SparseRCNN 模型，用于目标检测任务
import logging
import math
from typing import Listimport numpy as np
import torch
import torch.distributed as dist
import torch.nn.functional as F
from torch import nn
from detectron2.modeling import META_ARCH_REGISTRY, build_backbone, detector_postprocess
from detectron2.modeling.roi_heads import build_roi_headsfrom detectron2.structures import Boxes, ImageList, Instances
from detectron2.utils.logger import log_first_n
from fvcore.nn import giou_loss, smooth_l1_lossfrom .loss import SetCriterion, HungarianMatcher
from .head import DynamicHead
from .util.box_ops import box_cxcywh_to_xyxy, box_xyxy_to_cxcywh
from .util.misc import (NestedTensor, nested_tensor_from_tensor_list,accuracy, get_world_size, interpolate,is_dist_avail_and_initialized)__all__ = ["SparseRCNN"]import numpy as np
import torch
from torch import nn
from torch.nn import initclass SEAttention(nn.Module):def __init__(self, channel=512, reduction=16):super().__init__()self.ave_pool = nn.AdaptiveAvgPool2d(1)self.fc = nn.Sequential(nn.Linear(channel, channel // reduction, bias=False),nn.ReLU(inplace=True),nn.Linear(channel // reduction, channel, bias=False),nn.Sigmoid())def init_weights(self):for m in self.modules():if isinstance(m, nn.Conv2d):init.kaiming_normal_(m.weight, mode='fan_out')if m.bias is not None:init.constant_(m.bias, 0)elif isinstance(m, nn.BatchNorm2d):init.constant_(m.weight, 1)init.constant_(m.weight, 0)elif isinstance(m, nn.Linear):init.normal_(m.weight, std=0.001)if m.bias is not None:init.constant_(m.bias, 0)def forward(self, x):b, c, _, _ = x.size()y = self.ave_pool(x).view(b, c)y = self.fc(y).view(b, c, 1, 1)return x
