集成YOLOX的backbone（CSPDarknet和Pafpn）到yolov5（v7.0）框架中

# YOLOv5 ���� by Ultralytics, GPL-3.0 license """ Common modules """ import ast import contextlib import json import math import platform import warnings import zipfile from collections import OrderedDict, namedtuple from copy import copy from pathlib import Path from urllib.parse import urlparse import cv2 import numpy as np import pandas as pd import requests import torch import torch.nn as nn import torch.nn.functional as F from IPython.display import display from PIL import Image from torch.cuda import amp from utils import TryExcept from utils.dataloaders import exif_transpose, letterbox from utils.general import (LOGGER, ROOT, Profile, check_requirements, check_suffix, check_version, colorstr, increment_path, is_notebook, make_divisible, non_max_suppression, scale_boxes, xywh2xyxy, xyxy2xywh, yaml_load) from utils.plots import Annotator, colors, save_one_box from utils.torch_utils import copy_attr, smart_inference_mode def autopad(k, p=None, d=1): # kernel, padding, dilation # Pad to 'same' shape outputs if d > 1: k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k] # actual kernel-size if p is None: p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad return p class Conv(nn.Module): # Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation) default_act = nn.SiLU() # default activation def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True): super().__init__() self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False) self.bn = nn.BatchNorm2d(c2) self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity() def forward(self, x): return self.act(self.bn(self.conv(x))) def forward_fuse(self, x): return self.act(self.conv(x)) class DWConv(Conv): # Depth-wise convolution def __init__(self, c1, c2, k=1, s=1, d=1, act=True): # ch_in, ch_out, kernel, stride, dilation, activation super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act) class DWConvTranspose2d(nn.ConvTranspose2d): # Depth-wise transpose convolution def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0): # ch_in, ch_out, kernel, stride, padding, padding_out super().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2)) class TransformerLayer(nn.Module): # Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance) def __init__(self, c, num_heads): super().__init__() self.q = nn.Linear(c, c, bias=False) self.k = nn.Linear(c, c, bias=False) self.v = nn.Linear(c, c, bias=False) self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads) self.fc1 = nn.Linear(c, c, bias=False) self.fc2 = nn.Linear(c, c, bias=False) def forward(self, x): x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x x = self.fc2(self.fc1(x)) + x return x class TransformerBlock(nn.Module): # Vision Transformer https://arxiv.org/abs/2010.11929 def __init__(self, c1, c2, num_heads, num_layers): super().__init__() self.conv = None if c1 != c2: self.conv = Conv(c1, c2) self.linear = nn.Linear(c2, c2) # learnable position embedding self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers))) self.c2 = c2 def forward(self, x): if self.conv is not None: x = self.conv(x) b, _, w, h = x.shape p = x.flatten(2).permute(2, 0, 1) return self.tr(p + self.linear(p)).permute(1, 2, 0).reshape(b, self.c2, w, h) class Bottleneck(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 = Conv(c_, c2, 3, 1, g=g) 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 BottleneckCSP(nn.Module): # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks 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 = nn.Conv2d(c1, c_, 1, 1, bias=False) self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False) self.cv4 = Conv(2 * c_, c2, 1, 1) self.bn = nn.BatchNorm2d(2 * c_) # applied to cat(cv2, cv3) self.act = nn.SiLU() self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) def forward(self, x): y1 = self.cv3(self.m(self.cv1(x))) y2 = self.cv2(x) return self.cv4(self.act(self.bn(torch.cat((y1, y2), 1)))) class CrossConv(nn.Module): # Cross Convolution Downsample def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False): # ch_in, ch_out, kernel, stride, groups, expansion, shortcut super().__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, (1, k), (1, s)) self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g) 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(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(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)) class C3x(C3): # C3 module with cross-convolutions def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): super().__init__(c1, c2, n, shortcut, g, e) c_ = int(c2 * e) self.m = nn.Sequential(*(CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n))) class C3TR(C3): # C3 module with TransformerBlock() def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): super().__init__(c1, c2, n, shortcut, g, e) c_ = int(c2 * e) self.m = TransformerBlock(c_, c_, 4, n) class C3SPP(C3): # C3 module with SPP() def __init__(self, c1, c2, k=(5, 9, 13), n=1, shortcut=True, g=1, e=0.5): super().__init__(c1, c2, n, shortcut, g, e) c_ = int(c2 * e) self.m = SPP(c_, c_, k) class C3Ghost(C3): # C3 module with GhostBottleneck() def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): super().__init__(c1, c2, n, shortcut, g, e) c_ = int(c2 * e) # hidden channels self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n))) class SPP(nn.Module): # Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729 def __init__(self, c1, c2, k=(5, 9, 13)): super().__init__() c_ = c1 // 2 # hidden channels self.cv1 = Conv(c1, c_, 1, 1) self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1) self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k]) def forward(self, x): x = self.cv1(x) with warnings.catch_warnings(): warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1)) class SPPF(nn.Module):