YOLOv5改进 | 2023卷积篇 | AKConv轻量级架构下的高效检测（既轻量又提点）

?

?

?

import torch.nn as nn
import torch
from einops import rearrange
import math

from models.common import Conv


class AKConv(nn.Module):
    def __init__(self, inc, outc, num_param, stride=1, bias=None):
        super(AKConv, self).__init__()
        self.num_param = num_param
        self.stride = stride
        self.conv = nn.Sequential(nn.Conv2d(inc, outc, kernel_size=(num_param, 1), stride=(num_param, 1), bias=bias),
                                  nn.BatchNorm2d(outc),
                                  nn.SiLU())  # the conv adds the BN and SiLU to compare original Conv in YOLOv5.
        self.p_conv = nn.Conv2d(inc, 2 * num_param, kernel_size=3, padding=1, stride=stride)
        nn.init.constant_(self.p_conv.weight, 0)
        self.p_conv.register_full_backward_hook(self._set_lr)

    @staticmethod
    def _set_lr(module, grad_input, grad_output):
        grad_input = (grad_input[i] * 0.1 for i in range(len(grad_input)))
        grad_output = (grad_output[i] * 0.1 for i in range(len(grad_output)))

    def forward(self, x):
        # N is num_param.
        offset = self.p_conv(x)
        dtype = offset.data.type()
        N = offset.size(1) // 2
        # (b, 2N, h, w)
        p = self._get_p(offset, dtype)

        # (b, h, w, 2N)
        p = p.contiguous().permute(0, 2, 3, 1)
        q_lt = p.detach().floor()
        q_rb = q_lt + 1

        q_lt = torch.cat([torch.clamp(q_lt[..., :N], 0, x.size(2) - 1), torch.clamp(q_lt[..., N:], 0, x.size(3) - 1)],
                         dim=-1).long()
        q_rb = torch.cat([torch.clamp(q_rb[..., :N], 0, x.size(2) - 1), torch.clamp(q_rb[..., N:], 0, x.size(3) - 1)],
                         dim=-1).long()
        q_lb = torch.cat([q_lt[..., :N], q_rb[..., N:]], dim=-1)
        q_rt = torch.cat([q_rb[..., :N], q_lt[..., N:]], dim=-1)

        # clip p
        p = torch.cat([torch.clamp(p[..., :N], 0, x.size(2) - 1), torch.clamp(p[..., N:], 0, x.size(3) - 1)], dim=-1)

        # bilinear kernel (b, h, w, N)
        g_lt = (1 + (q_lt[..., :N].type_as(p) - p[..., :N])) * (1 + (q_lt[..., N:].type_as(p) - p[..., N:]))
        g_rb = (1 - (q_rb[..., :N].type_as(p) - p[..., :N])) * (1 - (q_rb[..., N:].type_as(p) - p[..., N:]))
        g_lb = (1 + (q_lb[..., :N].type_as(p) - p[..., :N])) * (1 - (q_lb[..., N:].type_as(p) - p[..., N:]))
        g_rt = (1 - (q_rt[..., :N].type_as(p) - p[..., :N])) * (1 + (q_rt[..., N:].type_as(p) - p[..., N:]))

        # resampling the features based on the modified coordinates.
        x_q_lt = self._get_x_q(x, q_lt, N)
        x_q_rb = self._get_x_q(x, q_rb, N)
        x_q_lb = self._get_x_q(x, q_lb, N)
        x_q_rt = self._get_x_q(x, q_rt, N)

        # bilinear
        x_offset = g_lt.unsqueeze(dim=1) * x_q_lt + \
                   g_rb.unsqueeze(dim=1) * x_q_rb + \
                   g_lb.unsqueeze(dim=1) * x_q_lb + \
                   g_rt.unsqueeze(dim=1) * x_q_rt

        x_offset = self._reshape_x_offset(x_offset, self.num_param)
        out = self.conv(x_offset)

        return out

    # generating the inital sampled shapes for the AKConv with different sizes.
    def _get_p_n(self, N, dtype):
        base_int = round(math.sqrt(self.num_param))
        row_number = self.num_param // base_int
        mod_number = self.num_param % base_int
        p_n_x, p_n_y = torch.meshgrid(
            torch.arange(0, row_number),
            torch.arange(0, base_int), indexing='xy')
        p_n_x = torch.flatten(p_n_x)
        p_n_y = torch.flatten(p_n_y)
        if mod_number > 0:
            mod_p_n_x, mod_p_n_y = torch.meshgrid(
                torch.arange(row_number, row_number + 1),
                torch.arange(0, mod_number),indexing='xy')

            mod_p_n_x = torch.flatten(mod_p_n_x)
            mod_p_n_y = torch.flatten(mod_p_n_y)
            p_n_x, p_n_y = torch.cat((p_n_x, mod_p_n_x)), torch.cat((p_n_y, mod_p_n_y))
        p_n = torch.cat([p_n_x, p_n_y], 0)
        p_n = p_n.view(1, 2 * N, 1, 1).type(dtype)
        return p_n

    # no zero-padding
    def _get_p_0(self, h, w, N, dtype):
        p_0_x, p_0_y = torch.meshgrid(
            torch.arange(0, h * self.stride, self.stride),
            torch.arange(0, w * self.stride, self.stride),indexing='xy')

        p_0_x = torch.flatten(p_0_x).view(1, 1, h, w).repeat(1, N, 1, 1)
        p_0_y = torch.flatten(p_0_y).view(1, 1, h, w).repeat(1, N, 1, 1)
        p_0 = torch.cat([p_0_x, p_0_y], 1).type(dtype)

        return p_0

    def _get_p(self, offset, dtype):
        N, h, w = offset.size(1) // 2, offset.size(2), offset.size(3)

        # (1, 2N, 1, 1)
        p_n = self._get_p_n(N, dtype)
        # (1, 2N, h, w)
        p_0 = self._get_p_0(h, w, N, dtype)
        p = p_0 + p_n + offset
        return p

    def _get_x_q(self, x, q, N):
        b, h, w, _ = q.size()
        padded_w = x.size(3)
        c = x.size(1)
        # (b, c, h*w)
        x = x.contiguous().view(b, c, -1)

        # (b, h, w, N)
        index = q[..., :N] * padded_w + q[..., N:]  # offset_x*w + offset_y
        # (b, c, h*w*N)

        index = index.contiguous().unsqueeze(dim=1).expand(-1, c, -1, -1, -1).contiguous().view(b, c, -1)

        # 根据实际情况调整
        index = index.clamp(min=0, max=x.shape[-1] - 1)

        x_offset = x.gather(dim=-1, index=index).contiguous().view(b, c, h, w, N)

        return x_offset

    #  Stacking resampled features in the row direction.
    @staticmethod
    def _reshape_x_offset(x_offset, num_param):
        b, c, h, w, n = x_offset.size()
        # using Conv3d
        # x_offset = x_offset.permute(0,1,4,2,3), then Conv3d(c,c_out, kernel_size =(num_param,1,1),stride=(num_param,1,1),bias= False)
        # using 1 × 1 Conv
        # x_offset = x_offset.permute(0,1,4,2,3), then, x_offset.view(b,c×num_param,h,w)  finally, Conv2d(c×num_param,c_out, kernel_size =1,stride=1,bias= False)
        # using the column conv as follow， then, Conv2d(inc, outc, kernel_size=(num_param, 1), stride=(num_param, 1), bias=bias)

        x_offset = rearrange(x_offset, 'b c h w n -> b c (h n) w')
        return x_offset

class Bottleneck_AKConv(nn.Module):
    # Standard bottleneck
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = AKConv(c_, c2, 3, 1)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))


class C3_AKConv(nn.Module):
    # CSP Bottleneck with 3 convolutions
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 * c_, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.Sequential(*(Bottleneck_AKConv(c_, c_, shortcut, g, e=1.0) for _ in range(n)))

    def forward(self, x):
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))

?4.1.2 修改二

# YOLOv5 🚀 by Ultralytics, AGPL-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

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, AKConv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, AKConv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, AKConv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, AKConv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, AKConv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, AKConv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3_AKConv, [256, False]],  # 17 (P3/8-small)

   [-1, 1, AKConv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3_AKConv, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, AKConv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3_AKConv, [1024, False]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]