目标检测算法改进系列之Backbone替换为LSKNet

LSKNet

Large Selective Kernel Network（LSKNet）可以动态地调整其大空间感受野，以更好地建模遥感场景中各种物体的测距的场景。据我们所知，这是首次在遥感物体检测领域探索大选择性卷积核机制的工作。在没有任何附加条件的情况下，我们LSKNet比主流检测器轻量的多，而且在多个数据集上刷新了SOTA！HRSC2016（98.46% mAP）、DOTA-v1.0（81.64% mAP）和FAIR1M-v1.0（47.87% mAP）。

论文地址：Large Selective Kernel Network for Remote Sensing Object Detection

添加LSKNet定义文件

添加路径：ultralytics/nn/backbone/lsknet.py
代码如下：

import torch
import torch.nn as nn
from torch.nn.modules.utils import _pair as to_2tuple
from timm.layers import DropPath, to_2tuple
from functools import partial
import numpy as np

__all__ = 'lsknet_t', 'lsknet_s'

class Mlp(nn.Module):
    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        self.fc1 = nn.Conv2d(in_features, hidden_features, 1)
        self.dwconv = DWConv(hidden_features)
        self.act = act_layer()
        self.fc2 = nn.Conv2d(hidden_features, out_features, 1)
        self.drop = nn.Dropout(drop)

    def forward(self, x):
        x = self.fc1(x)
        x = self.dwconv(x)
        x = self.act(x)
        x = self.drop(x)
        x = self.fc2(x)
        x = self.drop(x)
        return x


class LSKblock(nn.Module):
    def __init__(self, dim):
        super().__init__()
        self.conv0 = nn.Conv2d(dim, dim, 5, padding=2, groups=dim)
        self.conv_spatial = nn.Conv2d(dim, dim, 7, stride=1, padding=9, groups=dim, dilation=3)
        self.conv1 = nn.Conv2d(dim, dim//2, 1)
        self.conv2 = nn.Conv2d(dim, dim//2, 1)
        self.conv_squeeze = nn.Conv2d(2, 2, 7, padding=3)
        self.conv = nn.Conv2d(dim//2, dim, 1)

    def forward(self, x):   
        attn1 = self.conv0(x)
        attn2 = self.conv_spatial(attn1)

        attn1 = self.conv1(attn1)
        attn2 = self.conv2(attn2)
        
        attn = torch.cat([attn1, attn2], dim=1)
        avg_attn = torch.mean(attn, dim=1, keepdim=True)
        max_attn, _ = torch.max(attn, dim=1, keepdim=True)
        agg = torch.cat([avg_attn, max_attn], dim=1)
        sig = self.conv_squeeze(agg).sigmoid()
        attn = attn1 * sig[:,0,:,:].unsqueeze(1) + attn2 * sig[:,1,:,:].unsqueeze(1)
        attn = self.conv(attn)
        return x * attn



class Attention(nn.Module):
    def __init__(self, d_model):
        super().__init__()

        self.proj_1 = nn.Conv2d(d_model, d_model, 1)
        self.activation = nn.GELU()
        self.spatial_gating_unit = LSKblock(d_model)
        self.proj_2 = nn.Conv2d(d_model, d_model, 1)

    def forward(self, x):
        shorcut = x.clone()
        x = self.proj_1(x)
        x = self.activation(x)
        x = self.spatial_gating_unit(x)
        x = self.proj_2(x)
        x = x + shorcut
        return x


class Block(nn.Module):
    def __init__(self, dim, mlp_ratio=4., drop=0.,drop_path=0., act_layer=nn.GELU, norm_cfg=None):
        super().__init__()
        self.norm1 = nn.BatchNorm2d(dim)
        self.norm2 = nn.BatchNorm2d(dim)
        self.attn = Attention(dim)
        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
        mlp_hidden_dim = int(dim * mlp_ratio)
        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
        layer_scale_init_value = 1e-2            
        self.layer_scale_1 = nn.Parameter(
            layer_scale_init_value * torch.ones((dim)), requires_grad=True)
        self.layer_scale_2 = nn.Parameter(
            layer_scale_init_value * torch.ones((dim)), requires_grad=True)

    def forward(self, x):
        x = x + self.drop_path(self.layer_scale_1.unsqueeze(-1).unsqueeze(-1) * self.attn(self.norm1(x)))
        x = x + self.drop_path(self.layer_scale_2.unsqueeze(-1).unsqueeze(-1) * self.mlp(self.norm2(x)))
        return x


class OverlapPatchEmbed(nn.Module):
    """ Image to Patch Embedding
    """

    def __init__(self, img_size=224, patch_size=7, stride=4, in_chans=3, embed_dim=768, norm_cfg=None):
        super().__init__()
        patch_size = to_2tuple(patch_size)
        self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=stride,
                              padding=(patch_size[0] // 2, patch_size[1] // 2))
        self.norm = nn.BatchNorm2d(embed_dim)


    def forward(self, x):
        x = self.proj(x)
        _, _, H, W = x.shape
        x = self.norm(x)        
        return x, H, W

class LSKNet(nn.Module):
    def __init__(self, img_size=224, in_chans=3, embed_dims=[64, 128, 256, 512],
                mlp_ratios=[8, 8, 4, 4], drop_rate=0., drop_path_rate=0., norm_layer=partial(nn.LayerNorm, eps=1e-6),
                 depths=[3, 4, 6, 3], num_stages=4, 
                 norm_cfg=None):
        super().__init__()
        
        self.depths = depths
        self.num_stages = num_stages

        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]  # stochastic depth decay rule
        cur = 0

        for i in range(num_stages):
            patch_embed = OverlapPatchEmbed(img_size=img_size if i == 0 else img_size // (2 ** (i + 1)),
                                            patch_size=7 if i == 0 else 3,
                                            stride=4 if i == 0 else 2,
                                            in_chans=in_chans if i == 0 else embed_dims[i - 1],
                                            embed_dim=embed_dims[i], norm_cfg=norm_cfg)

            block = nn.ModuleList([Block(
                dim=embed_dims[i], mlp_ratio=mlp_ratios[i], drop=drop_rate, drop_path=dpr[cur + j],norm_cfg=norm_cfg)
                for j in range(depths[i])])
            norm = norm_layer(embed_dims[i])
            cur += depths[i]

            setattr(self, f"patch_embed{i + 1}", patch_embed)
            setattr(self, f"block{i + 1}", block)
            setattr(self, f"norm{i + 1}", norm)
        
        self.channel = [i.size(1) for i in self.forward(torch.randn(1, 3, 640, 640))]

    def forward(self, x):
        B = x.shape[0]
        outs = []
        for i in range(self.num_stages):
            patch_embed = getattr(self, f"patch_embed{i + 1}")
            block = getattr(self, f"block{i + 1}")
            norm = getattr(self, f"norm{i + 1}")
            x, H, W = patch_embed(x)
            for blk in block:
                x = blk(x)
            x = x.flatten(2).transpose(1, 2)
            x = norm(x)
            x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
            outs.append(x)
        return outs


class DWConv(nn.Module):
    def __init__(self, dim=768):
        super(DWConv, self).__init__()
        self.dwconv = nn.Conv2d(dim, dim, 3, 1, 1, bias=True, groups=dim)

    def forward(self, x):
        x = self.dwconv(x)
        return x

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 lsknet_t(weights=''):
    model = LSKNet(embed_dims=[32, 64, 160, 256], depths=[3, 3, 5, 2], drop_rate=0.1, drop_path_rate=0.1)
    if weights:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(weights)['state_dict']))
    return model

def lsknet_s(weights=''):
    model = LSKNet(embed_dims=[64, 128, 256, 512], depths=[2, 2, 4, 2], drop_rate=0.1, drop_path_rate=0.1)
    if weights:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(weights)['state_dict']))
    return model

if __name__ == '__main__':
    model = lsknet_t('lsk_t_backbone-2ef8a593.pth')
    inputs = torch.randn((1, 3, 640, 640))
    for i in model(inputs):
        print(i.size())

yolo.py文件修改

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 {}:
        #     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

yaml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, vovnet39a, [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)
  ]