提示：文章写完后，目录可以自动生成，如何生成可参考右边的帮助文档
文章目录 YOLO v5加入注意力机制、swin-head、解耦头部（回归源码）一、YOLO v5 简介二、全局注意力机制的引入三、引入SwinTransformer_Layer层四、引入解耦头部层五、修改模型yaml文件六、运行代码1.train.py报错问题2.再次运行train.py3.自己数据集实验结果 总结YOLO v5加入注意力机制、swin-head、解耦头部（回归源码）
提示：这里可以添加本文要记录的大概内容：
在YOLO v5的backbone和head引入全局注意力机制（GAM attention）、检测头引入解耦头部、SwinTransformer_Layer层，部分commom.py代码参考地址为：
https://github.com/iloveai8086/YOLOC
提示：以下是本篇文章正文内容，下面案例可供参考
一、YOLO v5 简介YOLO v5由输入端、Backbone、Neck、Head四部分组成。YOLO v5输入端是对图像进行预处理操作,达到对输入图片进行数据增强的效果；Backbone采用了Conv复合卷积模块、C3模块以及SPPF模块组成，Neck部分主则采用 FPN+PAN的特征金字塔结构，增加多尺度的语义表达，从而增强不同尺度上的表达能力；Head部分采用三种损失函数分别计算位置、分类和置信度损失。
二、全局注意力机制的引入在YOLO v5 d的commom.py加入以下全局注意力机制的代码。
class GAM_Attention(nn.Module): # https://paperswithcode.com/paper/global-attention-mechanism-retain-information def __init__(self, c1, c2, group=True, rate=4): super(GAM_Attention, self).__init__() self.channel_attention = nn.Sequential( nn.Linear(c1, int(c1 / rate)), nn.ReLU(inplace=True), nn.Linear(int(c1 / rate), c1) ) self.spatial_attention = nn.Sequential( nn.Conv2d(c1, c1 // rate, kernel_size=7, padding=3, groups=rate) if group else nn.Conv2d(c1, int(c1 / rate), kernel_size=7, padding=3), nn.BatchNorm2d(int(c1 / rate)), nn.ReLU(inplace=True), nn.Conv2d(c1 // rate, c2, kernel_size=7, padding=3, groups=rate) if group else nn.Conv2d(int(c1 / rate), c2, kernel_size=7, padding=3), nn.BatchNorm2d(c2) ) def forward(self, x): b, c, h, w = x.shape x_permute = x.permute(0, 2, 3, 1).view(b, -1, c) x_att_permute = self.channel_attention(x_permute).view(b, h, w, c) x_channel_att = x_att_permute.permute(0, 3, 1, 2) # x_channel_att=channel_shuffle(x_channel_att,4) #last shuffle x = x * x_channel_att x_spatial_att = self.spatial_attention(x).sigmoid() x_spatial_att = channel_shuffle(x_spatial_att, 4) # last shuffle out = x * x_spatial_att # out=channel_shuffle(out,4) #last shuffle return out def channel_shuffle(x, groups=2): ##shuffle channel # RESHAPE----->transpose------->Flatten B, C, H, W = x.size() out = x.view(B, groups, C // groups, H, W).permute(0, 2, 1, 3, 4).contiguous() out = out.view(B, C, H, W) return out 三、引入SwinTransformer_Layer层在commom.py加入以下代码。代码较多
def window_reverse(windows, window_size: int, H: int, W: int): """ 将window还原成一个feature map Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size(M) H (int): Height of image W (int): Width of image Returns: x: (B, H, W, C) """ B = int(windows.shape[0] / (H * W / window_size / window_size)) # view: [B*num_windows, Mh, Mw, C] -> [B, H//Mh, W//Mw, Mh, Mw, C] x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1) # permute: [B, H//Mh, W//Mw, Mh, Mw, C] -> [B, H//Mh, Mh, W//Mw, Mw, C] # view: [B, H//Mh, Mh, W//Mw, Mw, C] -> [B, H, W, C] x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1) return x class PatchMerging(nn.Module): """ Patch Merging Layer Args: dim (int): Number of input channels. norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm """ def __init__(self, dim, norm_layer=nn.LayerNorm): super().__init__() self.dim = dim self.reduction = nn.Linear(4 * dim, 2 * dim, bias=False) self.norm = norm_layer(4 * dim) def forward(self, x, H, W): """ Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature. """ B, C, H, W = x.shape # print('------------------------PatchMErging input shape:',x.size()) # H=L**0.5 # W=H # assert L == H * W, "input feature has wrong size" # assert H==W , "input feature has wrong size" x = x.view(B, int(H), int(W), C) # padding pad_input = (H % 2 == 1) or (W % 2 == 1) if pad_input: x = F.pad(x, (0, 0, 0, W % 2, 0, H % 2)) x0 = x[:, 0::2, 0::2, :] # B H/2 W/2 C 左上 x1 = x[:, 1::2, 0::2, :] # B H/2 W/2 C 左下 x2 = x[:, 0::2, 1::2, :] # B H/2 W/2 C 右上 x3 = x[:, 1::2, 1::2, :] # B H/2 W/2 C 右下 x = torch.cat([x0, x1, x2, x3], -1) # B H/2 W/2 4*C x = x.view(B, -1, 4 * C) # B H/2*W/2 4*C x = self.norm(x) x = self.reduction(x) # B H/2*W/2 2*C # print('PatchMerging output shape:',x.size()) return x class Mlp(nn.Module): """ MLP as used in Vision Transformer, MLP-Mixer and related networks """ def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.): super().__init__() out_features = out_features or in_features hidden_features = hidden_features or in_features self.fc1 = nn.Linear(in_features, hidden_features) self.act = act_layer() self.drop1 = nn.Dropout(drop) self.fc2 = nn.Linear(hidden_features, out_features) self.drop2 = nn.Dropout(drop) def forward(self, x): x = self.fc1(x) x = self.act(x) x = self.drop1(x) x = self.fc2(x) x = self.drop2(x) return x class WindowAttention(nn.Module): """ 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., meta_network_hidden_features=256): 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_weight = nn.Parameter( torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads)) # [2*Mh-1 * 2*Mw-1, nH] # 获取窗口内每对token的相对位置索引 # 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]indexing="ij" # 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) # Init meta network for positional encodings self.meta_network: nn.Module = nn.Sequential( nn.Linear(in_features=2, out_features=meta_network_hidden_features, bias=True), nn.ReLU(inplace=True), nn.Linear(in_features=meta_network_hidden_features, out_features=num_heads, bias=True)) 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_weight, std=.02) self.softmax = nn.Softmax(dim=-1) # Init tau self.register_parameter("tau", nn.Parameter(torch.zeros(1, num_heads, 1, 1))) # Init pair-wise relative positions (log-spaced) indexes = torch.arange(self.window_size[0], device=self.tau.device) coordinates = torch.stack(torch.meshgrid([indexes, indexes]), dim=0) coordinates = torch.flatten(coordinates, start_dim=1) relative_coordinates = coordinates[:, :, None] - coordinates[:, None, :] relative_coordinates = relative_coordinates.permute(1, 2, 0).reshape(-1, 2).float() relative_coordinates_log = torch.sign(relative_coordinates) \ * torch.log(1. + relative_coordinates.abs()) self.register_buffer("relative_coordinates_log", relative_coordinates_log) def get_relative_positional_encodings(self): """ Method computes the relative positional encodings :return: Relative positional encodings [1, number of heads, window size ** 2, window size ** 2] """ relative_position_bias = self.meta_network(self.relative_coordinates_log) relative_position_bias = relative_position_bias.permute(1, 0) relative_position_bias = relative_position_bias.reshape(self.num_heads, self.window_size[0] * self.window_size[1], \ self.window_size[0] * self.window_size[1]) return relative_position_bias.unsqueeze(0) def forward(self, x, mask=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) attn = torch.einsum("bhqd, bhkd -> bhqk", q, k) \ / torch.maximum(torch.norm(q, dim=-1, keepdim=True) * torch.norm(k, dim=-1, keepdim=True).transpose(-2, -1), torch.tensor(1e-06, device=q.device, dtype=q.dtype)) # 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 # cosine -->dot?????? Scaled cosine attention：cosine(q,k)/tau 也许理解的不准确： 控制数值范围有利于训练稳定 （残差块的累加 导致深层难以稳定训练） # attn = (q @ k.transpose(-2, -1)) # q = torch.norm(q, p=2, dim=-1) # k = torch.norm(k, p=2, dim=-1) # attn /= q.unsqueeze(-1) # attn /= k.unsqueeze(-2) # attn=attention_map # print('attn shape:',attn.size()) # print('attn2 shape:',attention_map.size()) attn /= self.tau.clamp(min=0.01) # relative_position_bias_table.view: [Mh*Mw*Mh*Mw,nH] -> [Mh*Mw,Mh*Mw,nH] # relative_position_bias = self.relative_position_bias_weight[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] # print("net work new positional_enco:",self.__get_relative_positional_encodings().size()) # print('attn shape:',attn.size()) # attn = attn + relative_position_bias.unsqueeze(0) attn = attn + self.get_relative_positional_encodings() 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) ## float() x = torch.einsum("bhal, bhlv -> bhav", attn, v) # x = self.proj(x) # x = self.proj_drop(x) # print('out shape:',x.size()) return x 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, Global=False): 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" # patches_resolution = [img_size[0] // patch_size[0], img_size[1] // patch_size[1]] 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) # if Global else Global_WindowAttention( # dim, window_size=(self.window_size, self.window_size),input_resolution=() 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, out_features=dim, act_layer=act_layer, drop=drop) def forward(self, x, attn_mask): # H, W = self.H, self.W # print("org-input block shape:",x.size()) x = x.permute(0, 3, 2, 1).contiguous() # B,H,W,C B, H, W, C = x.shape # B, L, C = x.shape # assert L == H * W, "input feature has wrong size" shortcut = x # H,W=int(H), int(W) # 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 # if min(H, W) < self.window_size or H % self.window_size!=0: # Padding = True 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 = self.norm1(x) # pos-norm.1 # x = x.view(B, H * W, C) # FFN x = shortcut + self.drop_path(x) x = x + self.drop_path(self.norm2(self.mlp(x))) # pos-norm.2 x = x.permute(0, 3, 2, 1).contiguous() # print("swinblock ouput——shape：",x.size()) return x def window_partition(x, window_size: int): """ 将feature map按照window_size划分成一个个没有重叠的window Args: x: (B, H, W, C) window_size (int): window size(M) Returns: windows: (num_windows*B, window_size, window_size, C) """ B, H, W, C = x.shape x = x.view(B, H // window_size, window_size, W // window_size, window_size, C) # permute: [B, H//Mh, Mh, W//Mw, Mw, C] -> [B, H//Mh, W//Mh, Mw, Mw, C] # view: [B, H//Mh, W//Mw, Mh, Mw, C] -> [B*num_windows, Mh, Mw, C] windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C) return windows class SwinTransformer_Layer(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: 7 or 8 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, last_layer=False, window_size=7, mlp_ratio=4., qkv_bias=True, drop=0., attn_drop=0., drop_path=0., norm_layer=nn.LayerNorm, downsample=PatchMerging, use_checkpoint=False): super().__init__() self.dim = dim self.depth = depth self.last_layer = last_layer 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, Global=False) for i in range(depth)]) # patch merging layer if self.last_layer is False: # print('开始进行patchmergin------打印层深度：',depth) self.downsample = downsample(dim=dim, norm_layer=norm_layer) else: # print('最后1层默认没有Patchmerging：',depth) # self.norm = norm_layer(self.num_features) # self.avgpool = nn.AdaptiveAvgPool1d(1) self.downsample = None self.avgpool = nn.AdaptiveAvgPool1d(1) 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): # print('swinlayers input shape:',x.size()) B, C, H, W = x.size() # H=int(L**0.5) # W=H # assert L == H * W, "input feature has wrong size" 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 # if self.last_layer: # x=x.view(B,H,W,C) # x=x.transpose(1,3) # x = self.norm(x) # [B, L, C] # x = self.avgpool(x.transpose(1, 2)) # [B, C, 1] # x = x.view(B,-1,H,W) # x = window_reverse(x, self.window_size, H, W) # [B, H', W', C] # x = torch.flatten(x, 1) x = x.view(B, -1, H, W) # # print("Swin-Transform 层 ------------------------输出维度:",x.size()) return x class DropPath(nn.Module): """Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). """ def __init__(self, drop_prob=None): super(DropPath, self).__init__() self.drop_prob = drop_prob def forward(self, x): return drop_path_f(x, self.drop_prob, self.training) 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 四、引入解耦头部层引入解耦头部的方法，就不在讲述了，其他比我厉害的博主也都有些写引入解耦头部的方法，大家可以去网上查看别的博客。
五、修改模型yaml文件这里是我修改的模型yaml文件如下： 自己添加的注意力机制层数稍微多点。从下面可以看出在在head部分每一层的SwinTransformer_Layer都加了一层注意力机制。最后一层Detect部分采用Decoupled_Detect解耦头部。
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license # Parameters nc: 1 # number of classes depth_multiple: 0.33 # model depth multiple width_multiple: 0.50 # 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 # YOLOv5 v6.0 backbone backbone: # [from, number, module, args] [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 [-1, 3, C3, [128]], # 2 [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 [-1, 1, SwinTransformer_Layer, [128,2,8,True,8]], # 4 [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 [-1, 1, SwinTransformer_Layer, [256,2,8,True,8]], # 6 [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 [-1, 1, SwinTransformer_Layer, [512,2,8,True,4]], # 8 [-1, 1, GAM_Attention, [512,512]], # 9 [-1, 1, SPPF, [1024, 5]], # 10 ] head: [[-1, 1, Conv, [512, 1, 1]], # 11 [-1, 1, nn.Upsample, [None, 2, 'nearest']], # 12 [[-1, 6], 1, Concat, [1]], # 13 [-1, 3, C3, [512, False]], # 14 [-1, 1, Conv, [256, 1, 1]], # 15 [-1, 1, nn.Upsample, [None, 2, 'nearest']], # 16 [[-1, 4], 1, Concat, [1]], # 17 [-1, 3, C3, [256, False]], # 18 [-1, 1,GAM_Attention, [128,128]], # 19 [-1, 1, Conv, [512, 3, 2]], # 20 [[-1, 6, 13], 1, Concat, [1]], # 21 [-1, 3, C3, [512, False]], # 22 [-1, 1, SwinTransformer_Layer, [256,2,2,True,8]], # 23 [-1, 1,GAM_Attention, [256,256]], # 24 [-1, 1, Conv, [1024, 3, 2]], # 25 [[-1, 10], 1, Concat, [1]], # 26 [-1, 3, C3, [1024, False]], # 27 (P4/16-medium) [-1, 1, SwinTransformer_Layer, [512,2,2,True,4]], # 28 [-1, 1,GAM_Attention, [512,512]], # 29 [[19, 24, 29], 1,Decoupled_Detect, [nc, anchors]], # Detect(P3, P4, P5) ] 六、运行代码 1.train.py报错问题在修改后的YOLO v5中运行上述修改的yaml模型文件时候训练会报错，因为精度的问题，报错内容如下：RuntimeError: expected scalar type Half but found Float 在train.py的def parse_opt(known=False)中增加下面的最后一行代码： 添加上述代码还会继续报错，还是同样的问题，在对train.py文件进行继续修改，在下面两个部分添加half=not opt.swin_float这句代码修改后部分如下：
2.再次运行train.py再次运行代码，–data部分是我自己的数据集yam文件，–cfg部分是上述修改后的模型yaml文件，这里权重设置为空，训练为200次，批次大小为4。终端运行训练代码如下：
python train.py --data huo.yaml --cfg yolov5s_swin_head.yaml --weights ' ' --epoch 200 --batch-size 4 --swin_float 3.自己数据集实验结果第一次写这个，奈何自己才疏学浅，后期有新的想法会继续更新。还望大家积极批评指正。 commom.py部分代码参考： 链接: [link] (https://github.com/iloveai8086/YOLOC)
 1.本站遵循行业规范，任何转载的稿件都会明确标注作者和来源；2.本站的原创文章，会注明原创字样,如未注明都非原创，如有侵权请联系删除！；3.作者投稿可能会经我们编辑修改或补充；4.本站不提供任何储存功能只提供收集或者投稿人的网盘链接。 |
