---

🚀🚀 前言 🚀🚀

timm 库实现了最新的几乎所有的具有影响力的视觉模型，它不仅提供了模型的权重，还提供了一个很棒的分布式训练和评估的代码框架，方便后人开发。更难能可贵的是它还在不断地更新迭代新的训练方法，新的视觉模型和优化代码。本章主要介绍如何使用timm替换YOLO系列的主干网络。

---

🔥🔥 YOLO系列实验实战篇：

📖 YOLOv5/v7/v8改进实验（一）之数据准备篇
📖 YOLOv5/v7/v8改进实验（二）之数据增强篇
📖 YOLOv5/v7/v8改进实验（三）之训练技巧篇

📖 YOLOv5/v7/v8改进实验（五）之使用timm更换YOLOv5模型主干网络Backbone篇
📖 YOLOv5/v7/v8改进实验（七）之使用timm更换YOLOv8模型主干网络Backbone篇

更新中…

---

一、timm

官方链接：pytorch-image-models

Pytorch Image Models (timm) 整合了常用的models, layers, utilities, optimizers, schedulers, data-loaders / augmentations, and reference training / validation scripts，它的目的是将各种SOTA模型整合在一起，并具有再现ImageNet训练结果的能力。

1.1 安装

timm环境的安装非常简单，pip直接安装即可，版本越高，模型越多。

pip install timm -i https://mirror.baidu.com/pypi/simple

版本更新：

pip install timm --upgrade -i https://mirror.baidu.com/pypi/simple

1.2 测试模型库

安装完成即可查看timm可供我们使用的所有模型。

# timm-0.9.7
import timmprint(timm.list_models())
print(len(timm.list_models())) # 991

# timm-0.6.13
import timmprint(timm.list_models())
print(len(timm.list_models())) # 964

1.3 加载模型

import torch, timm
from thop import clever_format, profiledevice = torch.device("cuda" if torch.cuda.is_available() else "cpu")
dummy_input = torch.randn(1, 3, 640, 640).to(device)model = timm.create_model('mobileone_s0', pretrained=False, features_only=True)
model.to(device)
model.eval()print(model.feature_info.channels())
for feature in model(dummy_input):print(feature.size())flops, params = profile(model.to(device), (dummy_input,), verbose=False)
params = clever_format(params, "%.3f")
print(f'Total {(flops * 2 / 1E9):.3f} GFLOPS')
print(f'Total {params} params')

PS：其他详细操作可参考官方文档

二、YOLOv5

主要修改models/yolo.py文件中的parse_model和_forward_once函数

替换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)is_backbone = Falselayers, save, c2 = [], [], ch[-1]  # layers, savelist, ch outfor i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, argstry:t = mm = eval(m) if isinstance(m, str) else m  # eval stringsexcept:passfor j, a in enumerate(args):with contextlib.suppress(NameError):try:args[j] = eval(a) if isinstance(a, str) else a  # eval stringsexcept:args[j] = an = 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] ** 2elif isinstance(m, str):t = mm = timm.create_model(m, pretrained=args[0], features_only=True)c2 = m.feature_info.channels()# elif m in {}:#     m = m(*args)#     c2 = m.channelelse:c2 = ch[f]if isinstance(c2, list):is_backbone = Truem_ = mm_.backbone = Trueelse: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 + 4 if is_backbone else 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 + 4 if is_backbone else i) for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelistlayers.append(m_)if i == 0:ch = []if isinstance(c2, list):ch.extend(c2)for _ in range(5 - len(ch)):ch.insert(0, 0)else:ch.append(c2)return nn.Sequential(*layers), sorted(save)def _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)if hasattr(m, 'backbone'):x = m(x)for _ in range(5 - len(x)):x.insert(0, None)for i_idx, i in enumerate(x):if i_idx in self.save:y.append(i)else:y.append(None)x = x[-1]else: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 x

替换BaseModel类中的_forward_once函数

def _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)if hasattr(m, 'backbone'):x = m(x)for _ in range(5 - len(x)):x.insert(0, None)for i_idx, i in enumerate(x):y.append(i if i_idx in self.save else None)x = x[-1]else: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 x

yolov5s-ghostnet.yaml文件配置

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license# Parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.25  # layer channel multiple
anchors:- [10,13, 16,30, 33,23]  # P3/8- [30,61, 62,45, 59,119]  # P4/16- [116,90, 156,198, 373,326]  # P5/32# 0-P1/2
# 1-P2/4
# 2-P3/8
# 3-P4/16
# 4-P5/32# YOLOv5 v6.0 backbone
backbone:# [from, number, module, args][[-1, 1, ghostnet_050, []], # 4[-1, 1, SPPF, [1024, 5]],  # 5]# YOLOv5 v6.0 head
head:[[-1, 1, Conv, [512, 1, 1]], # 6[-1, 1, nn.Upsample, [None, 2, 'nearest']], # 7[[-1, 3], 1, Concat, [1]],  # cat backbone P4 8[-1, 3, C3, [512, False]],  # 9[-1, 1, Conv, [256, 1, 1]], # 10[-1, 1, nn.Upsample, [None, 2, 'nearest']], # 11[[-1, 2], 1, Concat, [1]],  # cat backbone P3 12[-1, 3, C3, [256, False]],  # 13 (P3/8-small)[-1, 1, Conv, [256, 3, 2]], # 14[[-1, 10], 1, Concat, [1]],  # cat head P4 15[-1, 3, C3, [512, False]],  # 16 (P4/16-medium)[-1, 1, Conv, [512, 3, 2]], # 17[[-1, 5], 1, Concat, [1]],  # cat head P5 18[-1, 3, C3, [1024, False]],  # 19 (P5/32-large)[[13, 16, 19], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)]

模型测试

python models/yolo.py --cfg yolov5s-ghostnet.yaml

模型训练

python train.py --cfg yolov5s-ghostnet.yaml