YOLOv8改进添加swin transformer

文章YOLOv8改进添加swin transformer分享给大家，欢迎收藏Python资料网，专注分享技术知识

最近在做实验，需要改进YOLOv8，去网上找了很多教程都是充钱才能看的，NND这对一个一餐只能吃两个菜的大学生来说是多么的痛苦，所以自己去找代码手动改了一下，成功实现YOLOv8改进添加swin transformer，本人水平有限，改得不对的地方请自行改正。

第一步，在ultralytics\nn\modules\block.py代码中的最后部分中添加swin transformer代码，代码如下：

#----------swintf----C3STR---------------------------------
class SwinTransformerBlock(nn.Module):
    def __init__(self, c1, c2, num_heads, num_layers, window_size=8):
        super().__init__()
        self.conv = None
        if c1 != c2:
            self.conv = Conv(c1, c2)

        # remove input_resolution
        self.blocks = nn.Sequential(*[SwinTransformerLayer(dim=c2, num_heads=num_heads, window_size=window_size,
                                                           shift_size=0 if (i % 2 == 0) else window_size // 2) for i in
                                      range(num_layers)])

    def forward(self, x):
        if self.conv is not None:
            x = self.conv(x)
        x = self.blocks(x)
        return x


class WindowAttention(nn.Module):

    def __init__(self, dim, window_size, num_heads, qkv_bias=True, qk_scale=None, attn_drop=0., proj_drop=0.):

        super().__init__()
        self.dim = dim
        self.window_size = window_size  # Wh, Ww
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = qk_scale or head_dim ** -0.5

        # define a parameter table of relative position bias
        self.relative_position_bias_table = nn.Parameter(
            torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads))  # 2*Wh-1 * 2*Ww-1, nH

        # get pair-wise relative position index for each token inside the window
        coords_h = torch.arange(self.window_size[0])
        coords_w = torch.arange(self.window_size[1])
        coords = torch.stack(torch.meshgrid([coords_h, coords_w]))  # 2, Wh, Ww
        coords_flatten = torch.flatten(coords, 1)  # 2, Wh*Ww
        relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :]  # 2, Wh*Ww, Wh*Ww
        relative_coords = relative_coords.permute(1, 2, 0).contiguous()  # Wh*Ww, Wh*Ww, 2
        relative_coords[:, :, 0] += self.window_size[0] - 1  # shift to start from 0
        relative_coords[:, :, 1] += self.window_size[1] - 1
        relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1
        relative_position_index = relative_coords.sum(-1)  # Wh*Ww, Wh*Ww
        self.register_buffer("relative_position_index", relative_position_index)

        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
        self.attn_drop = nn.Dropout(attn_drop)
        self.proj = nn.Linear(dim, dim)
        self.proj_drop = nn.Dropout(proj_drop)

        nn.init.normal_(self.relative_position_bias_table, std=.02)
        self.softmax = nn.Softmax(dim=-1)

    def forward(self, x, mask=None):

        B_, N, C = x.shape
        qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
        q, k, v = qkv[0], qkv[1], qkv[2]  # make torchscript happy (cannot use tensor as tuple)

        q = q * self.scale
        attn = (q @ k.transpose(-2, -1))

        relative_position_bias = self.relative_position_bias_table[self.relative_position_index.view(-1)].view(
            self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1)  # Wh*Ww,Wh*Ww,nH
        relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous()  # nH, Wh*Ww, Wh*Ww
        attn = attn + relative_position_bias.unsqueeze(0)

        if mask is not None:
            nW = mask.shape[0]
            attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)
            attn = attn.view(-1, self.num_heads, N, N)
            attn = self.softmax(attn)
        else:
            attn = self.softmax(attn)

        attn = self.attn_drop(attn)

        # print(attn.dtype, v.dtype)
        try:
            x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
        except:
            # print(attn.dtype, v.dtype)
            x = (attn.half() @ v).transpose(1, 2).reshape(B_, N, C)
        x = self.proj(x)
        x = self.proj_drop(x)
        return x


class Mlp(nn.Module):

    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.SiLU, drop=0.):
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        self.fc1 = nn.Linear(in_features, hidden_features)
        self.act = act_layer()
        self.fc2 = nn.Linear(hidden_features, out_features)
        self.drop = nn.Dropout(drop)

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


class SwinTransformerLayer(nn.Module):

    def __init__(self, dim, num_heads, window_size=8, shift_size=0,
                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0., drop_path=0.,
                 act_layer=nn.SiLU, norm_layer=nn.LayerNorm):
        super().__init__()
        self.dim = dim
        self.num_heads = num_heads
        self.window_size = window_size
        self.shift_size = shift_size
        self.mlp_ratio = mlp_ratio
        # if min(self.input_resolution) <= self.window_size:
        #     # if window size is larger than input resolution, we don't partition windows
        #     self.shift_size = 0
        #     self.window_size = min(self.input_resolution)
        assert 0 <= self.shift_size < self.window_size, "shift_size must in 0-window_size"

        self.norm1 = norm_layer(dim)
        self.attn = WindowAttention(
            dim, window_size=(self.window_size, self.window_size), num_heads=num_heads,
            qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)

        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
        self.norm2 = norm_layer(dim)
        mlp_hidden_dim = int(dim * mlp_ratio)
        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)

    def create_mask(self, H, W):
        # calculate attention mask for SW-MSA
        img_mask = torch.zeros((1, H, W, 1))  # 1 H W 1
        h_slices = (slice(0, -self.window_size),
                    slice(-self.window_size, -self.shift_size),
                    slice(-self.shift_size, None))
        w_slices = (slice(0, -self.window_size),
                    slice(-self.window_size, -self.shift_size),
                    slice(-self.shift_size, None))
        cnt = 0
        for h in h_slices:
            for w in w_slices:
                img_mask[:, h, w, :] = cnt
                cnt += 1

        def window_partition(x, window_size):
            """
            Args:
                x: (B, H, W, C)
                window_size (int): window size
            Returns:
                windows: (num_windows*B, window_size, window_size, C)
            """
            B, H, W, C = x.shape
            x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
            windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
            return windows

        def window_reverse(windows, window_size, H, W):
            """
            Args:
                windows: (num_windows*B, window_size, window_size, C)
                window_size (int): Window size
                H (int): Height of image
                W (int): Width of image
            Returns:
                x: (B, H, W, C)
            """
            B = int(windows.shape[0] / (H * W / window_size / window_size))
            x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
            x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
            return x

        mask_windows = window_partition(img_mask, self.window_size)  # nW, window_size, window_size, 1
        mask_windows = mask_windows.view(-1, self.window_size * self.window_size)
        attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
        attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))

        return attn_mask

    def forward(self, x):
        # reshape x[b c h w] to x[b l c]
        _, _, H_, W_ = x.shape

        Padding = False
        if min(H_, W_) < self.window_size or H_ % self.window_size != 0 or W_ % self.window_size != 0:
            Padding = True
            # print(f'img_size {min(H_, W_)} is less than (or not divided by) window_size {self.window_size}, Padding.')
            pad_r = (self.window_size - W_ % self.window_size) % self.window_size
            pad_b = (self.window_size - H_ % self.window_size) % self.window_size
            x = F.pad(x, (0, pad_r, 0, pad_b))

        # print('2', x.shape)
        B, C, H, W = x.shape
        L = H * W
        x = x.permute(0, 2, 3, 1).contiguous().view(B, L, C)  # b, L, c

        # create mask from init to forward
        if self.shift_size > 0:
            attn_mask = self.create_mask(H, W).to(x.device)
        else:
            attn_mask = None

        shortcut = x
        x = self.norm1(x)
        x = x.view(B, H, W, C)

        # cyclic shift
        if self.shift_size > 0:
            shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
        else:
            shifted_x = x

        def window_partition(x, window_size):
            """
            Args:
                x: (B, H, W, C)
                window_size (int): window size
            Returns:
                windows: (num_windows*B, window_size, window_size, C)
            """
            B, H, W, C = x.shape
            x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
            windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
            return windows

        def window_reverse(windows, window_size, H, W):
            """
            Args:
                windows: (num_windows*B, window_size, window_size, C)
                window_size (int): Window size
                H (int): Height of image
                W (int): Width of image
            Returns:
                x: (B, H, W, C)
            """
            B = int(windows.shape[0] / (H * W / window_size / window_size))
            x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
            x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
            return x

        # partition windows
        x_windows = window_partition(shifted_x, self.window_size)  # nW*B, window_size, window_size, C
        x_windows = x_windows.view(-1, self.window_size * self.window_size, C)  # nW*B, window_size*window_size, C

        # W-MSA/SW-MSA
        attn_windows = self.attn(x_windows, mask=attn_mask)  # nW*B, window_size*window_size, C

        # merge windows
        attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
        shifted_x = window_reverse(attn_windows, self.window_size, H, W)  # B H' W' C

        # reverse cyclic shift
        if self.shift_size > 0:
            x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))
        else:
            x = shifted_x
        x = x.view(B, H * W, C)

        # FFN
        x = shortcut + self.drop_path(x)
        x = x + self.drop_path(self.mlp(self.norm2(x)))

        x = x.permute(0, 2, 1).contiguous().view(-1, C, H, W)  # b c h w

        if Padding:
            x = x[:, :, :H_, :W_]  # reverse padding

        return x


class C3STR(C3):
    # C3 module with SwinTransformerBlock()
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)
        num_heads = c_ // 32
        self.m = SwinTransformerBlock(c_, c_, num_heads, n)

在开头引入代码：from timm.models.layers import DropPath, to_2tuple, trunc_normal_
一般是没有的，先在自己的环境下输入:pip install timm -i https://mirrors.bfsu.edu.cn/pypi/web/simple下载
第二步：ultralytics\nn\modules_init_.py中添加 C3STR，首先在from .block import 中添加如下：

from .block import (
    C1,
    C2,
    C3,
    C3TR,
    DFL,
    SPP,
    SPPF,
    Bottleneck,
    BottleneckCSP,
    C2f,
    C2fAttn,
    ImagePoolingAttn,
    C3Ghost,
    C3x,
    GhostBottleneck,
    HGBlock,
    HGStem,
    Proto,
    RepC3,
    ResNetLayer,
    ContrastiveHead,
    BNContrastiveHead,
    RepNCSPELAN4,
    ADown,
    SPPELAN,
    CBFuse,
    CBLinear,
    Silence,
    C3STR,#添加swin_transfomer
)

添加后如下图：

在__all__ 中添加如下代码：

__all__ = (
    "Conv",
    "Conv2",
    "LightConv",
    "RepConv",
    "DWConv",
    "DWConvTranspose2d",
    "ConvTranspose",
    "Focus",
    "GhostConv",
    "ChannelAttention",
    "SpatialAttention",
    "CBAM",
    "Concat",
    "TransformerLayer",
    "TransformerBlock",
    "MLPBlock",
    "LayerNorm2d",
    "DFL",
    "HGBlock",
    "HGStem",
    "SPP",
    "SPPF",
    "C1",
    "C2",
    "C3",
    "C2f",
    "C2fAttn",
    "C3x",
    "C3TR",
    "C3Ghost",
    "GhostBottleneck",
    "Bottleneck",
    "BottleneckCSP",
    "Proto",
    "Detect",
    "Segment",
    "Pose",
    "Classify",
    "TransformerEncoderLayer",
    "RepC3",
    "RTDETRDecoder",
    "AIFI",
    "DeformableTransformerDecoder",
    "DeformableTransformerDecoderLayer",
    "MSDeformAttn",
    "MLP",
    "ResNetLayer",
    "OBB",
    "WorldDetect",
    "ImagePoolingAttn",
    "ContrastiveHead",
    "BNContrastiveHead",
    "RepNCSPELAN4",
    "ADown",
    "SPPELAN",
    "CBFuse",
    "CBLinear",
    "Silence",
    "GAMAttention",#修改添加GAM
    "C3STR",#添加swin_transfomer

)

添加后如下图：

第三步，在ultralytics\nn\tasks.py中添加C3STR，首先在from ultralytics.nn.modules import处添加，效果如下：

from ultralytics.nn.modules import (
    AIFI,
    C1,
    C2,
    C3,
    C3TR,
    OBB,
    SPP,
    SPPF,
    Bottleneck,
    BottleneckCSP,
    C2f,
    C2fAttn,
    ImagePoolingAttn,
    C3Ghost,
    C3x,
    Classify,
    Concat,
    Conv,
    Conv2,
    ConvTranspose,
    Detect,
    DWConv,
    DWConvTranspose2d,
    Focus,
    GhostBottleneck,
    GhostConv,
    HGBlock,
    HGStem,
    Pose,
    RepC3,
    RepConv,
    ResNetLayer,
    RTDETRDecoder,
    Segment,
    WorldDetect,
    RepNCSPELAN4,
    ADown,
    SPPELAN,
    CBFuse,
    CBLinear,
    Silence,
    GAMAttention,
    C3STR,
)

添加后图如下：

其次：按住 Ctrl+F 输入if m in在如下图位置输入： C3STR

第四步，在ultralytics\cfg\models\v8中复制yolov8.yaml文件，修改如下：

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect

# Parameters
nc: 1 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
  s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
  m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
  l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
  x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs

# YOLOv8.0n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
  - [-1, 3, C2f, [128, True]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 6, C2f, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 6, C2f, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 3, C2f, [1024, True]]
  - [-1, 3,  C3STR, [1024]]
  - [-1, 1, SPPF, [1024, 5]] # 10

# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 3, C2f, [512]] # 13

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 3, C2f, [256]] # 16 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 12], 1, Concat, [1]] # cat head P4
  - [-1, 3, C2f, [512]] # 19 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 9], 1, Concat, [1]] # cat head P5
  - [-1, 3, C2f, [1024]] # 22 (P5/32-large)

  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

在本项目中创建一个train.py文件，大致代码为：

from ultralytics import YOLO
#import os
#os.environ['CUDA_VISIBLE_DEVICES']='1'
if __name__ == '__main__':
    # Load a model
    model = YOLO(r'E:\yolov8_car_deepsort\yolov8_car\ultralytics\cfg\models\v8\yolov8-Swin_transformer.yaml')  # 不使用预训练权重训练
    # model = YOLO(r'yolov8p.yaml').load("yolov8n.pt")  # 使用预训练权重训练
    # Trainparameters ----------------------------------------------------------------------------------------------
    model.train(
        data=r'E:\yolov8_car_deepsort\yolov8_car\ultralytics\cfg\datasets\mycar.yaml',
        epochs= 300 , # (int) number of epochs to train for
        batch= 16 , # (int) number of images per batch (-1 for AutoBatch)
        imgsz= 640 , # (int) size of input images as integer or w,h
        save= True , # (bool) save train checkpoints and predict results
        save_period= -1, # (int) Save checkpoint every x epochs (disabled if < 1)
        project= 'result', # (str, optional) project name
        name= 'yolov8-Swin_transformer' ,# (str, optional) experiment name, results saved to 'project/name' directory
        resume=True
                )
 

运行结果：

表示成功，添加位置很多，具体添加情况看个人

版权声明：本文来自互联网用户投稿，该文观点仅代表作者本人，不代表本站立场。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如若内容造成侵权/违法违规/事实不符，请联系邮箱：jacktools123@163.com进行投诉反馈，一经查实，立即删除！