基于深度学习的花卉检测系统(含PyQt界面)

基于深度学习的花卉检测系统(含PyQt界面)

  • 前言
  • 一、数据集
    • 1.1 数据集介绍
    • 1.2 数据预处理
  • 二、模型搭建
  • 三、训练与测试
    • 3.1 模型训练
    • 3.2 模型测试
  • 四、PyQt界面实现
  • 参考资料

前言

本项目是基于swin_transformer深度学习网络模型的花卉检测系统,目前能够检测daisy、dandelion、roses、sunflowers、tulips五类花卉,可以自己添加花卉种类进行训练。本文将详述数据集处理、模型构建、训练代码、以及基于PyQt5的应用界面设计。在应用中可以对花卉的图片进行识别,输出花卉的类别和模型对其预测结果的置信度。本文附带了完整的应用界面设计、深度学习模型代码和训练数据集的下载链接。

完整资源下载链接:博主在面包多网站上的完整资源下载页

项目演示视频:

【项目分享】基于深度学习的花卉检测系统(含PyQt界面)

一、数据集

1.1 数据集介绍

本项目使用的数据集是由谷歌创建的一个用于机器学习和计算机视觉任务的图像数据集,称为花卉数据集(Flower Photos Dataset)。它包含了来自五种不同花卉类别的图像,每个类别大约有几百到一千张图像。这些花卉类别包括:雏菊(Daisy)、蒲公英(Dandelion)、玫瑰(Roses)、向日葵(Sunflowers)、郁金香(Tulips) 。

下载链接:http://download.tensorflow.org/example_images/flower_photos.tgz

下载后得到一个.tgr文件,解压后,文件夹下包含了5个子文件夹,每个子文件夹都存储了一种类别的花的图片,子文件夹的名称就是花的类别的名称,如下图:
在这里插入图片描述

1.2 数据预处理

使用MyDataSet类在 PyTorch 中加载图像数据并将其与相应的类别标签配对,完成自定义数据集的生成。它包含初始化方法__init__来接收图像文件路径列表和对应的类别标签列表,并提供了__getitem__方法来获取图像及其标签,同时还可以使用collate_fn将多个样本进行批处理。

class MyDataSet(Dataset):
    """自定义数据集"""

    def __init__(self, images_path: list, images_class: list, transform=None):
        self.images_path = images_path
        self.images_class = images_class
        self.transform = transform

    def __len__(self):
        return len(self.images_path)

    def __getitem__(self, item):
        img = Image.open(self.images_path[item])
        # RGB为彩色图片,L为灰度图片
        if img.mode != 'RGB':
            raise ValueError("image: {} isn't RGB mode.".format(self.images_path[item]))
        label = self.images_class[item]

        if self.transform is not None:
            img = self.transform(img)

        return img, label

    @staticmethod
    def collate_fn(batch):
        # 官方实现的default_collate可以参考
        # https://github.com/pytorch/pytorch/blob/67b7e751e6b5931a9f45274653f4f653a4e6cdf6/torch/utils/data/_utils/collate.py
        images, labels = tuple(zip(*batch))

        images = torch.stack(images, dim=0)
        labels = torch.as_tensor(labels)
        return images, labels

二、模型搭建

我们使用的是一种称为 Swin_Transformer 的新视觉 Transformer,它可以作为 CV 的通用主干。将 Transformer 从语言适应到视觉方面的挑战来自两个域之间的差异,例如视觉实体的规模以及相比于文本单词的高分辨率图像像素的巨大差异。为解决这些差异,我们提出了一种 层次化 (hierarchical) Transformer,其表示是用移位窗口 (Shifted Windows) 计算的。移位窗口方案通过将自注意力计算限制在不重叠的局部窗口的同时,还允许跨窗口连接来提高效率。这种分层架构具有在各种尺度上建模的灵活性,并且相对于图像大小具有线性计算复杂度。Swin Transformer 的这些特性使其与广泛的视觉任务兼容,包括图像分类(ImageNet-1K 的 87.3 top-1 Acc)和密集预测任务,例如目标检测(COCO test dev 的 58.7 box AP 和 51.1 mask AP)和语义分割(ADE20K val 的 53.5 mIoU)。它的性能在 COCO 上以 +2.7 box AP 和 +2.6 mask AP 以及在 ADE20K 上 +3.2 mIoU 的大幅度超越了SOTA 技术,证明了基于 Transformer 的模型作为视觉主干的潜力。分层设计和移位窗口方法也证明了其对全 MLP 架构是有益的。Swin_Transformer模型的整体架构,如下图所示:
在这里插入图片描述
而我们代码的模型具体实现主要包括如下几个模块:PatchEmbed 模块WindowAttention模块、SwinTransformerBlock模块 BasicLayer模块、SwinTransformer模块以及辅助函数drop_path_f等。

PatchEmbed 模块:将输入图像划分为不重叠的图像块,并将每个图像块转换为嵌入向量。

class PatchEmbed(nn.Module):
    """
    2D Image to Patch Embedding
    """
    def __init__(self, patch_size=4, in_c=3, embed_dim=96, norm_layer=None):
        super().__init__()
        patch_size = (patch_size, patch_size)
        self.patch_size = patch_size
        self.in_chans = in_c
        self.embed_dim = embed_dim
        self.proj = nn.Conv2d(in_c, embed_dim, kernel_size=patch_size, stride=patch_size)
        self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity()

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

        # padding
        # 如果输入图片的H,W不是patch_size的整数倍,需要进行padding
        pad_input = (H % self.patch_size[0] != 0) or (W % self.patch_size[1] != 0)
        if pad_input:
            # to pad the last 3 dimensions,
            # (W_left, W_right, H_top,H_bottom, C_front, C_back)
            x = F.pad(x, (0, self.patch_size[1] - W % self.patch_size[1],
                          0, self.patch_size[0] - H % self.patch_size[0],
                          0, 0))

        # 下采样patch_size倍
        x = self.proj(x)
        _, _, H, W = x.shape
        # flatten: [B, C, H, W] -> [B, C, HW]
        # transpose: [B, C, HW] -> [B, HW, C]
        x = x.flatten(2).transpose(1, 2)
        x = self.norm(x)
        return x, H, W

WindowAttention 模块:基于窗口的多头自注意力机制,用于捕获图像块之间的全局关系。

class WindowAttention(nn.Module):
    r""" Window based multi-head self attention (W-MSA) module with relative position bias.
    It supports both of shifted and non-shifted window.

    Args:
        dim (int): Number of input channels.
        window_size (tuple[int]): The height and width of the window.
        num_heads (int): Number of attention heads.
        qkv_bias (bool, optional):  If True, add a learnable bias to query, key, value. Default: True
        attn_drop (float, optional): Dropout ratio of attention weight. Default: 0.0
        proj_drop (float, optional): Dropout ratio of output. Default: 0.0
    """

    def __init__(self, dim, window_size, num_heads, qkv_bias=True, attn_drop=0., proj_drop=0.):

        super().__init__()
        self.dim = dim
        self.window_size = window_size  # [Mh, Mw]
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = 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*Mh-1 * 2*Mw-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, Mh, Mw]
        coords_flatten = torch.flatten(coords, 1)  # [2, Mh*Mw]
        # [2, Mh*Mw, 1] - [2, 1, Mh*Mw]
        relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :]  # [2, Mh*Mw, Mh*Mw]
        relative_coords = relative_coords.permute(1, 2, 0).contiguous()  # [Mh*Mw, Mh*Mw, 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)  # [Mh*Mw, Mh*Mw]
        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.trunc_normal_(self.relative_position_bias_table, std=.02)
        self.softmax = nn.Softmax(dim=-1)

    def forward(self, x, mask: Optional[torch.Tensor] = None):
        """
        Args:
            x: input features with shape of (num_windows*B, Mh*Mw, C)
            mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None
        """
        # [batch_size*num_windows, Mh*Mw, total_embed_dim]
        B_, N, C = x.shape
        # qkv(): -> [batch_size*num_windows, Mh*Mw, 3 * total_embed_dim]
        # reshape: -> [batch_size*num_windows, Mh*Mw, 3, num_heads, embed_dim_per_head]
        # permute: -> [3, batch_size*num_windows, num_heads, Mh*Mw, embed_dim_per_head]
        qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
        # [batch_size*num_windows, num_heads, Mh*Mw, embed_dim_per_head]
        q, k, v = qkv.unbind(0)  # make torchscript happy (cannot use tensor as tuple)

        # transpose: -> [batch_size*num_windows, num_heads, embed_dim_per_head, Mh*Mw]
        # @: multiply -> [batch_size*num_windows, num_heads, Mh*Mw, Mh*Mw]
        q = q * self.scale
        attn = (q @ k.transpose(-2, -1))

        # relative_position_bias_table.view: [Mh*Mw*Mh*Mw,nH] -> [Mh*Mw,Mh*Mw,nH]
        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)
        relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous()  # [nH, Mh*Mw, Mh*Mw]
        attn = attn + relative_position_bias.unsqueeze(0)

        if mask is not None:
            # mask: [nW, Mh*Mw, Mh*Mw]
            nW = mask.shape[0]  # num_windows
            # attn.view: [batch_size, num_windows, num_heads, Mh*Mw, Mh*Mw]
            # mask.unsqueeze: [1, nW, 1, Mh*Mw, Mh*Mw]
            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)

        # @: multiply -> [batch_size*num_windows, num_heads, Mh*Mw, embed_dim_per_head]
        # transpose: -> [batch_size*num_windows, Mh*Mw, num_heads, embed_dim_per_head]
        # reshape: -> [batch_size*num_windows, Mh*Mw, total_embed_dim]
        x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
        x = self.proj(x)
        x = self.proj_drop(x)
        return x

SwinTransformerBlock 模块:Swin Transformer 的基本模块,包含了窗口注意力机制和MLP前馈网络。

class SwinTransformerBlock(nn.Module):
    r""" Swin Transformer Block.

    Args:
        dim (int): Number of input channels.
        num_heads (int): Number of attention heads.
        window_size (int): Window size.
        shift_size (int): Shift size for SW-MSA.
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
        qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
        drop (float, optional): Dropout rate. Default: 0.0
        attn_drop (float, optional): Attention dropout rate. Default: 0.0
        drop_path (float, optional): Stochastic depth rate. Default: 0.0
        act_layer (nn.Module, optional): Activation layer. Default: nn.GELU
        norm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNorm
    """

    def __init__(self, dim, num_heads, window_size=7, shift_size=0,
                 mlp_ratio=4., qkv_bias=True, drop=0., attn_drop=0., drop_path=0.,
                 act_layer=nn.GELU, 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
        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,
            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 forward(self, x, attn_mask):
        H, W = self.H, self.W
        B, L, C = x.shape
        assert L == H * W, "input feature has wrong size"

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

        # pad feature maps to multiples of window size
        # 把feature map给pad到window size的整数倍
        pad_l = pad_t = 0
        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, 0, pad_l, pad_r, pad_t, pad_b))
        _, Hp, Wp, _ = x.shape

        # 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
            attn_mask = None

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

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

        # merge windows
        attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)  # [nW*B, Mh, Mw, C]
        shifted_x = window_reverse(attn_windows, self.window_size, Hp, Wp)  # [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

        if pad_r > 0 or pad_b > 0:
            # 把前面pad的数据移除掉
            x = x[:, :H, :W, :].contiguous()

        x = x.view(B, H * W, C)

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

        return x

BasicLayer 模块:用于构建 Swin Transformer 的一个阶段,可以包含多个 SwinTransformerBlock 模块。

class BasicLayer(nn.Module):
    """
    A basic Swin Transformer layer for one stage.

    Args:
        dim (int): Number of input channels.
        depth (int): Number of blocks.
        num_heads (int): Number of attention heads.
        window_size (int): Local window size.
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
        qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
        drop (float, optional): Dropout rate. Default: 0.0
        attn_drop (float, optional): Attention dropout rate. Default: 0.0
        drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0
        norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
        downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None
        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
    """

    def __init__(self, dim, depth, num_heads, window_size,
                 mlp_ratio=4., qkv_bias=True, drop=0., attn_drop=0.,
                 drop_path=0., norm_layer=nn.LayerNorm, downsample=None, use_checkpoint=False):
        super().__init__()
        self.dim = dim
        self.depth = depth
        self.window_size = window_size
        self.use_checkpoint = use_checkpoint
        self.shift_size = window_size // 2

        # build blocks
        self.blocks = nn.ModuleList([
            SwinTransformerBlock(
                dim=dim,
                num_heads=num_heads,
                window_size=window_size,
                shift_size=0 if (i % 2 == 0) else self.shift_size,
                mlp_ratio=mlp_ratio,
                qkv_bias=qkv_bias,
                drop=drop,
                attn_drop=attn_drop,
                drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path,
                norm_layer=norm_layer)
            for i in range(depth)])

        # patch merging layer
        if downsample is not None:
            self.downsample = downsample(dim=dim, norm_layer=norm_layer)
        else:
            self.downsample = None

    def create_mask(self, x, H, W):
        # calculate attention mask for SW-MSA
        # 保证Hp和Wp是window_size的整数倍
        Hp = int(np.ceil(H / self.window_size)) * self.window_size
        Wp = int(np.ceil(W / self.window_size)) * self.window_size
        # 拥有和feature map一样的通道排列顺序,方便后续window_partition
        img_mask = torch.zeros((1, Hp, Wp, 1), device=x.device)  # [1, Hp, Wp, 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

        mask_windows = window_partition(img_mask, self.window_size)  # [nW, Mh, Mw, 1]
        mask_windows = mask_windows.view(-1, self.window_size * self.window_size)  # [nW, Mh*Mw]
        attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)  # [nW, 1, Mh*Mw] - [nW, Mh*Mw, 1]
        # [nW, Mh*Mw, Mh*Mw]
        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, H, W):
        attn_mask = self.create_mask(x, H, W)  # [nW, Mh*Mw, Mh*Mw]
        for blk in self.blocks:
            blk.H, blk.W = H, W
            if not torch.jit.is_scripting() and self.use_checkpoint:
                x = checkpoint.checkpoint(blk, x, attn_mask)
            else:
                x = blk(x, attn_mask)
        if self.downsample is not None:
            x = self.downsample(x, H, W)
            H, W = (H + 1) // 2, (W + 1) // 2

        return x, H, W

SwinTransformer 模块:整个 Swin Transformer 模型的主体结构,包含了多个 BasicLayer 模块。

class SwinTransformer(nn.Module):
    r""" Swin Transformer
        A PyTorch impl of : `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows`  -
          https://arxiv.org/pdf/2103.14030

    Args:
        patch_size (int | tuple(int)): Patch size. Default: 4
        in_chans (int): Number of input image channels. Default: 3
        num_classes (int): Number of classes for classification head. Default: 1000
        embed_dim (int): Patch embedding dimension. Default: 96
        depths (tuple(int)): Depth of each Swin Transformer layer.
        num_heads (tuple(int)): Number of attention heads in different layers.
        window_size (int): Window size. Default: 7
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4
        qkv_bias (bool): If True, add a learnable bias to query, key, value. Default: True
        drop_rate (float): Dropout rate. Default: 0
        attn_drop_rate (float): Attention dropout rate. Default: 0
        drop_path_rate (float): Stochastic depth rate. Default: 0.1
        norm_layer (nn.Module): Normalization layer. Default: nn.LayerNorm.
        patch_norm (bool): If True, add normalization after patch embedding. Default: True
        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False
    """

    def __init__(self, patch_size=4, in_chans=3, num_classes=1000,
                 embed_dim=96, depths=(2, 2, 6, 2), num_heads=(3, 6, 12, 24),
                 window_size=7, mlp_ratio=4., qkv_bias=True,
                 drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1,
                 norm_layer=nn.LayerNorm, patch_norm=True,
                 use_checkpoint=False, **kwargs):
        super().__init__()

        self.num_classes = num_classes
        self.num_layers = len(depths)
        self.embed_dim = embed_dim
        self.patch_norm = patch_norm
        # stage4输出特征矩阵的channels
        self.num_features = int(embed_dim * 2 ** (self.num_layers - 1))
        self.mlp_ratio = mlp_ratio

        # split image into non-overlapping patches
        self.patch_embed = PatchEmbed(
            patch_size=patch_size, in_c=in_chans, embed_dim=embed_dim,
            norm_layer=norm_layer if self.patch_norm else None)
        self.pos_drop = nn.Dropout(p=drop_rate)

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

        # build layers
        self.layers = nn.ModuleList()
        for i_layer in range(self.num_layers):
            # 注意这里构建的stage和论文图中有些差异
            # 这里的stage不包含该stage的patch_merging层,包含的是下个stage的
            layers = BasicLayer(dim=int(embed_dim * 2 ** i_layer),
                                depth=depths[i_layer],
                                num_heads=num_heads[i_layer],
                                window_size=window_size,
                                mlp_ratio=self.mlp_ratio,
                                qkv_bias=qkv_bias,
                                drop=drop_rate,
                                attn_drop=attn_drop_rate,
                                drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])],
                                norm_layer=norm_layer,
                                downsample=PatchMerging if (i_layer < self.num_layers - 1) else None,
                                use_checkpoint=use_checkpoint)
            self.layers.append(layers)

        self.norm = norm_layer(self.num_features)
        self.avgpool = nn.AdaptiveAvgPool1d(1)
        self.head = nn.Linear(self.num_features, num_classes) if num_classes > 0 else nn.Identity()

        self.apply(self._init_weights)

    def _init_weights(self, m):
        if isinstance(m, nn.Linear):
            nn.init.trunc_normal_(m.weight, std=.02)
            if isinstance(m, nn.Linear) and m.bias is not None:
                nn.init.constant_(m.bias, 0)
        elif isinstance(m, nn.LayerNorm):
            nn.init.constant_(m.bias, 0)
            nn.init.constant_(m.weight, 1.0)

    def forward(self, x):
        # x: [B, L, C]
        x, H, W = self.patch_embed(x)
        x = self.pos_drop(x)

        for layer in self.layers:
            x, H, W = layer(x, H, W)

        x = self.norm(x)  # [B, L, C]
        x = self.avgpool(x.transpose(1, 2))  # [B, C, 1]
        x = torch.flatten(x, 1)
        x = self.head(x)
        return x

辅助函数drop_path_f :用于实现随机深度路径(Stochastic Depth)以及一些用于处理窗口的辅助函数。

def drop_path_f(x, drop_prob: float = 0., training: bool = False):
    """Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

    This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
    the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
    See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
    changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
    'survival rate' as the argument.

    """
    if drop_prob == 0. or not training:
        return x
    keep_prob = 1 - drop_prob
    shape = (x.shape[0],) + (1,) * (x.ndim - 1)  # work with diff dim tensors, not just 2D ConvNets
    random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
    random_tensor.floor_()  # binarize
    output = x.div(keep_prob) * random_tensor
    return output

三、训练与测试

3.1 模型训练

我们训练的模型是在通用的预训练模型swin_base_patch4_window7_224.pth上再次训练的,通过模型训练微调,能给得到一个效果更好的花卉检测模型。

首先,设置模型训练的关键参数,如检测目标类别数目(可以按照自己的数据集和检测种类进行设置)、批量大小、训练周期、输入数据的维度等参数。

    parser = argparse.ArgumentParser()
    parser.add_argument('--num_classes', type=int, default=5)
    parser.add_argument('--epochs', type=int, default=100)
    parser.add_argument('--batch-size', type=int, default=16)
    parser.add_argument('--lr', type=float, default=0.0001)

    # 数据集所在根目录
    # http://download.tensorflow.org/example_images/flower_photos.tgz
    parser.add_argument('--data-path', type=str,
                        default="flower_photos")

    # 预训练权重路径,如果不想载入就设置为空字符
    parser.add_argument('--weights', type=str, default='./swin_base_patch4_window7_224.pth',
                        help='initial weights path')
    # 是否冻结权重
    parser.add_argument('--freeze-layers', type=bool, default=False)
    parser.add_argument('--device', default='cuda:0', help='device id (i.e. 0 or 0,1 or cpu)')

然后通过下面代码,设置模型训练设备和文件夹路径。接着对数据进行预处理并创建数据集和数据加载器。并根据命令行参数配置模型并加载预训练权重,可选择性地冻结部分模型参数。最后,使用AdamW优化器进行训练,并在每个epoch结束时保存模型权重。整个训练过程可以记录损失、准确率等指标,并将其写入TensorBoard。

def main(args):
    device = torch.device(args.device if torch.cuda.is_available() else "cpu")

    if os.path.exists("./weights") is False:
        os.makedirs("./weights")

    tb_writer = SummaryWriter()

    train_images_path, train_images_label, val_images_path, val_images_label = read_split_data(args.data_path)

    img_size = 224
    data_transform = {
        "train": transforms.Compose([transforms.RandomResizedCrop(img_size),
                                     transforms.RandomHorizontalFlip(),
                                     transforms.ToTensor(),
                                     transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),
        "val": transforms.Compose([transforms.Resize(int(img_size * 1.143)),
                                   transforms.CenterCrop(img_size),
                                   transforms.ToTensor(),
                                   transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])}

    # 实例化训练数据集
    train_dataset = MyDataSet(images_path=train_images_path,
                              images_class=train_images_label,
                              transform=data_transform["train"])

    # 实例化验证数据集
    val_dataset = MyDataSet(images_path=val_images_path,
                            images_class=val_images_label,
                            transform=data_transform["val"])

    batch_size = args.batch_size
    nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8])  # number of workers
    print('Using {} dataloader workers every process'.format(nw))
    train_loader = torch.utils.data.DataLoader(train_dataset,
                                               batch_size=batch_size,
                                               shuffle=True,
                                               pin_memory=True,
                                               num_workers=nw,
                                               collate_fn=train_dataset.collate_fn)

    val_loader = torch.utils.data.DataLoader(val_dataset,
                                             batch_size=batch_size,
                                             shuffle=False,
                                             pin_memory=True,
                                             num_workers=nw,
                                             collate_fn=val_dataset.collate_fn)

    model = create_model(num_classes=args.num_classes).to(device)

    if args.weights != "":
        assert os.path.exists(args.weights), "weights file: '{}' not exist.".format(args.weights)
        weights_dict = torch.load(args.weights, map_location=device)["model"]
        # 删除有关分类类别的权重
        for k in list(weights_dict.keys()):
            if "head" in k:
                del weights_dict[k]
        print(model.load_state_dict(weights_dict, strict=False))

    if args.freeze_layers:
        for name, para in model.named_parameters():
            # 除head外,其他权重全部冻结
            if "head" not in name:
                para.requires_grad_(False)
            else:
                print("training {}".format(name))

    pg = [p for p in model.parameters() if p.requires_grad]
    optimizer = optim.AdamW(pg, lr=args.lr, weight_decay=5E-2)

    for epoch in range(args.epochs):
        # train
        train_loss, train_acc = train_one_epoch(model=model,
                                                optimizer=optimizer,
                                                data_loader=train_loader,
                                                device=device,
                                                epoch=epoch)

        # validate
        val_loss, val_acc = evaluate(model=model,
                                     data_loader=val_loader,
                                     device=device,
                                     epoch=epoch)

        train_acc_list.append(train_acc)
        train_loss_list.append(train_loss)

        val_acc_list.append(val_acc)
        val_loss_list.append(val_loss)


        tags = ["train_loss", "train_acc", "val_loss", "val_acc", "learning_rate"]
        tb_writer.add_scalar(tags[0], train_loss, epoch)
        tb_writer.add_scalar(tags[1], train_acc, epoch)
        tb_writer.add_scalar(tags[2], val_loss, epoch)
        tb_writer.add_scalar(tags[3], val_acc, epoch)
        tb_writer.add_scalar(tags[4], optimizer.param_groups[0]["lr"], epoch)

        torch.save(model.state_dict(), "./weights/model-{}.pth".format(epoch))

整个训练过程可以记录损失、准确率等指标
在这里插入图片描述

3.2 模型测试

可以分别使用predict.py对单张花卉图片和predict-batch.py批量进行检测。

# predict.py
def main(img_path):
    import os
    os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE'

    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

    img_size = 224
    data_transform = transforms.Compose(
        [transforms.Resize(int(img_size * 1.143)),
         transforms.CenterCrop(img_size),
         transforms.ToTensor(),
         transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])

    # load image
    # img_path = "./tulip.jpg"
    assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path)
    img = Image.open(img_path)
    plt.imshow(img)
    # [N, C, H, W]
    img = data_transform(img)
    # expand batch dimension
    img = torch.unsqueeze(img, dim=0)

    # read class_indict
    json_path = './class_indices.json'
    assert os.path.exists(json_path), "file: '{}' dose not exist.".format(json_path)

    json_file = open(json_path, "r")
    class_indict = json.load(json_file)

    # create model
    model = create_model(num_classes=5).to(device)
    # load model weights
    model_weight_path = "./weights/model-86.pth"
    model.load_state_dict(torch.load(model_weight_path, map_location=device))
    model.eval()
    with torch.no_grad():
        # predict class
        output = torch.squeeze(model(img.to(device))).cpu()
        predict = torch.softmax(output, dim=0)
        predict_cla = torch.argmax(predict).numpy()

    # print_res = "class: {}   prob: {:.3}".format(class_indict[str(predict_cla)],
    #                                              predict[predict_cla].numpy())
    # plt.title(print_res)
    for i in range(len(predict)):
        print("class: {:10}   prob: {:.3}".format(class_indict[str(i)],
                                                  predict[i].numpy()))
    # plt.show()
    res = class_indict[str(list(predict.numpy()).index(max(predict.numpy())))]
    num= "%.2f" % (max(predict.numpy()) * 100) + "%"
    print(res,num)
    return res,max(predict.numpy())
    # print(class_indict[str(list(predict.numpy()).index(max(predict.numpy())))])
def main():
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

    img_size = 224
    data_transform = transforms.Compose(
        [transforms.Resize(int(img_size * 1.143)),
         transforms.CenterCrop(img_size),
         transforms.ToTensor(),
         transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])

    # read class_indict
    json_path = './class_indices.json'
    assert os.path.exists(json_path), "file: '{}' dose not exist.".format(json_path)

    json_file = open(json_path, "r")
    class_indict = json.load(json_file)

    # create model
    model = create_model(num_classes=5).to(device)
    # load model weights
    model_weight_path = "./weights/model-86.pth"
    model.load_state_dict(torch.load(model_weight_path, map_location=device))
    model.eval()


    # load image
    data_root = os.path.abspath(os.path.join(os.getcwd(), "../"))  # get data root path
    all_dir = os.path.join(data_root, "data_set")  # flower data set path
    # img_path_list = ["../tulip.jpg", "../rose.jpg"]
    img_list = []
    test_dir = os.path.join(all_dir, "jpg")  # test
    test_datasets = datasets.ImageFolder(test_dir, transform=data_transform)
    for img_path, idx in test_datasets.imgs:
        assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path)
        # img_path = "./tulip.jpg"
        assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path)
        img = Image.open(img_path)
        plt.imshow(img)
        # [N, C, H, W]
        img = data_transform(img)
        # expand batch dimension
        img = torch.unsqueeze(img, dim=0)


        with torch.no_grad():
            # predict class
            output = torch.squeeze(model(img.to(device))).cpu()
            predict = torch.softmax(output, dim=0)

            predict_cla = torch.argmax(predict).numpy()

        print_res = "image: {}  class: {}   prob: {:.3}".format(img_path, class_indict[str(predict_cla)],
                                                     predict[predict_cla].numpy())
        print(print_res)

测试结果:

在这里插入图片描述

四、PyQt界面实现

当整个项目构建完成后,使用PyQt5编写可视化界面,可以支持花卉图像的检测。运行主界面.py,然后点击文件夹图片传入待检测的花卉图像即可。经过花卉识别系统识别后,会输出相应的类别和置信度。
在这里插入图片描述

参考资料

  1. 论文:https://arxiv.org/pdf/2103.14030.pdf
  2. 代码:https://github.com/microsoft/Swin-Transformer
  3. timm:https://hub.fastgit.org/rwightman/pytorch-image-models/blob/master/timm/models/swin_transformer.py
  4. Swin_Transformer网络模型详解资料:详解Swin_Transformer (SwinT)

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:/a/544284.html

如若内容造成侵权/违法违规/事实不符,请联系我们进行投诉反馈qq邮箱809451989@qq.com,一经查实,立即删除!

相关文章

架构师系列-搜索引擎ElasticSearch(八)- 集群管理故障恢复

故障转移 集群的master节点会监控集群中的节点状态&#xff0c;如果发现有节点宕机&#xff0c;会立即将宕机节点的分片数据迁移到其它节点&#xff0c;确保数据安全&#xff0c;这个叫做故障转移。 下图中node1是主节点&#xff0c;其他两个节点是从节点 节点故障 此时node1…

【uniapp】vscode安装插件、ts校验、允许json文件注释

1、vscode安装的插件&#xff1a; uni-create-viewuni-hlperuniapp小程序扩展 2、ts校验 安装插件&#xff1a; pnpm i -D types/wechat-miniprogram uni-helper/uni-app-types配置tsconfig.json {"extends": "vue/tsconfig/tsconfig.json","compi…

论文笔记:The Expressive Power of Transformers with Chain of Thought

ICLR 2024 reviewer 评分 6888【但是chair 很不喜欢】 1 intro 之前的研究表明&#xff0c;即使是具有理想参数的标准Transformer&#xff0c;也无法完美解决许多大规模的顺序推理问题&#xff0c;如模拟有限状态机、判断图中的节点是否相连&#xff0c;或解决矩阵等式问题 这…

IOS 短信拦截插件

在使⽤iOS设备的时候, 我们经常会收到1069、1065开头的垃圾短信, 如果开了iMessage会更严重, 各种乱七⼋糟的垃圾信息会时不时地收到。 从iOS11开始, ⼿机可以⽀持恶短信拦截插件了. 我们可以通过该插件添加⼀些规则通过滤这些不需要的信息. ⼀. 使⽤xcode新建⼀个项⽬ 【1】…

MongoDB 初识

介绍 MongoDB是一种开源的文档型数据库管理系统&#xff0c;它使用类似于JSON的BSON格式&#xff08;Binary JSON&#xff09;来存储数据。与传统关系型数据库不同&#xff0c;MongoDB不使用表和行的结构&#xff0c;而是采用集合&#xff08;Collection&#xff09;(Mysql表)和…

LabVIEW直流稳定电源自动化校准系统

LabVIEW直流稳定电源自动化校准系统 直流稳定电源正向着智能化、高精度、多通道、宽量程的方向发展。基于LabVIEW开发环境&#xff0c;设计并实现了一种直流稳定电源自动化校准系统&#xff0c;以提升校准过程的整体效能&#xff0c;实现自动化设备替代人工进行电源校准工作。…

【DNS】

文章目录 DNS域名解析系统&#xff08;Domain Name System&#xff09;DNS系统需要解决的问题DNS域名解析系统&#xff08;Domain Name System&#xff09;问题1&#xff1a;DNS名字空间(The DNS Name Space&#xff09;DNS名字空间(The DNS Name Space)DNS名字空间(The DNS Na…

oracle 19c 主备 补丁升级19.22

补丁升级流程 备库升级 备库备份$ORALCE_HOME du -sh $ORACLE_HOME ​​​​​​​ 备份目录将dbhome_1压缩 cd $ORACLE_HOME cd .. Ls tar -cvzf db_home.tar.gz db_home_1 /opt/oracle/product/19c ​​​​​​​​​​​​​​ 关闭监听关闭数据库查看sq…

基于表面势的增强型p-GaN HEMT器件模型

来源&#xff1a;电子学报 22年 摘要 为了满足功率电路及系统设计对p-GaN HEMT&#xff08;High Electron Mobility Transistor&#xff09;器件模型的需求&#xff0c;本文建立了一套基于表面势计算方法的增强型p-GaN HEMT器件SPICE&#xff08;Simulation Program with Int…

【opencv】示例-travelsalesman.cpp 使用模拟退火算法求解旅行商问题

// 载入 OpenCV 的核心头文件 #include <opencv2/core.hpp> // 载入 OpenCV 的图像处理头文件 #include <opencv2/imgproc.hpp> // 载入 OpenCV 的高层GUI(图形用户界面)头文件 #include <opencv2/highgui.hpp> // 载入 OpenCV 的机器学习模块头文件 #includ…

数据库:SQL分类之DQL详解

1.DQL语法 select 字段列表 from 表名列表 where 条件列表 group by 分组字段列表 having 分组后条件列表 order by 排序字段列表 limit 分页参数 基本查询 条件查询&#xff08;where&#xff09; 聚合函数&#xff08;count、max、min、avg、sum &#xff09; 分组查询&…

Linux网络基础 (二) ——(IP、MAC、端口号、TCPUDP协议、网络字节序)

文章目录 IP 地址基本概念源IP地址 & 目的IP地址 MAC 地址基本概念源MAC地址 & 目的MAC地址 端口号基本概念源端口号 & 目的端口号 TCP & UDP 协议基本概念TCP 与 UDP 的抉择 网络字节序大端、小端字节序 &#x1f396; 博主的CSDN主页&#xff1a;Ryan.Alask…

OLTP 与 OLAP 系统说明对比和大数据经典架构 Lambda 和 Kappa 说明对比——解读大数据架构(五)

文章目录 前言OLTP 和 OLAPSMP 和 MPPlambda 架构Kappa 架构 前言 本文我们将研究不同类型的大数据架构设计&#xff0c;将讨论 OLTP 和 OLAP 的系统设计&#xff0c;以及有效处理数据的策略包括 SMP 和 MPP 等概念。然后我们将了解经典的 Lambda 架构和 Kappa 架构。 OLTP …

杰发科技AC7840——CAN通信简介(5)_可变波特率设置

0. 简介 设置可变波特率时候&#xff0c;遇到2个坑&#xff0c;在此记录下来 使用该函数即可 can_time_segment_t bitrate2 s_canBitrate[CAN_BITRATE_250K]; CAN_DRV_SetBitrate(instance, &bitrate2); 1. 波特率指针注意不要空 查看设置波特率的接口&#xff0c;发现…

Pytest精通指南(09)利用Fixture给函数设置别名

文章目录 前言测试用例默认显示传递一个参数传递多个参数 利用Fixture修改测试函数名称传递一个参数传递多个参数 验证ids和params长度不一致修改Fixture函数名称 前言 在 pytest 中&#xff0c;pytest.fixture 装饰器用于定义可以在多个测试函数中重用的设置和清理代码。 name…

C/C++基础----内存相关

malloc分配内存 用法 参数为要开辟内存的大小&#xff08;字节为单位&#xff09;返回值为void*,所以要强转一下语法&#xff1a;malloc()动态开辟20个字节的内存&#xff0c;代码&#xff1a;#include <iostream>using namespace std;int main() {int *a (int *) mal…

安全加速SCDN带的态势感知能为网站安全带来哪些帮助

随着安全加速SCDN被越来越多的用户使用&#xff0c;很多用户都不知道安全加速SCDN的态势感知是用于做什么的&#xff0c;德迅云安全今天就带大家来了解下什么是态势感知&#xff0c;态势感知顾名思义就是对未发生的事件进行预知&#xff0c;并提前进行防范措施的布置&#xff0…

内网渗透-Earthworm的简单使用(内网穿透工具)

Earthworm的简单介绍&#xff08;一&#xff09; 文章目录 EarthWorm下载地址1. 普通网络 1.1 跳板机存在公网IP 1.1.1 网络环境1.1.2 使用方法1.1.3 流量走向 1.2 跳板机不存在公网IP&#xff0c;可出网 1.2.1 网络环境1.2.2 使用方法1.2.3 流量走向 2. 二级网络 2.1 一级跳…

系统架构最佳实践 -- 金融企业的资损问题介绍

什么是资损 资损通常来讲是指支付场景下的资金损失&#xff0c;这里可以从两个维度看 用户角度&#xff1a;多扣用户款导致用户资金损失&#xff0c;此问题一般需要通过客服等渠道反馈&#xff0c;可以把多的钱退给用户&#xff0c;但是很大程度上损失了用户体验&#xff1b; …

ESP32 S3音频开发

1. 音频硬件框架 Codec&#xff1a;音频编解码芯片&#xff0c;一种低功耗单声道音频编解码器&#xff0c;包含单通道 ADC、单通道 DAC、低噪声前置放大器、耳机驱动器、数字音效、模拟混音和增益功能。它通过 I2S 和 I2C 总线与 ESP32-S3-WROOM-1 模组连接&#xff0c;以提供独…