RT-DETR优化改进：Backbone改进 | VanillaNet一种新视觉Backbone，极简且强大！华为诺亚2023

class VanillaNet(nn.Module):
    def __init__(self, in_chans=3, num_classes=1000, dims=[96, 192, 384, 768],
                 drop_rate=0, act_num=3, strides=[2, 2, 2, 1], deploy=False, ada_pool=None, **kwargs):
        super().__init__()
        self.deploy = deploy
        if self.deploy:
            self.stem = nn.Sequential(
                nn.Conv2d(in_chans, dims[0], kernel_size=4, stride=4),
                activation(dims[0], act_num)
            )
        else:
            self.stem1 = nn.Sequential(
                nn.Conv2d(in_chans, dims[0], kernel_size=4, stride=4),
                nn.BatchNorm2d(dims[0], eps=1e-6),
            )
            self.stem2 = nn.Sequential(
                nn.Conv2d(dims[0], dims[0], kernel_size=1, stride=1),
                nn.BatchNorm2d(dims[0], eps=1e-6),
                activation(dims[0], act_num)
            )

        self.act_learn = 1

        self.stages = nn.ModuleList()
        for i in range(len(strides)):
            if not ada_pool:
                stage = Block(dim=dims[i], dim_out=dims[i + 1], act_num=act_num, stride=strides[i], deploy=deploy)
            else:
                stage = Block(dim=dims[i], dim_out=dims[i + 1], act_num=act_num, stride=strides[i], deploy=deploy,
                              ada_pool=ada_pool[i])
            self.stages.append(stage)
        self.depth = len(strides)

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

    def _init_weights(self, m):
        if isinstance(m, (nn.Conv2d, nn.Linear)):
            weight_init.trunc_normal_(m.weight, std=.02)
            nn.init.constant_(m.bias, 0)

    def change_act(self, m):
        for i in range(self.depth):
            self.stages[i].act_learn = m
        self.act_learn = m

    def forward(self, x):
        input_size = x.size(2)
        scale = [4, 8, 16, 32]
        features = [None, None, None, None]
        if self.deploy:
            x = self.stem(x)
        else:
            x = self.stem1(x)
            x = torch.nn.functional.leaky_relu(x, self.act_learn)
            x = self.stem2(x)
        if input_size // x.size(2) in scale:
            features[scale.index(input_size // x.size(2))] = x
        for i in range(self.depth):
            x = self.stages[i](x)
            if input_size // x.size(2) in scale:
                features[scale.index(input_size // x.size(2))] = x
        return features

    def _fuse_bn_tensor(self, conv, bn):
        kernel = conv.weight
        bias = conv.bias
        running_mean = bn.running_mean
        running_var = bn.running_var
        gamma = bn.weight
        beta = bn.bias
        eps = bn.eps
        std = (running_var + eps).sqrt()
        t = (gamma / std).reshape(-1, 1, 1, 1)
        return kernel * t, beta + (bias - running_mean) * gamma / std

    def switch_to_deploy(self):
        if not self.deploy:
            self.stem2[2].switch_to_deploy()
            kernel, bias = self._fuse_bn_tensor(self.stem1[0], self.stem1[1])
            self.stem1[0].weight.data = kernel
            self.stem1[0].bias.data = bias
            kernel, bias = self._fuse_bn_tensor(self.stem2[0], self.stem2[1])
            self.stem1[0].weight.data = torch.einsum('oi,icjk->ocjk', kernel.squeeze(3).squeeze(2),
                                                     self.stem1[0].weight.data)
            self.stem1[0].bias.data = bias + (self.stem1[0].bias.data.view(1, -1, 1, 1) * kernel).sum(3).sum(2).sum(1)
            self.stem = torch.nn.Sequential(*[self.stem1[0], self.stem2[2]])
            self.__delattr__('stem1')
            self.__delattr__('stem2')

            for i in range(self.depth):
                self.stages[i].switch_to_deploy()

            self.deploy = True