目标检测算法改进系列之Backbone替换为RepViT

news2024/11/19 21:14:09

RepViT简介

轻量级模型研究一直是计算机视觉任务中的一个焦点，其目标是在降低计算成本的同时达到优秀的性能。轻量级模型与资源受限的移动设备尤其相关，使得视觉模型的边缘部署成为可能。在过去十年中，研究人员主要关注轻量级卷积神经网络（CNNs）的设计，提出了许多高效的设计原则，包括可分离卷积 [2] 、逆瓶颈结构 [3] 、通道打乱 [4] 和结构重参数化 [5] 等，产生了 MobileNets [2, 3]，ShuffleNets [4] 和 RepVGG [5] 等代表性模型。

另一方面，视觉 Transformers（ViTs）成为学习视觉表征的另一种高效方案。与 CNNs 相比，ViTs 在各种计算机视觉任务中表现出了更优越的性能。然而，ViT 模型一般尺寸很大，延迟很高，不适合资源受限的移动设备。因此，研究人员开始探索 ViT 的轻量级设计。许多高效的ViTs设计原则被提出，大大提高了移动设备上 ViTs 的计算效率，产生了EfficientFormers [6] ，MobileViTs [7] 等代表性模型。这些轻量级 ViTs 在移动设备上展现出了相比 CNNs 的更强的性能和更低的延迟。

轻量级 ViTs 优于轻量级 CNNs 的原因通常归结于多头注意力模块，该模块使模型能够学习全局表征。然而，轻量级 ViTs 和轻量级 CNNs 在块结构、宏观和微观架构设计方面存在值得注意的差异，但这些差异尚未得到充分研究。这自然引出了一个问题：轻量级 ViTs 的架构选择能否提高轻量级 CNN 的性能？在这项工作中，我们结合轻量级 ViTs 的架构选择，重新审视了轻量级 CNNs 的设计。我们的旨在缩小轻量级 CNNs 与轻量级 ViTs 之间的差距，并强调前者与后者相比在移动设备上的应用潜力。

原文地址：RepViT: Revisiting Mobile CNN From ViT Perspective

RepViT结构图

RepViT代码实现

import torch.nn as nn
import numpy as np
from timm.models.layers import SqueezeExcite
import torch

__all__ = ['repvit_m1', 'repvit_m2', 'repvit_m3']

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

def _make_divisible(v, divisor, min_value=None):
    """
    This function is taken from the original tf repo.
    It ensures that all layers have a channel number that is divisible by 8
    It can be seen here:
    https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
    :param v:
    :param divisor:
    :param min_value:
    :return:
    """
    if min_value is None:
        min_value = divisor
    new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
    # Make sure that round down does not go down by more than 10%.
    if new_v < 0.9 * v:
        new_v += divisor
    return new_v

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 fuse_self(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,
            device=c.weight.device)
        m.weight.data.copy_(w)
        m.bias.data.copy_(b)
        return m

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)
    
    @torch.no_grad()
    def fuse_self(self):
        if isinstance(self.m, Conv2d_BN):
            m = self.m.fuse_self()
            assert(m.groups == m.in_channels)
            identity = torch.ones(m.weight.shape[0], m.weight.shape[1], 1, 1)
            identity = torch.nn.functional.pad(identity, [1,1,1,1])
            m.weight += identity.to(m.weight.device)
            return m
        elif isinstance(self.m, torch.nn.Conv2d):
            m = self.m
            assert(m.groups != m.in_channels)
            identity = torch.ones(m.weight.shape[0], m.weight.shape[1], 1, 1)
            identity = torch.nn.functional.pad(identity, [1,1,1,1])
            m.weight += identity.to(m.weight.device)
            return m
        else:
            return self


class RepVGGDW(torch.nn.Module):
    def __init__(self, ed) -> None:
        super().__init__()
        self.conv = Conv2d_BN(ed, ed, 3, 1, 1, groups=ed)
        self.conv1 = Conv2d_BN(ed, ed, 1, 1, 0, groups=ed)
        self.dim = ed
    
    def forward(self, x):
        return self.conv(x) + self.conv1(x) + x
    
    @torch.no_grad()
    def fuse_self(self):
        conv = self.conv.fuse_self()
        conv1 = self.conv1.fuse_self()
        
        conv_w = conv.weight
        conv_b = conv.bias
        conv1_w = conv1.weight
        conv1_b = conv1.bias
        
        conv1_w = torch.nn.functional.pad(conv1_w, [1,1,1,1])

        identity = torch.nn.functional.pad(torch.ones(conv1_w.shape[0], conv1_w.shape[1], 1, 1, device=conv1_w.device), [1,1,1,1])

        final_conv_w = conv_w + conv1_w + identity
        final_conv_b = conv_b + conv1_b

        conv.weight.data.copy_(final_conv_w)
        conv.bias.data.copy_(final_conv_b)
        return conv


class RepViTBlock(nn.Module):
    def __init__(self, inp, hidden_dim, oup, kernel_size, stride, use_se, use_hs):
        super(RepViTBlock, self).__init__()
        assert stride in [1, 2]

        self.identity = stride == 1 and inp == oup
        assert(hidden_dim == 2 * inp)

        if stride == 2:
            self.token_mixer = nn.Sequential(
                Conv2d_BN(inp, inp, kernel_size, stride, (kernel_size - 1) // 2, groups=inp),
                SqueezeExcite(inp, 0.25) if use_se else nn.Identity(),
                Conv2d_BN(inp, oup, ks=1, stride=1, pad=0)
            )
            self.channel_mixer = Residual(nn.Sequential(
                    # pw
                    Conv2d_BN(oup, 2 * oup, 1, 1, 0),
                    nn.GELU() if use_hs else nn.GELU(),
                    # pw-linear
                    Conv2d_BN(2 * oup, oup, 1, 1, 0, bn_weight_init=0),
                ))
        else:
            assert(self.identity)
            self.token_mixer = nn.Sequential(
                RepVGGDW(inp),
                SqueezeExcite(inp, 0.25) if use_se else nn.Identity(),
            )
            self.channel_mixer = Residual(nn.Sequential(
                    # pw
                    Conv2d_BN(inp, hidden_dim, 1, 1, 0),
                    nn.GELU() if use_hs else nn.GELU(),
                    # pw-linear
                    Conv2d_BN(hidden_dim, oup, 1, 1, 0, bn_weight_init=0),
                ))

    def forward(self, x):
        return self.channel_mixer(self.token_mixer(x))

class RepViT(nn.Module):
    def __init__(self, cfgs):
        super(RepViT, self).__init__()
        # setting of inverted residual blocks
        self.cfgs = cfgs

        # building first layer
        input_channel = self.cfgs[0][2]
        patch_embed = torch.nn.Sequential(Conv2d_BN(3, input_channel // 2, 3, 2, 1), torch.nn.GELU(),
                           Conv2d_BN(input_channel // 2, input_channel, 3, 2, 1))
        layers = [patch_embed]
        # building inverted residual blocks
        block = RepViTBlock
        for k, t, c, use_se, use_hs, s in self.cfgs:
            output_channel = _make_divisible(c, 8)
            exp_size = _make_divisible(input_channel * t, 8)
            layers.append(block(input_channel, exp_size, output_channel, k, s, use_se, use_hs))
            input_channel = output_channel
        self.features = nn.ModuleList(layers)
        self.channel = [i.size(1) for i in self.forward(torch.randn(1, 3, 640, 640))]
        
    def forward(self, x):
        input_size = x.size(2)
        scale = [4, 8, 16, 32]
        features = [None, None, None, None]
        for f in self.features:
            x = f(x)
            if input_size // x.size(2) in scale:
                features[scale.index(input_size // x.size(2))] = x
        return features
    
    def switch_to_deploy(self):
        replace_batchnorm(self)

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

def repvit_m1(weights=''):
    """
    Constructs a MobileNetV3-Large model
    """
    cfgs = [
        # k, t, c, SE, HS, s 
        [3,   2,  48, 1, 0, 1],
        [3,   2,  48, 0, 0, 1],
        [3,   2,  48, 0, 0, 1],
        [3,   2,  96, 0, 0, 2],
        [3,   2,  96, 1, 0, 1],
        [3,   2,  96, 0, 0, 1],
        [3,   2,  96, 0, 0, 1],
        [3,   2,  192, 0, 1, 2],
        [3,   2,  192, 1, 1, 1],
        [3,   2,  192, 0, 1, 1],
        [3,   2,  192, 1, 1, 1],
        [3,   2, 192, 0, 1, 1],
        [3,   2, 192, 1, 1, 1],
        [3,   2, 192, 0, 1, 1],
        [3,   2, 192, 1, 1, 1],
        [3,   2, 192, 0, 1, 1],
        [3,   2, 192, 1, 1, 1],
        [3,   2, 192, 0, 1, 1],
        [3,   2, 192, 1, 1, 1],
        [3,   2, 192, 0, 1, 1],
        [3,   2, 192, 1, 1, 1],
        [3,   2, 192, 0, 1, 1],
        [3,   2, 192, 0, 1, 1],
        [3,   2, 384, 0, 1, 2],
        [3,   2, 384, 1, 1, 1],
        [3,   2, 384, 0, 1, 1]
    ]
    model = RepViT(cfgs)
    if weights:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(weights)['model']))
    return model

def repvit_m2(weights=''):
    """
    Constructs a MobileNetV3-Large model
    """
    cfgs = [
        # k, t, c, SE, HS, s 
        [3,   2,  64, 1, 0, 1],
        [3,   2,  64, 0, 0, 1],
        [3,   2,  64, 0, 0, 1],
        [3,   2,  128, 0, 0, 2],
        [3,   2,  128, 1, 0, 1],
        [3,   2,  128, 0, 0, 1],
        [3,   2,  128, 0, 0, 1],
        [3,   2,  256, 0, 1, 2],
        [3,   2,  256, 1, 1, 1],
        [3,   2,  256, 0, 1, 1],
        [3,   2,  256, 1, 1, 1],
        [3,   2, 256, 0, 1, 1],
        [3,   2, 256, 1, 1, 1],
        [3,   2, 256, 0, 1, 1],
        [3,   2, 256, 1, 1, 1],
        [3,   2, 256, 0, 1, 1],
        [3,   2, 256, 1, 1, 1],
        [3,   2, 256, 0, 1, 1],
        [3,   2, 256, 1, 1, 1],
        [3,   2, 256, 0, 1, 1],
        [3,   2, 256, 0, 1, 1],
        [3,   2, 512, 0, 1, 2],
        [3,   2, 512, 1, 1, 1],
        [3,   2, 512, 0, 1, 1]
    ]
    model = RepViT(cfgs)
    if weights:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(weights)['model']))
    return model

def repvit_m3(weights=''):
    """
    Constructs a MobileNetV3-Large model
    """
    cfgs = [
        # k, t, c, SE, HS, s 
        [3,   2,  64, 1, 0, 1],
        [3,   2,  64, 0, 0, 1],
        [3,   2,  64, 1, 0, 1],
        [3,   2,  64, 0, 0, 1],
        [3,   2,  64, 0, 0, 1],
        [3,   2,  128, 0, 0, 2],
        [3,   2,  128, 1, 0, 1],
        [3,   2,  128, 0, 0, 1],
        [3,   2,  128, 1, 0, 1],
        [3,   2,  128, 0, 0, 1],
        [3,   2,  128, 0, 0, 1],
        [3,   2,  256, 0, 1, 2],
        [3,   2,  256, 1, 1, 1],
        [3,   2,  256, 0, 1, 1],
        [3,   2,  256, 1, 1, 1],
        [3,   2,  256, 0, 1, 1],
        [3,   2,  256, 1, 1, 1],
        [3,   2,  256, 0, 1, 1],
        [3,   2,  256, 1, 1, 1],
        [3,   2, 256, 0, 1, 1],
        [3,   2, 256, 1, 1, 1],
        [3,   2, 256, 0, 1, 1],
        [3,   2, 256, 1, 1, 1],
        [3,   2, 256, 0, 1, 1],
        [3,   2, 256, 1, 1, 1],
        [3,   2, 256, 0, 1, 1],
        [3,   2, 256, 1, 1, 1],
        [3,   2, 256, 0, 1, 1],
        [3,   2, 256, 1, 1, 1],
        [3,   2, 256, 0, 1, 1],
        [3,   2, 256, 0, 1, 1],
        [3,   2, 512, 0, 1, 2],
        [3,   2, 512, 1, 1, 1],
        [3,   2, 512, 0, 1, 1]
    ]
    model = RepViT(cfgs)
    if weights:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(weights)['model']))
    return model

if __name__ == '__main__':
    model = repvit_m1('repvit_m1_distill_300.pth')
    inputs = torch.randn((1, 3, 640, 640))
    res = model(inputs)
    for i in res:
        print(i.size())

Backbone替换

yolo.py修改

def parse_model函数

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 {repvit_m1}: #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函数

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

创建.yaml配置文件

# 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, repvit_m1, [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)
  ]

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/1062385.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

整体网络架构p22

整体网络架构p22

1. 两次卷积&#xff0c;一次池化。得到一个三维特征图&#xff0c;然后让三维的特征图&#xff0c;三个值进行相乘拉成特征向量&#xff0c;把得到的结果需要靠全连接层。 带参数计算才算一层 算conv的个数FC全连接层就得到卷积神经网络的层数 FC:全连接层 2. 3.reset网络&a…
阅读更多...
连接查询-多表联合查

连接查询-多表联合查

一、连接查询的分类 根据表的连接方式&#xff0c;连接查询分为内连接、外连接和全连接。 内连接&#xff1a; 等值连接非等值连接自连接外连接&#xff1a; 左外连接&#xff08;左连接&#xff09;右外连接&#xff08;右连接&#xff09; 全连接 二、笛卡尔积 交叉连接也…
阅读更多...
番外--Task1:

番外--Task1:

""" 重置root管理员密码添加yum源测试软件包安装成功 """ step1: 在shell界面输入重启命令&#xff1b; step2: 重启过程中出现此界面&#xff0c;快速按键盘‘e’, 进入系统内核程序&#xff1b; step3: 在系统内核程序内&#xff0c…
阅读更多...
【MATLAB源码-第42期】基于matlab的人民币面额识别系统（GUI）。

【MATLAB源码-第42期】基于matlab的人民币面额识别系统（GUI）。

操作环境&#xff1a; MATLAB 2022a 1、算法描述 基于 MATLAB 的人民币面额识别系统设计可以分为以下步骤&#xff1a; 1. 数据收集与预处理 数据收集&#xff1a; 收集不同面额的人民币照片&#xff0c;如 1 元、5 元、10 元、20 元、50 元和 100 元。确保在不同环境、不…
阅读更多...
【算法学习】-【双指针】-【盛水最多的容器】

【算法学习】-【双指针】-【盛水最多的容器】

LeetCode原题链接&#xff1a;盛水最多的容器 下面是题目描述&#xff1a; 给定一个长度为 n 的整数数组 height 。有 n 条垂线&#xff0c;第 i 条线的两个端点是 (i, 0) 和 (i, height[i]) 。 找出其中的两条线&#xff0c;使得它们与 x 轴共同构成的容器可以容纳最多的水。…
阅读更多...
Net相关的各类开源项目

Net相关的各类开源项目

Net相关的各类开源项目 WPFHandyControlLive-ChartsWPFDeveloperswpf-uidesignStylet WebScheduleMasterYiShaAdminBlog.CoreNebula.AdminNewLife.CubeOpenAuth UnityuGUIUnityCsReferenceEpitomeMyUnityFrameWorkKSFrameworkTowerDefense-GameFramework-Demo 通用ClientServer…
阅读更多...
目标检测算法改进系列之Backbone替换为InceptionNeXt

目标检测算法改进系列之Backbone替换为InceptionNeXt

InceptionNeXt 受 Vision Transformer 长距离依赖关系建模能力的启发&#xff0c;最近一些视觉模型开始上大 Kernel 的 Depth-Wise 卷积&#xff0c;比如一篇出色的工作 ConvNeXt。虽然这种 Depth-Wise 的算子只消耗少量的 FLOPs&#xff0c;但由于高昂的内存访问成本 (memory…
阅读更多...
机器学习必修课 - 编码分类变量 encoding categorical variables

机器学习必修课 - 编码分类变量 encoding categorical variables

1. 数据预处理和数据集分割 import pandas as pd from sklearn.model_selection import train_test_split导入所需的Python库 !git clone https://github.com/JeffereyWu/Housing-prices-data.git下载数据集 # Read the data X pd.read_csv(/content/Housing-prices-data/t…
阅读更多...
CTFshow Web入门 文件上传

CTFshow Web入门 文件上传

目录 web151 web152 web153 web154 web155 web156 web157 web158、web159 web160 web161 web162 web163 web164 web165 web166 web167 web168 web169 web170 web151 1. 写马改后缀为png上传&#xff0c;抓包修改文件信息 回显路径&#xff0c;蚁剑连接 2. …
阅读更多...
仿函数的学习

仿函数的学习

仿函数 也叫 函数对象 仿函数是什么东西&#xff1f; 当你第一眼看到下面的代码的时候&#xff0c;你会觉得它是一个函数的调用&#xff1a; bool result less(a, b);但是我如果告诉你&#xff0c;less 是一个我自定义的一个类的对象呢&#xff1f; class Less { public:bo…
阅读更多...
不标准的 json 格式的字符串如何转为标准的（json字符串属性名不带双引号如何转

不标准的 json 格式的字符串如何转为标准的（json字符串属性名不带双引号如何转

背景 不规范的 json 字符串例如 属性名不带双引号 {name:"abc"}属性名带单引号而不是双引号 {name:"abc"}属性值该用双引号的时候用了单引号 {"name":abc}还有一种情况就是以上情况的混合 所谓规范的json字串就是属性名要用双引号&#xf…
阅读更多...
13种改进粒子群优化算法 matlab2022 运行结果和耗时对比

13种改进粒子群优化算法 matlab2022 运行结果和耗时对比

前言 阅读粒子群优化算法的文章&#xff0c;发现代码不仅要付费而且还没有运行结果&#xff0c;需要自己手动写代码运行&#xff0c;这里提供下我的运行结果。包含参数结果和耗时对比。 https://www.bilibili.com/read/cv11905136/?spm_id_from333.999.0.0 % 定义适应度函数 …
阅读更多...
Visual Studio Code 安裝

Visual Studio Code 安裝

一、Visual Studio Code 安裝 VS Code 下载地址&#xff1a;https://code.visualstudio.com/ windows系统的快速下载地址&#xff1a;https://vscode.cdn.azure.cn/stable/441438abd1ac652551dbe4d408dfcec8a499b8bf/VSCodeUserSetup-x64-1.75.1.exe macOS系统的快速下载地址…
阅读更多...
最短路径专题6 最短路径-多路径

最短路径专题6 最短路径-多路径

题目&#xff1a; 样例&#xff1a; 输入 4 5 0 2 0 1 2 0 2 5 0 3 1 1 2 1 3 2 2 输出 2 0->1->2 0->3->2 思路&#xff1a; 根据题意&#xff0c;最短路模板还是少不了的&#xff0c; 我们要添加的是&#xff0c; 记录各个结点有多少个上一个结点走动得来的…
阅读更多...
即时通讯软件

即时通讯软件

通信协议 发送消息可以是个struct 客户端分两个线程&#xff1a;读取服务器&#xff0c;给服务器发&#xff08;否则会导致阻塞&#xff09; read和write的第二个参数类型是&#xff1a;void *buf——————不仅仅是一个字符串&#xff0c;也可以是一个结构体等等&#xf…
阅读更多...
【进程管理】初识进程

【进程管理】初识进程

一.何为进程 教材一般会给出这样的答案: 运行起来的程序 或者 内存中的程序 这样说太抽象了&#xff0c;那我问程序和进程有什么区别呢&#xff1f;诶&#xff1f;这我知道&#xff0c;书上说&#xff0c;动态的叫进程&#xff0c;静态的叫程序。那么静态和动态又是什么意思…
阅读更多...
JAVA面经整理(8)

JAVA面经整理(8)

一)为什么要有区&#xff0c;段&#xff0c;页&#xff1f; 1)页是内存和磁盘之间交互的基本单位内存中的值修改之后刷到磁盘的时候还是以页为单位的索引结构给程序员提供了高效的索引实现方式&#xff0c;不过索引信息以及数据记录都是记录在文件上面的&#xff0c;确切来说是…
阅读更多...
buuctf-[GXYCTF2019]禁止套娃 git泄露，无参数rce

buuctf-[GXYCTF2019]禁止套娃 git泄露，无参数rce

用dirsearch扫一下&#xff0c;看到flag.php 访问一下没啥东西&#xff0c;使用githack python2 GitHack.py http://8996e81f-a75c-4180-b0ad-226d97ba61b2.node4.buuoj.cn/.git/查看index.php <?php include "flag.php"; echo "flag在哪里呢&#xff1f;…
阅读更多...
【Jmeter】性能测试脚本开发——性能测试环境准备、Jmeter脚本编写和执行

【Jmeter】性能测试脚本开发——性能测试环境准备、Jmeter脚本编写和执行

文章目录 一、常用的Jmeter元件二、性能测试环境准备三、编写Jmeter脚本四、执行测试脚本 一、常用的Jmeter元件 取样器-HTTP请求 作用&#xff1a;发送HTTP请求配置原件-HTTP请求默认值 作用&#xff1a;设置HTTP请求的默认参数配置原件-用户定义的变量 作用&#xff1a;定义…
阅读更多...
在win10里顺利安装了apache2.4.41和php7.4.29

在win10里顺利安装了apache2.4.41和php7.4.29

最近在学习网站搭建。其中有一项内容是在windows操作系统里搭建apachephp环境。几天前根据一本书的上的说明尝试了一下&#xff0c;在win10操作系统里安装这两个软件&#xff1a;apache2.4.41和php7.4.29&#xff0c;安装以后apche能正常启动&#xff0c;但是php没有正常工作。…
阅读更多...
推荐文章
最新文章

Copyright @ 2022~2023