yolov7的网络结构代码详解

yolov7的主干网络是其核心创新，主要是增加了E-ELAN模块和aux的辅助检测头，目前来看新的网络结构还是有点效果的，主要的代码详解如下，对应yolo.py。

import argparse
import logging
import sys
from copy import deepcopy

sys.path.append('./')  # to run '$ python *.py' files in subdirectories
logger = logging.getLogger(__name__)
import torch
from models.common import *
from models.experimental import *
from utils.autoanchor import check_anchor_order
from utils.general import make_divisible, check_file, set_logging
from utils.torch_utils import time_synchronized, fuse_conv_and_bn, model_info, scale_img, initialize_weights, \
    select_device, copy_attr
from utils.loss import SigmoidBin

try:
    import thop  # for FLOPS computation
except ImportError:
    thop = None


class Detect(nn.Module):
    stride = None  # strides computed during build
    export = False  # onnx export
    end2end = False
    include_nms = False 

    def __init__(self, nc=80, anchors=(), ch=()):  # detection layer
        super(Detect, self).__init__()
        self.nc = nc  # number of classes
        self.no = nc + 5  # number of outputs per anchor
        self.nl = len(anchors)  # number of detection layers
        self.na = len(anchors[0]) // 2  # number of anchors
        self.grid = [torch.zeros(1)] * self.nl  # init grid
        a = torch.tensor(anchors).float().view(self.nl, -1, 2)
        self.register_buffer('anchors', a)  # shape(nl,na,2)
        self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))  # shape(nl,1,na,1,1,2)
        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv

    def forward(self, x):
        # x = x.copy()  # for profiling
        z = []  # inference output
        self.training |= self.export
        for i in range(self.nl):
            x[i] = self.m[i](x[i])  # conv
            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()

            if not self.training:  # inference
                if self.grid[i].shape[2:4] != x[i].shape[2:4]:
                    self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
                y = x[i].sigmoid()
                if not torch.onnx.is_in_onnx_export():
                    y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
                    y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
                else:
                    xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
                    wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i].data  # wh
                    y = torch.cat((xy, wh, y[..., 4:]), -1)
                z.append(y.view(bs, -1, self.no))

        if self.training:
            out = x
        elif self.end2end:
            out = torch.cat(z, 1)
        elif self.include_nms:
            z = self.convert(z)
            out = (z, )
        else:
            out = (torch.cat(z, 1), x)

        return out

    @staticmethod
    def _make_grid(nx=20, ny=20):
        yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
        return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()

    def convert(self, z):
        z = torch.cat(z, 1)
        box = z[:, :, :4]
        conf = z[:, :, 4:5]
        score = z[:, :, 5:]
        score *= conf
        convert_matrix = torch.tensor([[1, 0, 1, 0], [0, 1, 0, 1], [-0.5, 0, 0.5, 0], [0, -0.5, 0, 0.5]],
                                           dtype=torch.float32,
                                           device=z.device)
        box @= convert_matrix                          
        return (box, score)


class IDetect(nn.Module):
    stride = None  # strides computed during build
    export = False  # onnx export
    end2end = False
    include_nms = False 

    def __init__(self, nc=80, anchors=(), ch=()):  # detection layer
        super(IDetect, self).__init__()
        self.nc = nc  # number of classes
        self.no = nc + 5  # number of outputs per anchor
        self.nl = len(anchors)  # number of detection layers=3 
        self.na = len(anchors[0]) // 2  # number of anchors 6//2=3
        self.grid = [torch.zeros(1)] * self.nl  # init grid [tensor([0.]), tensor([0.]), tensor([0.])]
        a = torch.tensor(anchors).float().view(self.nl, -1, 2) # (3, 6)->(3, 3, 2) = [[[10,13], [16,30], [33,23]], [[30,61], [62,45], [59,119]], [[116,90], [156,198], [373,326]]]
        self.register_buffer('anchors', a)  # shape(nl,na,2)=(3,3,2)
        self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))  # shape(nl,1,na,1,1,2)=(3,1,3,1,1,2)
        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
        
        self.ia = nn.ModuleList(ImplicitA(x) for x in ch)
        self.im = nn.ModuleList(ImplicitM(self.no * self.na) for _ in ch)

    def forward(self, x):
        # x = x.copy()  # for profiling
        z = []  # inference output
        self.training |= self.export
        for i in range(self.nl):
            x[i] = self.m[i](self.ia[i](x[i]))  # conv
            x[i] = self.im[i](x[i])
            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()

            if not self.training:  # inference
                if self.grid[i].shape[2:4] != x[i].shape[2:4]:
                    self.grid[i] = self._make_grid(nx, ny).to(x[i].device)

                y = x[i].sigmoid()
                y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
                y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
                z.append(y.view(bs, -1, self.no))

        return x if self.training else (torch.cat(z, 1), x)
    
    def fuseforward(self, x):
        # x = x.copy()  # for profiling
        z = []  # inference output
        self.training |= self.export
        for i in range(self.nl):
            x[i] = self.m[i](x[i])  # conv
            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()

            if not self.training:  # inference
                if self.grid[i].shape[2:4] != x[i].shape[2:4]:
                    self.grid[i] = self._make_grid(nx, ny).to(x[i].device)

                y = x[i].sigmoid()
                if not torch.onnx.is_in_onnx_export():
                    y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
                    y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
                else:
                    xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
                    wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i].data  # wh
                    y = torch.cat((xy, wh, y[..., 4:]), -1)
                z.append(y.view(bs, -1, self.no))

        if self.training:
            out = x
        elif self.end2end:
            out = torch.cat(z, 1)
        elif self.include_nms:
            z = self.convert(z)
            out = (z, )
        else:
            out = (torch.cat(z, 1), x)

        return out
    
    def fuse(self):
        print("IDetect.fuse")
        # fuse ImplicitA and Convolution
        for i in range(len(self.m)):
            c1,c2,_,_ = self.m[i].weight.shape
            c1_,c2_, _,_ = self.ia[i].implicit.shape
            self.m[i].bias