yolov8涨点系列之轻量化主干网络替换

news2024/11/23 20:12:08

文章目录

    • YOLOv8 替换成efficientvit轻量级主干网络的好处
      • 计算效率提升
        • 模型部署更便捷
        • 方便模型移植
      • 模型可扩展性增强
        • 便于集成其他模块
        • 支持模型压缩技术
  • 主干网络替换
    • 1.创建yolov8_efficeintVit.py
    • 2.修改task.py
      • (1)引入创建的efficientViT文件
      • (2)修改_predict_once函数
      • (3)修改parse_model函数
    • 3.yolov8.yaml文件修改
      • yolov8.yaml
      • EfficientVit.yaml
    • 4.基于EfficientVit.yaml训练

  从网上可搜索的其他博主写的关于yolov8轻量化主干网络EfficientVit替换效果来看,传入代码后会有不能运行或者报错等情况,针对这种问题,专门编写了这篇“yolov8涨点系列之轻量化主干网络替换”,进行Ultralytics版本替换的具体步骤介绍。

YOLOv8 替换成efficientvit轻量级主干网络的好处

计算效率提升

  减少计算资源需求:轻量级主干网络的参数数量和计算复杂度较低,可以在硬件资源有限的设备上更高效地运行,如嵌入式设备、移动设备等。这使得 YOLOv8 能够在资源受限的环境中快速进行目标检测,扩大了其应用范围。例如,在一些智能摄像头、无人机等设备上,使用轻量级主干网络可以降低设备的能耗和散热需求,提高设备的续航能力和稳定性。
加快推理速度:轻量级网络的结构简单,计算量小,能够更快地处理输入图像,从而提高 YOLOv8 的推理速度。这对于实时性要求较高的应用场景,如自动驾驶、视频监控等非常重要,可以更快地检测到目标物体,为后续的决策和处理提供更及时的信息。

模型部署更便捷

  易于优化和调试:轻量级主干网络的结构相对简单,更容易进行优化和调试。在模型训练过程中,可以更快地收敛,减少训练时间和资源消耗。同时,在模型出现问题时,也更容易进行排查和修复,提高了开发效率。

方便模型移植

  由于轻量级网络的资源需求较低,更容易将训练好的模型移植到不同的硬件平台上,实现跨平台部署。这对于需要在多种设备上运行的应用场景,如智能家居、智能安防等,具有很大的优势。

模型可扩展性增强

便于集成其他模块

  轻量级主干网络为 YOLOv8 提供了更多的空间和灵活性,方便集成其他模块,如注意力机制、特征融合模块等,以进一步提高模型的性能。这些额外的模块可以根据具体的应用需求进行选择和组合,使模型具有更好的适应性和可扩展性。

支持模型压缩技术

  轻量级网络更容易与模型压缩技术相结合,如量化、剪枝等。通过这些技术,可以进一步降低模型的存储和计算需求,提高模型的运行效率。这对于在资源受限的设备上部署大规模的目标检测模型具有重要意义。

主干网络替换

1.创建yolov8_efficeintVit.py

  创建yolov8_efficeintVit.py的路径如下图所示:
在这里插入图片描述
  创建完成后,将下面代码直接复制粘贴进去:

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.checkpoint as checkpoint
import itertools

from timm.models.layers import SqueezeExcite

import numpy as np
import itertools

__all__ = ['YOLOv8_EfficientViT_M0', 'YOLOv8_EfficientViT_M1', 'YOLOv8_EfficientViT_M2', 'YOLOv8_EfficientViT_M3', 'YOLOv8_EfficientViT_M4',
           'YOLOv8_EfficientViT_M5']


class Conv2d_BN(torch.nn.Sequential):
    def __init__(self, a, b, ks=1, stride=1, pad=0, dilation=1,
                 groups=1, bn_weight_init=1, resolution=-10000):
        super().__init__()
        self.add_module('c', torch.nn.Conv2d(
            a, b, ks, stride, pad, dilation, groups, bias=False))
        self.add_module('bn', torch.nn.BatchNorm2d(b))
        torch.nn.init.constant_(self.bn.weight, bn_weight_init)
        torch.nn.init.constant_(self.bn.bias, 0)

    @torch.no_grad()
    def switch_to_deploy(self):
        c, bn = self._modules.values()
        w = bn.weight / (bn.running_var + bn.eps) ** 0.5
        w = c.weight * w[:, None, None, None]
        b = bn.bias - bn.running_mean * bn.weight / \
            (bn.running_var + bn.eps) ** 0.5
        m = torch.nn.Conv2d(w.size(1) * self.c.groups, w.size(
            0), w.shape[2:], stride=self.c.stride, padding=self.c.padding, dilation=self.c.dilation,
                            groups=self.c.groups)
        m.weight.data.copy_(w)
        m.bias.data.copy_(b)
        return m


def replace_batchnorm(net):
    for child_name, child in net.named_children():
        if hasattr(child, 'fuse'):
            setattr(net, child_name, child.fuse())
        elif isinstance(child, torch.nn.BatchNorm2d):
            setattr(net, child_name, torch.nn.Identity())
        else:
            replace_batchnorm(child)


class PatchMerging(torch.nn.Module):
    def __init__(self, dim, out_dim, input_resolution):
        super().__init__()
        hid_dim = int(dim * 4)
        self.conv1 = Conv2d_BN(dim, hid_dim, 1, 1, 0, resolution=input_resolution)
        self.act = torch.nn.ReLU()
        self.conv2 = Conv2d_BN(hid_dim, hid_dim, 3, 2, 1, groups=hid_dim, resolution=input_resolution)
        self.se = SqueezeExcite(hid_dim, .25)
        self.conv3 = Conv2d_BN(hid_dim, out_dim, 1, 1, 0, resolution=input_resolution // 2)

    def forward(self, x):
        x = self.conv3(self.se(self.act(self.conv2(self.act(self.conv1(x))))))
        return x


class Residual(torch.nn.Module):
    def __init__(self, m, drop=0.):
        super().__init__()
        self.m = m
        self.drop = drop

    def forward(self, x):
        if self.training and self.drop > 0:
            return x + self.m(x) * torch.rand(x.size(0), 1, 1, 1,
                                              device=x.device).ge_(self.drop).div(1 - self.drop).detach()
        else:
            return x + self.m(x)


class FFN(torch.nn.Module):
    def __init__(self, ed, h, resolution):
        super().__init__()
        self.pw1 = Conv2d_BN(ed, h, resolution=resolution)
        self.act = torch.nn.ReLU()
        self.pw2 = Conv2d_BN(h, ed, bn_weight_init=0, resolution=resolution)

    def forward(self, x):
        x = self.pw2(self.act(self.pw1(x)))
        return x


class CascadedGroupAttention(torch.nn.Module):
    r""" Cascaded Group Attention.

    Args:
        dim (int): Number of input channels.
        key_dim (int): The dimension for query and key.
        num_heads (int): Number of attention heads.
        attn_ratio (int): Multiplier for the query dim for value dimension.
        resolution (int): Input resolution, correspond to the window size.
        kernels (List[int]): The kernel size of the dw conv on query.
    """

    def __init__(self, dim, key_dim, num_heads=8,
                 attn_ratio=4,
                 resolution=14,
                 kernels=[5, 5, 5, 5], ):
        super().__init__()
        self.num_heads = num_heads
        self.scale = key_dim ** -0.5
        self.key_dim = key_dim
        self.d = int(attn_ratio * key_dim)
        self.attn_ratio = attn_ratio

        qkvs = []
        dws = []
        for i in range(num_heads):
            qkvs.append(Conv2d_BN(dim // (num_heads), self.key_dim * 2 + self.d, resolution=resolution))
            dws.append(Conv2d_BN(self.key_dim, self.key_dim, kernels[i], 1, kernels[i] // 2, groups=self.key_dim,
                                 resolution=resolution))
        self.qkvs = torch.nn.ModuleList(qkvs)
        self.dws = torch.nn.ModuleList(dws)
        self.proj = torch.nn.Sequential(torch.nn.ReLU(), Conv2d_BN(
            self.d * num_heads, dim, bn_weight_init=0, resolution=resolution))

        points = list(itertools.product(range(resolution), range(resolution)))
        N = len(points)
        attention_offsets = {}
        idxs = []
        for p1 in points:
            for p2 in points:
                offset = (abs(p1[0] - p2[0]), abs(p1[1] - p2[1]))
                if offset not in attention_offsets:
                    attention_offsets[offset] = len(attention_offsets)
                idxs.append(attention_offsets[offset])
        self.attention_biases = torch.nn.Parameter(
            torch.zeros(num_heads, len(attention_offsets)))
        self.register_buffer('attention_bias_idxs',
                             torch.LongTensor(idxs).view(N, N))

    @torch.no_grad()
    def train(self, mode=True):
        super().train(mode)
        if mode and hasattr(self, 'ab'):
            del self.ab
        else:
            self.ab = self.attention_biases[:, self.attention_bias_idxs]

    def forward(self, x):  # x (B,C,H,W)
        B, C, H, W = x.shape
        trainingab = self.attention_biases[:, self.attention_bias_idxs]
        feats_in = x.chunk(len(self.qkvs), dim=1)
        feats_out = []
        feat = feats_in[0]
        for i, qkv in enumerate(self.qkvs):
            if i > 0:  # add the previous output to the input
                feat = feat + feats_in[i]
            feat = qkv(feat)
            q, k, v = feat.view(B, -1, H, W).split([self.key_dim, self.key_dim, self.d], dim=1)  # B, C/h, H, W
            q = self.dws[i](q)
            q, k, v = q.flatten(2), k.flatten(2), v.flatten(2)  # B, C/h, N
            attn = (
                    (q.transpose(-2, -1) @ k) * self.scale
                    +
                    (trainingab[i] if self.training else self.ab[i])
            )
            attn = attn.softmax(dim=-1)  # BNN
            feat = (v @ attn.transpose(-2, -1)).view(B, self.d, H, W)  # BCHW
            feats_out.append(feat)
        x = self.proj(torch.cat(feats_out, 1))
        return x


class LocalWindowAttention(torch.nn.Module):
    r""" Local Window Attention.

    Args:
        dim (int): Number of input channels.
        key_dim (int): The dimension for query and key.
        num_heads (int): Number of attention heads.
        attn_ratio (int): Multiplier for the query dim for value dimension.
        resolution (int): Input resolution.
        window_resolution (int): Local window resolution.
        kernels (List[int]): The kernel size of the dw conv on query.
    """

    def __init__(self, dim, key_dim, num_heads=8,
                 attn_ratio=4,
                 resolution=14,
                 window_resolution=7,
                 kernels=[5, 5, 5, 5], ):
        super().__init__()
        self.dim = dim
        self.num_heads = num_heads
        self.resolution = resolution
        assert window_resolution > 0, 'window_size must be greater than 0'
        self.window_resolution = window_resolution

        self.attn = CascadedGroupAttention(dim, key_dim, num_heads,
                                           attn_ratio=attn_ratio,
                                           resolution=window_resolution,
                                           kernels=kernels, )

    def forward(self, x):
        B, C, H, W = x.shape

        if H <= self.window_resolution and W <= self.window_resolution:
            x = self.attn(x)
        else:
            x = x.permute(0, 2, 3, 1)
            pad_b = (self.window_resolution - H %
                     self.window_resolution) % self.window_resolution
            pad_r = (self.window_resolution - W %
                     self.window_resolution) % self.window_resolution
            padding = pad_b > 0 or pad_r > 0

            if padding:
                x = torch.nn.functional.pad(x, (0, 0, 0, pad_r, 0, pad_b))

            pH, pW = H + pad_b, W + pad_r
            nH = pH // self.window_resolution
            nW = pW // self.window_resolution
            # window partition, BHWC -> B(nHh)(nWw)C -> BnHnWhwC -> (BnHnW)hwC -> (BnHnW)Chw
            x = x.view(B, nH, self.window_resolution, nW, self.window_resolution, C).transpose(2, 3).reshape(
                B * nH * nW, self.window_resolution, self.window_resolution, C
            ).permute(0, 3, 1, 2)
            x = self.attn(x)
            # window reverse, (BnHnW)Chw -> (BnHnW)hwC -> BnHnWhwC -> B(nHh)(nWw)C -> BHWC
            x = x.permute(0, 2, 3, 1).view(B, nH, nW, self.window_resolution, self.window_resolution,
                                           C).transpose(2, 3).reshape(B, pH, pW, C)

            if padding:
                x = x[:, :H, :W].contiguous()

            x = x.permute(0, 3, 1, 2)

        return x


class EfficientViTBlock(torch.nn.Module):
    """ A basic EfficientViT building block.

    Args:
        type (str): Type for token mixer. Default: 's' for self-attention.
        ed (int): Number of input channels.
        kd (int): Dimension for query and key in the token mixer.
        nh (int): Number of attention heads.
        ar (int): Multiplier for the query dim for value dimension.
        resolution (int): Input resolution.
        window_resolution (int): Local window resolution.
        kernels (List[int]): The kernel size of the dw conv on query.
    """

    def __init__(self, type,
                 ed, kd, nh=8,
                 ar=4,
                 resolution=14,
                 window_resolution=7,
                 kernels=[5, 5, 5, 5], ):
        super().__init__()

        self.dw0 = Residual(Conv2d_BN(ed, ed, 3, 1, 1, groups=ed, bn_weight_init=0., resolution=resolution))
        self.ffn0 = Residual(FFN(ed, int(ed * 2), resolution))

        if type == 's':
            self.mixer = Residual(LocalWindowAttention(ed, kd, nh, attn_ratio=ar, \
                                                       resolution=resolution, window_resolution=window_resolution,
                                                       kernels=kernels))

        self.dw1 = Residual(Conv2d_BN(ed, ed, 3, 1, 1, groups=ed, bn_weight_init=0., resolution=resolution))
        self.ffn1 = Residual(FFN(ed, int(ed * 2), resolution))

    def forward(self, x):
        return self.ffn1(self.dw1(self.mixer(self.ffn0(self.dw0(x)))))


class YOLOv8_EfficientViT(torch.nn.Module):
    def __init__(self, img_size=400,
                 patch_size=16,
                 frozen_stages=0,
                 in_chans=3,
                 stages=['s', 's', 's'],
                 embed_dim=[64, 128, 192],
                 key_dim=[16, 16, 16],
                 depth=[1, 2, 3],
                 num_heads=[4, 4, 4],
                 window_size=[7, 7, 7],
                 kernels=[5, 5, 5, 5],
                 down_ops=[['subsample', 2], ['subsample', 2], ['']],
                 pretrained=None,
                 distillation=False, ):
        super().__init__()

        resolution = img_size
        self.patch_embed = torch.nn.Sequential(Conv2d_BN(in_chans, embed_dim[0] // 8, 3, 2, 1, resolution=resolution),
                                               torch.nn.ReLU(),
                                               Conv2d_BN(embed_dim[0] // 8, embed_dim[0] // 4, 3, 2, 1,
                                                         resolution=resolution // 2), torch.nn.ReLU(),
                                               Conv2d_BN(embed_dim[0] // 4, embed_dim[0] // 2, 3, 2, 1,
                                                         resolution=resolution // 4), torch.nn.ReLU(),
                                               Conv2d_BN(embed_dim[0] // 2, embed_dim[0], 3, 1, 1,
                                                         resolution=resolution // 8))

        resolution = img_size // patch_size
        attn_ratio = [embed_dim[i] / (key_dim[i] * num_heads[i]) for i in range(len(embed_dim))]
        self.blocks1 = []
        self.blocks2 = []
        self.blocks3 = []
        for i, (stg, ed, kd, dpth, nh, ar, wd, do) in enumerate(
                zip(stages, embed_dim, key_dim, depth, num_heads, attn_ratio, window_size, down_ops)):
            for d in range(dpth):
                eval('self.blocks' + str(i + 1)).append(EfficientViTBlock(stg, ed, kd, nh, ar, resolution, wd, kernels))
            if do[0] == 'subsample':
                # ('Subsample' stride)
                blk = eval('self.blocks' + str(i + 2))
                resolution_ = (resolution - 1) // do[1] + 1
                blk.append(torch.nn.Sequential(Residual(
                    Conv2d_BN(embed_dim[i], embed_dim[i], 3, 1, 1, groups=embed_dim[i], resolution=resolution)),
                                               Residual(FFN(embed_dim[i], int(embed_dim[i] * 2), resolution)), ))
                blk.append(PatchMerging(*embed_dim[i:i + 2], resolution))
                resolution = resolution_
                blk.append(torch.nn.Sequential(Residual(
                    Conv2d_BN(embed_dim[i + 1], embed_dim[i + 1], 3, 1, 1, groups=embed_dim[i + 1],
                              resolution=resolution)),
                                               Residual(
                                                   FFN(embed_dim[i + 1], int(embed_dim[i + 1] * 2), resolution)), ))
        self.blocks1 = torch.nn.Sequential(*self.blocks1)
        self.blocks2 = torch.nn.Sequential(*self.blocks2)
        self.blocks3 = torch.nn.Sequential(*self.blocks3)

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

    def forward(self, x):
        outs = []
        x = self.patch_embed(x)
        x = self.blocks1(x)
        outs.append(x)
        x = self.blocks2(x)
        outs.append(x)
        x = self.blocks3(x)
        outs.append(x)
        return outs


YOLOv8_EfficientViT_m0 = {
    'img_size': 224,
    'patch_size': 16,
    'embed_dim': [64, 128, 192],
    'depth': [1, 2, 3],
    'num_heads': [4, 4, 4],
    'window_size': [7, 7, 7],
    'kernels': [7, 5, 3, 3],
}

YOLOv8_EfficientViT_m1 = {
    'img_size': 224,
    'patch_size': 16,
    'embed_dim': [128, 144, 192],
    'depth': [1, 2, 3],
    'num_heads': [2, 3, 3],
    'window_size': [7, 7, 7],
    'kernels': [7, 5, 3, 3],
}

YOLOv8_EfficientViT_m2 = {
    'img_size': 224,
    'patch_size': 16,
    'embed_dim': [128, 192, 224],
    'depth': [1, 2, 3],
    'num_heads': [4, 3, 2],
    'window_size': [7, 7, 7],
    'kernels': [7, 5, 3, 3],
}

YOLOv8_EfficientViT_m3 = {
    'img_size': 224,
    'patch_size': 16,
    'embed_dim': [128, 240, 320],
    'depth': [1, 2, 3],
    'num_heads': [4, 3, 4],
    'window_size': [7, 7, 7],
    'kernels': [5, 5, 5, 5],
}

YOLOv8_EfficientViT_m4 = {
    'img_size': 224,
    'patch_size': 16,
    'embed_dim': [128, 256, 384],
    'depth': [1, 2, 3],
    'num_heads': [4, 4, 4],
    'window_size': [7, 7, 7],
    'kernels': [7, 5, 3, 3],
}

YOLOv8_EfficientViT_m5 = {
    'img_size': 224,
    'patch_size': 16,
    'embed_dim': [192, 288, 384],
    'depth': [1, 3, 4],
    'num_heads': [3, 3, 4],
    'window_size': [7, 7, 7],
    'kernels': [7, 5, 3, 3],
}


def YOLOv8_EfficientViT_M0(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None,
                    model_cfg=YOLOv8_EfficientViT_m0):
    model = YOLOv8_EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
    if pretrained:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
    if fuse:
        replace_batchnorm(model)
    return model


def YOLOv8_EfficientViT_M1(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None,
                    model_cfg=YOLOv8_EfficientViT_m1):
    model = YOLOv8_EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
    if pretrained:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
    if fuse:
        replace_batchnorm(model)
    return model


def YOLOv8_EfficientViT_M2(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None,
                    model_cfg=YOLOv8_EfficientViT_m2):
    model = YOLOv8_EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
    if pretrained:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
    if fuse:
        replace_batchnorm(model)
    return model


def YOLOv8_EfficientViT_M3(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None,
                    model_cfg=YOLOv8_EfficientViT_m3):
    model = YOLOv8_EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
    if pretrained:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
    if fuse:
        replace_batchnorm(model)
    return model


def YOLOv8_EfficientViT_M4(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None,
                    model_cfg=YOLOv8_EfficientViT_m4):
    model = YOLOv8_EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
    if pretrained:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
    if fuse:
        replace_batchnorm(model)
    return model


def YOLOv8_EfficientViT_M5(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None,
                    model_cfg=YOLOv8_EfficientViT_m5):
    model = YOLOv8_EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
    if pretrained:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
    if fuse:
        replace_batchnorm(model)
    return model


def update_weight(model_dict, weight_dict):
    idx, temp_dict = 0, {}
    for k, v in weight_dict.items():
        # k = k[9:]
        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

  一共创建了6个尺寸大小,分别是:(本文以YOLOv8_EfficientViT_M0替换为例)

'YOLOv8_EfficientViT_M0', 
'YOLOv8_EfficientViT_M1', 
'YOLOv8_EfficientViT_M2', 
'YOLOv8_EfficientViT_M3',
 'YOLOv8_EfficientViT_M4',
 'YOLOv8_EfficientViT_M5'

2.修改task.py

  task.py文件修改内容如下:

(1)引入创建的efficientViT文件

在这里插入图片描述

from ultralytics.nn.backbone.yolov8_efficientVit import *

(2)修改_predict_once函数

    def _predict_once(self, x, profile=False, visualize=False):
        """
        Perform a forward pass through the network.

        Args:
            x (torch.Tensor): The input tensor to the model.
            profile (bool):  Print the computation time of each layer if True, defaults to False.
            visualize (bool): Save the feature maps of the model if True, defaults to False.

        Returns:
            (torch.Tensor): The last output of the model.
        """
        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)
                # for i in x:
                #     if i is not None:
                #         print(i.size())
                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

(3)修改parse_model函数

def parse_model(d, ch, verbose=True, warehouse_manager=None):  # model_dict, input_channels(3)
    """Parse a YOLO model.yaml dictionary into a PyTorch model."""
    import ast

    # Args
    max_channels = float('inf')
    nc, act, scales = (d.get(x) for x in ('nc', 'activation', 'scales'))
    depth, width, kpt_shape = (d.get(x, 1.0) for x in ('depth_multiple', 'width_multiple', 'kpt_shape'))
    if scales:
        scale = d.get('scale')
        if not scale:
            scale = tuple(scales.keys())[0]
            LOGGER.warning(f"WARNING ⚠️ no model scale passed. Assuming scale='{scale}'.")
        depth, width, max_channels = scales[scale]

    if act:
        Conv.default_act = eval(act)  # redefine default activation, i.e. Conv.default_act = nn.SiLU()
        if verbose:
            LOGGER.info(f"{colorstr('activation:')} {act}")  # print

    if verbose:
        LOGGER.info(f"\n{'':>3}{'from':>20}{'n':>3}{'params':>10}  {'module':<45}{'arguments':<30}")
    ch = [ch]
    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out

    is_backbone = False
    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
        try:
            if m == 'node_mode':
                m = d[m]
                if len(args) > 0:
                    if args[0] == 'head_channel':
                        args[0] = int(d[args[0]])
            t = m
            m = getattr(torch.nn, m[3:]) if 'nn.' in m else globals()[m]  # get module
        except:
            pass
        for j, a in enumerate(args):
            if isinstance(a, str):
                with contextlib.suppress(ValueError):
                    try:
                        args[j] = locals()[a] if a in locals() else ast.literal_eval(a)
                    except:
                        args[j] = a

        n = n_ = max(round(n * depth), 1) if n > 1 else n  # depth gain
        if m in (Classify, Conv, ConvTranspose, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, Focus,
                 BottleneckCSP, C1, C2, C2f, C3, C3TR, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x, RepC3, RepC3_split,GS_CBAM):
            if args[0] == 'head_channel':
                args[0] = d[args[0]]
            c1, c2 = ch[f], args[0]
            if c2 != nc:  # if c2 not equal to number of classes (i.e. for Classify() output)
                c2 = make_divisible(min(c2, max_channels) * width, 8)

            args = [c1, c2, *args[1:]]

            if m in (BottleneckCSP, C1, C2, C2f, C3, C3TR, C3Ghost, C3x, RepC3,RepC3_split):
                args.insert(2, n)  # number of repeats
                n = 1
        elif m is AIFI:
            args = [ch[f], *args]
        elif m in (HGStem, HGBlock):
            c1, cm, c2 = ch[f], args[0], args[1]
            args = [c1, cm, c2, *args[2:]]
            if m is HGBlock:
                args.insert(4, 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)
        elif m in (Detect, Segment, Pose):
            args.append([ch[x] for x in f])
            if m is Segment:
                args[2] = make_divisible(min(args[2], max_channels) * width, 8)
        elif m is RTDETRDecoder:  # special case, channels arg must be passed in index 1
            args.insert(1, [ch[x] for x in f])
        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 {EfficientViT_M0, EfficientViT_M1, EfficientViT_M2, EfficientViT_M3, EfficientViT_M4,EfficientViT_M5,
                   YOLOv8_EfficientViT_M0, YOLOv8_EfficientViT_M1, YOLOv8_EfficientViT_M2, YOLOv8_EfficientViT_M3,YOLOv8_EfficientViT_M4,YOLOv8_EfficientViT_M5}:
            m = m(*args)
            c2 = m.channel
        elif m is CBAM:
            c2 = ch[f]
            args = [c2, *args]
        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

        m.np = sum(x.numel() for x in m_.parameters())  # number params
        m_.i, m_.f, m_.type = i + 4 if is_backbone else i, f, t  # attach index, 'from' index, type
        if verbose:
            LOGGER.info(f'{i:>3}{str(f):>20}{n_:>3}{m.np:10.0f}  {t:<45}{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)

3.yolov8.yaml文件修改

yolov8.yaml

# 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: 80  # 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, 1, SPPF, [1024, 5]]  # 9

# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
  - [-1, 3, C2f, [512]]  # 12

  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 12], 1, Concat, [1]]  # cat head P4
  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 9], 1, Concat, [1]]  # cat head P5
  - [-1, 3, C2f, [1024]]  # 21 (P5/32-large)

  - [[15, 18, 21 ], 1, Detect, [nc]]  # Detect(P3, P4, P5)

EfficientVit.yaml

  在yolov8.yaml文件基础上进行网络模型的轻量级网络修改,yaml文件修改如下:
在这里插入图片描述

nc: 80  # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024]

backbone:
  # [from, repeats, module, args]
  - [-1, 1, YOLOv8_EfficientViT_M0, []]  # 4
  - [-1, 1, SPPF, [1024, 5]]  # 5

# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']] # 6
  - [[-1, 3], 1, Concat, [1]]  # 7 cat backbone P4
  - [-1, 3, C2f, [512]]  # 8

  - [-1, 1, nn.Upsample, [None, 2, 'nearest']] # 9
  - [[-1, 2], 1, Concat, [1]]  # 10 cat backbone P3
  - [-1, 3, C2f, [256]]  # 11 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]] # 12
  - [[-1, 8], 1, Concat, [1]]  # 13 cat head P4
  - [-1, 3, C2f, [512]]  # 14 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]] # 15
  - [[-1, 5], 1, Concat, [1]]  # 16 cat head P5
  - [-1, 3, C2f, [1024]]  # 17 (P5/32-large)

  - [[11, 14, 17], 1, Detect, [nc]]  # Detect(P3, P4, P5)

4.基于EfficientVit.yaml训练

在这里插入图片描述

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。如若转载,请注明出处:http://www.coloradmin.cn/o/2234641.html

如若内容造成侵权/违法违规/事实不符,请联系多彩编程网进行投诉反馈,一经查实,立即删除!

相关文章

碧桂园服务启动“乘梯无忧”专项行动 携手业主共筑电梯安全新未来

摘要&#xff1a;全国400城8000项目全面覆盖 电梯是当代社会不可或缺的垂直交通工具&#xff0c;电梯安全问题不仅关系到居民的日常生活&#xff0c;更关乎到他们的生命财产安全。随着生活节奏的加快&#xff0c;居民对电梯的运行效率也有了更高的要求和期待。 碧桂园服务在2…

应对AI与机器学习的安全与授权管理新挑战,CodeMeter不断创新引领保护方案

人工智能&#xff08;AI&#xff09;和机器学习&#xff08;ML&#xff09;技术正在快速发展&#xff0c;逐渐应用到全球各类主流系统、设备及关键应用场景中&#xff0c;尤其是在政府、商业和工业组织不断加深互联的情况下&#xff0c;AI和ML技术的影响日益广泛。虽然AI技术的…

【AI换装整合包及教程】OOTDiffusion: AI换装工具的革命性创新

引言 在当今这个数字化时代&#xff0c;人工智能&#xff08;AI&#xff09;技术的发展日新月异&#xff0c;从最初的语音识别、图像识别到现在的自然语言处理&#xff0c;AI的应用范围不断扩大&#xff0c;深刻地改变了我们的生活方式和工作模式。特别是在时尚界&#xff0c;…

全面解析:网络协议及其应用

&#x1f493; 博客主页&#xff1a;瑕疵的CSDN主页 &#x1f4dd; Gitee主页&#xff1a;瑕疵的gitee主页 ⏩ 文章专栏&#xff1a;《热点资讯》 # 全面解析&#xff1a;网络协议及其应用 文章目录 网络协议概述定义发展历程主要优势 主要网络协议应用层协议传输层协议网络层…

零基础‘自外网到内网’渗透过程详细记录(cc123靶场)——下

细节较多&#xff0c;篇幅较大&#xff0c;分为上/下两部分发布在两篇文章内 另一部分详见下面文章 零基础‘自外网到内网’渗透过程详细记录(cc123靶场)——上https://blog.csdn.net/weixin_62808713/article/details/143572185 八、第二层数据库服务器权限获取 猜到新闻资…

参数跟丢了之JS生成器和包装器

如需转载请注明出处.欢迎小伙伴一起讨论技术. 逆向网址:aHR0cHM6Ly91bmlvbi5qZC5jb20vcHJvTWFuYWdlci9pbmRleD9wYWdlTm89MQ 跟踪接口:aHR0cHM6Ly9hcGkubS5qZC5jb20vYXBp 跟踪参数:h5st 本文目标:记录学习下自定义的生成器和包装器,不做具体的参数加密逻辑分析 直接启动器进…

【浪潮商城-注册安全分析报告-无验证方式导致安全隐患】

前言 由于网站注册入口容易被黑客攻击&#xff0c;存在如下安全问题&#xff1a; 1. 暴力破解密码&#xff0c;造成用户信息泄露 2. 短信盗刷的安全问题&#xff0c;影响业务及导致用户投诉 3. 带来经济损失&#xff0c;尤其是后付费客户&#xff0c;风险巨大&#xff0c;造…

openGauss数据库-头歌实验1-5 修改数据库

一、查看表结构与修改表名 &#xff08;一&#xff09;任务描述 本关任务&#xff1a;修改表名&#xff0c;并能顺利查询到修改后表的结构。 &#xff08;二&#xff09;相关知识 为了完成本关任务&#xff0c;你需要掌握&#xff1a; 1.如何查看表的结构&#xff1b; 2.如…

linux 磁盘配额 quota

增加一个facl的的知识点&#xff1a; linux中默认的文件系统支持facl&#xff0c;如果是新挂载的分区&#xff0c;则不支持facl应用。需要在挂载文件系统时使用-o acl选项来启用facl支持。如下图显示 在/etc/fstab添加defaults,acl 1.启用磁盘配额功能&#xff1a;修改/etc/f…

进程和线程概念

进程 进程是系统进程资源分配和调度的一个独立单位。 进程的状态与转换 就绪 -> 阻塞 -> 执行 另外还有一个挂起操作&#xff0c;可将进程转入静止状态&#xff0c;知道激活操作&#xff0c;程序将恢复原有状态。 线程 线程更加轻量&#xff0c;作为调度和分派的基本…

三周精通FastAPI:27 使用使用SQLModel操作SQL (关系型) 数据库

官网文档&#xff1a;https://fastapi.tiangolo.com/zh/tutorial/sql-databases/ SQL (关系型) 数据库 FastAPI不需要你使用SQL(关系型)数据库。 但是您可以使用任何您想要的关系型数据库。 这里我们将看到一个使用SQLModel的示例。 SQLModel是在SQLAlchemy和Pydantic的基础…

Java 并发编程学习笔记

参考资料&#xff1a; JAVA并发专题 - 终有救赎的专栏 - 掘金 Java并发编程学习路线&#xff08;建议收藏&#xfffd;&#xfffd;&#xff09; | Java程序员进阶之路x沉默王二 面试题目&#xff1a; JUC第一讲&#xff1a;Java并发知识体系详解 面试题汇总(P6熟练 P7精通…

Docker篇(基础命令)

目录 一、启动与停止 二、镜像相关的命令 1. 查看镜像 2. 搜索镜像 3. 拉取镜像 4. 删除镜像 三、容器创建与启动容器 1. 查看容器 2. 创建容器 交互式方式创建容器 守护式方式创建容器 3. 容器启动与停止 四、容器操作命令 1. 文件拷贝 2. 目录&#xff08;文件…

qt QColorDialog详解

1、概述 QColorDialog是Qt框架中的一个对话框类&#xff0c;专门用于让用户选择颜色。它提供了一个标准的颜色选择界面&#xff0c;其中包括基本的颜色选择器&#xff08;如调色板和颜色轮&#xff09;、自定义颜色输入区域以及预定义颜色列表。QColorDialog支持RGB、HSV和十六…

算法练习:904. 水果成篮

题目链接&#xff1a;904. 水果成篮。 题目意思就是可以选取两个种类的水果不能超过两个种类&#xff0c;该种类个数没有限制&#xff0c; 但是一旦超过两个种类的水果就要停止计数。 示例中数组编号就是就是种类&#xff0c;就是不能出现三个不同编号的数。 1.暴力解法&…

JAVA WEB — HTML CSS 入门学习

本文为JAVAWEB 关于HTML 的基础学习 一 概述 HTML 超文本标记语言 超文本 超越文本的限制 比普通文本更强大 除了文字信息 还可以存储图片 音频 视频等标记语言 由标签构成的语言HTML标签都是预定义的 HTML直接在浏览器中运行 在浏览器解析 CSS 是一种用来表现HTML或XML等文…

深度学习:卷积神经网络中的im2col

im2col 是一种在卷积神经网络&#xff08;CNN&#xff09;中常用的技术&#xff0c;用于将输入图像数据转换为适合卷积操作的矩阵形式。通过这种转换&#xff0c;卷积操作可以被高效地实现为矩阵乘法&#xff0c;从而加速计算。 在传统的卷积操作中&#xff0c;卷积核&#xff…

【论文阅读】Associative Alignment for Few-shot Image Classification

用于小样本图像分类的关联对齐 引用&#xff1a;Afrasiyabi A, Lalonde J F, Gagn C. Associative alignment for few-shot image classification[C]//Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part V 16. Spri…

HCIP-HarmonyOS Application Developer V1.0 笔记(五)

弹窗功能 prompt模块来调用系统弹窗API进行弹窗制作。 当前支持3种弹窗API&#xff0c;分别为&#xff1a; 文本弹窗&#xff0c;prompt.showToast&#xff1b;对话框&#xff0c;prompt.showDialog&#xff1b;操作菜单&#xff0c;prompt.showActionMenu。 要使用弹窗功能&…

【办公类-04-04】华为助手导出照片视频分类(根据图片、视频的文件名日期导入“年-月-日”文件夹中,并转移到“年-月”文件中整理、转移到“年”文件夹中整理)

背景需求 最近带班&#xff0c;没有时间整理照片&#xff0c;偶尔导一次&#xff0c;几个月的照片。发现用电脑版“华为手机助手“中的WLAN连接”与华为手机的“华为手机助手”连接&#xff0c;速度更快、更稳定&#xff0c;不会出现数据线连接时碰碰就断网的问题 1、先打开电…