目标检测算法改进系列之Backbone替换为ConvNextV2

ConvNextV2

受掩码自编码机制的启发，本文在 ConvNeXt 的架构基础上延伸出了一个完全卷积掩码自编码器框架——ConvNeXt V2，同时作者设计了一个全新的全局响应归一化(Global Response Normalization, GRN)层以增强原始 ConvNeXt 模块通道间的特征竞争，从而捕获更具有判别力的通道特征。

ConvNeXt V2 最终在各种识别基准上的性能，包括 ImageNet 分类、COCO 检测和 ADE20K 分割任务上均取得了极具竞争力的结果，其中最小的模型仅 3.7M 参数可获取 76.7% top-1 准确率，而最大的模型约 650M 参数则能达到 88.9% 准确率。

原文地址：ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders

ConvNextV2效果对比
ConvNextV2结构对比

代码实现

ConvNextV2定义

# Copyright (c) Meta Platforms, Inc. and affiliates.

# All rights reserved.

# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.

import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
from timm.models.layers import trunc_normal_, DropPath

__all__ = ['convnextv2_atto', 'convnextv2_femto', 'convnextv2_pico', 'convnextv2_nano', 'convnextv2_tiny', 'convnextv2_base', 'convnextv2_large', 'convnextv2_huge']

class LayerNorm(nn.Module):
    """ LayerNorm that supports two data formats: channels_last (default) or channels_first. 
    The ordering of the dimensions in the inputs. channels_last corresponds to inputs with 
    shape (batch_size, height, width, channels) while channels_first corresponds to inputs 
    with shape (batch_size, channels, height, width).
    """
    def __init__(self, normalized_shape, eps=1e-6, data_format="channels_last"):
        super().__init__()
        self.weight = nn.Parameter(torch.ones(normalized_shape))
        self.bias = nn.Parameter(torch.zeros(normalized_shape))
        self.eps = eps
        self.data_format = data_format
        if self.data_format not in ["channels_last", "channels_first"]:
            raise NotImplementedError 
        self.normalized_shape = (normalized_shape, )
    
    def forward(self, x):
        if self.data_format == "channels_last":
            return F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
        elif self.data_format == "channels_first":
            u = x.mean(1, keepdim=True)
            s = (x - u).pow(2).mean(1, keepdim=True)
            x = (x - u) / torch.sqrt(s + self.eps)
            x = self.weight[:, None, None] * x + self.bias[:, None, None]
            return x

class GRN(nn.Module):
    """ GRN (Global Response Normalization) layer
    """
    def __init__(self, dim):
        super().__init__()
        self.gamma = nn.Parameter(torch.zeros(1, 1, 1, dim))
        self.beta = nn.Parameter(torch.zeros(1, 1, 1, dim))

    def forward(self, x):
        Gx = torch.norm(x, p=2, dim=(1,2), keepdim=True)
        Nx = Gx / (Gx.mean(dim=-1, keepdim=True) + 1e-6)
        return self.gamma * (x * Nx) + self.beta + x

class Block(nn.Module):
    """ ConvNeXtV2 Block.
    
    Args:
        dim (int): Number of input channels.
        drop_path (float): Stochastic depth rate. Default: 0.0
    """
    def __init__(self, dim, drop_path=0.):
        super().__init__()
        self.dwconv = nn.Conv2d(dim, dim, kernel_size=7, padding=3, groups=dim) # depthwise conv
        self.norm = LayerNorm(dim, eps=1e-6)
        self.pwconv1 = nn.Linear(dim, 4 * dim) # pointwise/1x1 convs, implemented with linear layers
        self.act = nn.GELU()
        self.grn = GRN(4 * dim)
        self.pwconv2 = nn.Linear(4 * dim, dim)
        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()

    def forward(self, x):
        input = x
        x = self.dwconv(x)
        x = x.permute(0, 2, 3, 1) # (N, C, H, W) -> (N, H, W, C)
        x = self.norm(x)
        x = self.pwconv1(x)
        x = self.act(x)
        x = self.grn(x)
        x = self.pwconv2(x)
        x = x.permute(0, 3, 1, 2) # (N, H, W, C) -> (N, C, H, W)

        x = input + self.drop_path(x)
        return x

class ConvNeXtV2(nn.Module):
    """ ConvNeXt V2
        
    Args:
        in_chans (int): Number of input image channels. Default: 3
        num_classes (int): Number of classes for classification head. Default: 1000
        depths (tuple(int)): Number of blocks at each stage. Default: [3, 3, 9, 3]
        dims (int): Feature dimension at each stage. Default: [96, 192, 384, 768]
        drop_path_rate (float): Stochastic depth rate. Default: 0.
        head_init_scale (float): Init scaling value for classifier weights and biases. Default: 1.
    """
    def __init__(self, in_chans=3, num_classes=1000, 
                 depths=[3, 3, 9, 3], dims=[96, 192, 384, 768], 
                 drop_path_rate=0., head_init_scale=1.
                 ):
        super().__init__()
        self.depths = depths
        self.downsample_layers = nn.ModuleList() # stem and 3 intermediate downsampling conv layers
        stem = nn.Sequential(
            nn.Conv2d(in_chans, dims[0], kernel_size=4, stride=4),
            LayerNorm(dims[0], eps=1e-6, data_format="channels_first")
        )
        self.downsample_layers.append(stem)
        for i in range(3):
            downsample_layer = nn.Sequential(
                    LayerNorm(dims[i], eps=1e-6, data_format="channels_first"),
                    nn.Conv2d(dims[i], dims[i+1], kernel_size=2, stride=2),
            )
            self.downsample_layers.append(downsample_layer)

        self.stages = nn.ModuleList() # 4 feature resolution stages, each consisting of multiple residual blocks
        dp_rates=[x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))] 
        cur = 0
        for i in range(4):
            stage = nn.Sequential(
                *[Block(dim=dims[i], drop_path=dp_rates[cur + j]) for j in range(depths[i])]
            )
            self.stages.append(stage)
            cur += depths[i]

        self.norm = nn.LayerNorm(dims[-1], eps=1e-6) # final norm layer
        self.head = nn.Linear(dims[-1], num_classes)

        self.apply(self._init_weights)
        self.channel = [i.size(1) for i in self.forward(torch.randn(1, 3, 640, 640))]

    def _init_weights(self, m):
        if isinstance(m, (nn.Conv2d, nn.Linear)):
            trunc_normal_(m.weight, std=.02)
            nn.init.constant_(m.bias, 0)

    def forward(self, x):
        res = []
        for i in range(4):
            x = self.downsample_layers[i](x)
            x = self.stages[i](x)
            res.append(x)
        return res

def update_weight(model_dict, weight_dict):
    idx, temp_dict = 0, {}
    for k, v in weight_dict.items():
        if k in model_dict.keys() and np.shape(model_dict[k]) == np.shape(v):
            temp_dict[k] = v
            idx += 1
    model_dict.update(temp_dict)
    print(f'loading weights... {idx}/{len(model_dict)} items')
    return model_dict

def convnextv2_atto(weights='', **kwargs):
    model = ConvNeXtV2(depths=[2, 2, 6, 2], dims=[40, 80, 160, 320], **kwargs)
    if weights:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(weights)['model']))
    return model

def convnextv2_femto(weights='', **kwargs):
    model = ConvNeXtV2(depths=[2, 2, 6, 2], dims=[48, 96, 192, 384], **kwargs)
    if weights:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(weights)['model']))
    return model

def convnextv2_pico(weights='', **kwargs):
    model = ConvNeXtV2(depths=[2, 2, 6, 2], dims=[64, 128, 256, 512], **kwargs)
    if weights:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(weights)['model']))
    return model

def convnextv2_nano(weights='', **kwargs):
    model = ConvNeXtV2(depths=[2, 2, 8, 2], dims=[80, 160, 320, 640], **kwargs)
    if weights:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(weights)['model']))
    return model

def convnextv2_tiny(weights='', **kwargs):
    model = ConvNeXtV2(depths=[3, 3, 9, 3], dims=[96, 192, 384, 768], **kwargs)
    if weights:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(weights)['model']))
    return model

def convnextv2_base(weights='', **kwargs):
    model = ConvNeXtV2(depths=[3, 3, 27, 3], dims=[128, 256, 512, 1024], **kwargs)
    if weights:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(weights)['model']))
    return model

def convnextv2_large(weights='', **kwargs):
    model = ConvNeXtV2(depths=[3, 3, 27, 3], dims=[192, 384, 768, 1536], **kwargs)
    if weights:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(weights)['model']))
    return model

def convnextv2_huge(weights='', **kwargs):
    model = ConvNeXtV2(depths=[3, 3, 27, 3], dims=[352, 704, 1408, 2816], **kwargs)
    if weights:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(weights)['model']))
    return model

Backbone替换

yolo.py参数修改：（1）def parse_model部分（2）def _forward_once部分

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)

    is_backbone = False
    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
        try:
            t = m
            m = eval(m) if isinstance(m, str) else m  # eval strings
        except:
            pass
        for j, a in enumerate(args):
            with contextlib.suppress(NameError):
                try:
                    args[j] = eval(a) if isinstance(a, str) else a  # eval strings
                except:
                    args[j] = a

        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
        elif isinstance(m, str):
            t = m
            m = timm.create_model(m, pretrained=args[0], features_only=True)
            c2 = m.feature_info.channels()
        elif m in {convnextv2_tiny}: #可添加更多Backbone
            m = m(*args)
            c2 = m.channel
        else:
            c2 = ch[f]
        if isinstance(c2, list):
            is_backbone = True
            m_ = m
            m_.backbone = True
        else:
            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 + 4 if is_backbone else 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 + 4 if is_backbone else i) for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
        layers.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 = [], []  # 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)
        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)  # 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 _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)
        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)  # 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

.yaml配置文件修改

# 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, convnextv2_tiny, [False]], # 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)
  ]