolov5-master\\paper_data\\train.cache'
val: Scanning E:\doc\1.学院\3.学习培训\21.365深度学习训练营\y2\yolov5-master\paper_data\val.cache... 20 images, 0 backgrounds, 0 corrupt: 100%|██████████| 20/20 [00:00<?, ?it/s]

AutoAnchor: 4.82 anchors/target, 1.000 Best Possible Recall (BPR). Current anchors are a good fit to dataset
Plotting labels to runs\train\exp19\labels.jpg... 
Image sizes 928 train, 928 val
Using 2 dataloader workers
Logging results to runs\train\exp19
Starting training for 2 epochs...

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
        0/1         0G     0.1086    0.06274    0.04353          9        928:   0%|          | 0/90 [00:02<?, ?it/s]WARNING  TensorBoard graph visualization failure Sizes of tensors must match except in dimension 1. Expected size 58 but got size 57 for tensor number 1 in the list.
        0/1         0G     0.1054    0.06577     0.0437         11        928: 100%|██████████| 90/90 [03:21<00:00,  2.23s/it]
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:06<00:00,  1.31s/it]
                   all         20         60   0.000787      0.109   0.000597   7.26e-05

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
        1/1         0G     0.1004    0.06878    0.04284          5        928: 100%|██████████| 90/90 [03:17<00:00,  2.20s/it]
                 Class     Images  Instances          P          R      mAP50   mAP50-95:  40%|████      | 2/5 [00:03<00:04,  1.65s/it]WARNING  NMS time limit 0.700s exceeded
                 Class     Images  Instances          P          R      mAP50   mAP50-95:  80%|████████  | 4/5 [00:07<00:01,  1.82s/it]WARNING  NMS time limit 0.700s exceeded
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:08<00:00,  1.80s/it]
                   all         20         60    0.00232      0.251    0.00263   0.000611

2 epochs completed in 0.115 hours.
Optimizer stripped from runs\train\exp19\weights\last.pt, 15.0MB
Optimizer stripped from runs\train\exp19\weights\best.pt, 15.0MB

Validating runs\train\exp19\weights\best.pt...
Fusing layers... 
YOLOv5s summary: 170 layers, 7217201 parameters, 0 gradients, 17.0 GFLOPs
                 Class     Images  Instances          P          R      mAP50   mAP50-95:  40%|████      | 2/5 [00:02<00:04,  1.53s/it]WARNING  NMS time limit 0.700s exceeded
                 Class     Images  Instances          P          R      mAP50   mAP50-95:  80%|████████  | 4/5 [00:06<00:01,  1.71s/it]WARNING  NMS time limit 0.700s exceeded
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:08<00:00,  1.68s/it]
                   all         20         60    0.00196      0.213     0.0024   0.000587
                banana         20         16    0.00292      0.312    0.00268   0.000533
           snake fruit         20         20          0          0          0          0
          dragon fruit         20         11          0          0          0          0
             pineapple         20         13    0.00494      0.538    0.00693    0.00181
Results saved to runs\train\exp19