问题：

drn文件

import pdb
#pdb是 ThePythonDebugger 的缩写，为Python标准库的一个模块。pdb模块规定了一个Python程序交互式源代码调试器，支持在设置断点（包括条件断点），也支持源码级单步调试，支持栈帧监视，支持源代码列出，支持任意栈帧上下文的随机Python代码估值。它还支持事后调试（post-mortem debugging），并且能在程序控制下被调用。import torch 
import torch.nn as nn #class torch.nn.Module与class torch.nn.Parameter() https://pytorch-cn.readthedocs.io/zh/latest/package_references/torch-nn/
import math
import torch.utils.model_zoo as model_zoo
# 在给定URL上加载Torch序列化对象。https://pytorch-cn.readthedocs.io/zh/latest/package_references/model_zoo/
torch.backends.cudnn.benchmark = True
# 与GPU 相关的 flag，提速https://mp.weixin.qq.com/s?src=11&timestamp=1606096921&ver=2723&signature=jfMPYOAtEseWFpFchs1vKCGBrrOtigSR6fyj1lQz0MK4BeT3sFRxvQXi2Y5*EGXiS*v-V1n39jNzzWYtt93OzrK8c*TxDQBc0OLbVOQtXCJ8zsWA*l3LmTbBE5skkCVj&new=1
BatchNorm = nn.BatchNorm2d
#对小批量(mini-batch)3d数据组成的4d输入进行批标准化(Batch Normalization)操作https://pytorch-cn.readthedocs.io/zh/latest/package_references/torch-nn/#class-torchnnbatchnorm2dnum_features-eps1e-05-momentum01-affinetruesource# __all__ = ['DRN', 'drn26', 'drn42', 'drn58']webroot = 'https://tigress-web.princeton.edu/~fy/drn/models/'model_urls = {'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth','drn-c-26': webroot + 'drn_c_26-ddedf421.pth','drn-c-42': webroot + 'drn_c_42-9d336e8c.pth','drn-c-58': webroot + 'drn_c_58-0a53a92c.pth','drn-d-22': webroot + 'drn_d_22-4bd2f8ea.pth','drn-d-38': webroot + 'drn_d_38-eebb45f0.pth','drn-d-54': webroot + 'drn_d_54-0e0534ff.pth','drn-d-105': webroot + 'drn_d_105-12b40979.pth'
}def conv3x3(in_planes, out_planes, stride=1, padding=1, dilation=1):return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,padding=padding, bias=False, dilation=dilation)#二维卷积层, 输入的尺度是(N, C_in,H,W)，输出尺度（N,C_out,H_out,W_out）的计算方式：class BasicBlock(nn.Module):expansion = 1def __init__(self, inplanes, planes, stride=1, downsample=None,dilation=(1, 1), residual=True):super(BasicBlock, self).__init__()self.conv1 = conv3x3(inplanes, planes, stride,padding=dilation[0], dilation=dilation[0])self.bn1 = BatchNorm(planes)self.relu = nn.ReLU(inplace=True)self.conv2 = conv3x3(planes, planes,padding=dilation[1], dilation=dilation[1])self.bn2 = BatchNorm(planes)self.downsample = downsampleself.stride = strideself.residual = residualdef forward(self, x)://前向传播：将上一层的输出作为下一层的输入，并计算下一层的输出，一直到运算到输出层为止。residual = xout = self.conv1(x)out = self.bn1(out)out = self.relu(out)out = self.conv2(out)out = self.bn2(out)if self.downsample is not None:residual = self.downsample(x)if self.residual:out += residualout = self.relu(out)return outclass Bottleneck(nn.Module):expansion = 4def __init__(self, inplanes, planes, stride=1, downsample=None,dilation=(1, 1), residual=True):super(Bottleneck, self).__init__()self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)self.bn1 = BatchNorm(planes)self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,padding=dilation[1], bias=False,dilation=dilation[1])self.bn2 = BatchNorm(planes)self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)self.bn3 = BatchNorm(planes * 4)self.relu = nn.ReLU(inplace=True)self.downsample = downsampleself.stride = stridedef forward(self, x):residual = xout = self.conv1(x)out = self.bn1(out)out = self.relu(out)out = self.conv2(out)out = self.bn2(out)out = self.relu(out)out = self.conv3(out)out = self.bn3(out)if self.downsample is not None:residual = self.downsample(x)out += residualout = self.relu(out)return outclass DRN(nn.Module):def __init__(self, block, layers, num_classes=1000,channels=(16, 32, 64, 128, 256, 512, 512, 512),out_map=False, out_middle=False, pool_size=28, arch='D'):super(DRN, self).__init__()self.inplanes = channels[0]self.out_map = out_mapself.out_dim = channels[-1]self.out_middle = out_middleself.arch = archif arch == 'C':self.conv1 = nn.Conv2d(3, channels[0], kernel_size=7, stride=1,padding=3, bias=False)self.bn1 = BatchNorm(channels[0])self.relu = nn.ReLU(inplace=True)self.layer1 = self._make_layer(BasicBlock, channels[0], layers[0], stride=1)self.layer2 = self._make_layer(BasicBlock, channels[1], layers[1], stride=2)elif arch == 'D':self.layer0 = nn.Sequential(nn.Conv2d(3, channels[0], kernel_size=7, stride=1, padding=3,bias=False),BatchNorm(channels[0]),nn.ReLU(inplace=True))self.layer1 = self._make_conv_layers(channels[0], layers[0], stride=1)self.layer2 = self._make_conv_layers(channels[1], layers[1], stride=2)self.layer3 = self._make_layer(block, channels[2], layers[2], stride=2)self.layer4 = self._make_layer(block, channels[3], layers[3], stride=2)self.layer5 = self._make_layer(block, channels[4], layers[4],dilation=2, new_level=False)self.layer6 = None if layers[5] == 0 else \self._make_layer(block, channels[5], layers[5], dilation=4,new_level=False)if arch == 'C':self.layer7 = None if layers[6] == 0 else \self._make_layer(BasicBlock, channels[6], layers[6], dilation=2,new_level=False, residual=False)self.layer8 = None if layers[7] == 0 else \self._make_layer(BasicBlock, channels[7], layers[7], dilation=1,new_level=False, residual=False)elif arch == 'D':self.layer7 = None if layers[6] == 0 else \self._make_conv_layers(channels[6], layers[6], dilation=2)self.layer8 = None if layers[7] == 0 else \self._make_conv_layers(channels[7], layers[7], dilation=1)if num_classes > 0:self.avgpool = nn.AvgPool2d(pool_size)self.fc = nn.Conv2d(self.out_dim, num_classes, kernel_size=1,stride=1, padding=0, bias=True)for m in self.modules():if isinstance(m, nn.Conv2d):n = m.kernel_size[0] * m.kernel_size[1] * m.out_channelsm.weight.data.normal_(0, math.sqrt(2. / n))elif isinstance(m, BatchNorm):m.weight.data.fill_(1)m.bias.data.zero_()def _make_layer(self, block, planes, blocks, stride=1, dilation=1,new_level=True, residual=True):assert dilation == 1 or dilation % 2 == 0downsample = Noneif stride != 1 or self.inplanes != planes * block.expansion:downsample = nn.Sequential(nn.Conv2d(self.inplanes, planes * block.expansion,kernel_size=1, stride=stride, bias=False),BatchNorm(planes * block.expansion),)layers = list()layers.append(block(self.inplanes, planes, stride, downsample,dilation=(1, 1) if dilation == 1 else (dilation // 2 if new_level else dilation, dilation),residual=residual))self.inplanes = planes * block.expansionfor i in range(1, blocks):layers.append(block(self.inplanes, planes, residual=residual,dilation=(dilation, dilation)))return nn.Sequential(*layers)def _make_conv_layers(self, channels, convs, stride=1, dilation=1):modules = []for i in range(convs):modules.extend([nn.Conv2d(self.inplanes, channels, kernel_size=3,stride=stride if i == 0 else 1,padding=dilation, bias=False, dilation=dilation),BatchNorm(channels),nn.ReLU(inplace=True)])self.inplanes = channelsreturn nn.Sequential(*modules)def forward(self, x):y = list()if self.arch == 'C':x = self.conv1(x)x = self.bn1(x)x = self.relu(x)elif self.arch == 'D':x = self.layer0(x)x = self.layer1(x)y.append(x)x = self.layer2(x)y.append(x)x = self.layer3(x)y.append(x)x = self.layer4(x)y.append(x)x = self.layer5(x)y.append(x)if self.layer6 is not None:x = self.layer6(x)y.append(x)if self.layer7 is not None:x = self.layer7(x)y.append(x)if self.layer8 is not None:x = self.layer8(x)y.append(x)if self.out_map:x = self.fc(x)else:x = self.avgpool(x)x = self.fc(x)x = x.view(x.size(0), -1)if self.out_middle:return x, yelse:return xclass DRN_A(nn.Module):def __init__(self, block, layers, num_classes=1000):self.inplanes = 64super(DRN_A, self).__init__()self.out_dim = 512 * block.expansionself.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,bias=False)self.bn1 = nn.BatchNorm2d(64)self.relu = nn.ReLU(inplace=True)self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)self.layer1 = self._make_layer(block, 64, layers[0])self.layer2 = self._make_layer(block, 128, layers[1], stride=2)self.layer3 = self._make_layer(block, 256, layers[2], stride=1,dilation=2)self.layer4 = self._make_layer(block, 512, layers[3], stride=1,dilation=4)self.avgpool = nn.AvgPool2d(28, stride=1)self.fc = nn.Linear(512 * block.expansion, num_classes)for m in self.modules():if isinstance(m, nn.Conv2d):n = m.kernel_size[0] * m.kernel_size[1] * m.out_channelsm.weight.data.normal_(0, math.sqrt(2. / n))elif isinstance(m, BatchNorm):m.weight.data.fill_(1)m.bias.data.zero_()# for m in self.modules():#     if isinstance(m, nn.Conv2d):#         nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')#     elif isinstance(m, nn.BatchNorm2d):#         nn.init.constant_(m.weight, 1)#         nn.init.constant_(m.bias, 0)def _make_layer(self, block, planes, blocks, stride=1, dilation=1):downsample = Noneif stride != 1 or self.inplanes != planes * block.expansion:downsample = nn.Sequential(nn.Conv2d(self.inplanes, planes * block.expansion,kernel_size=1, stride=stride, bias=False),nn.BatchNorm2d(planes * block.expansion),)layers = []layers.append(block(self.inplanes, planes, stride, downsample))self.inplanes = planes * block.expansionfor i in range(1, blocks):layers.append(block(self.inplanes, planes,dilation=(dilation, dilation)))return nn.Sequential(*layers)def forward(self, x):x = self.conv1(x)x = self.bn1(x)x = self.relu(x)x = self.maxpool(x)x = self.layer1(x)x = self.layer2(x)x = self.layer3(x)x = self.layer4(x)x = self.avgpool(x)x = x.view(x.size(0), -1)x = self.fc(x)return xdef drn_a_50(pretrained=False, **kwargs):model = DRN_A(Bottleneck, [3, 4, 6, 3], **kwargs)if pretrained:model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))return modeldef drn_c_26(pretrained=False, **kwargs):model = DRN(BasicBlock, [1, 1, 2, 2, 2, 2, 1, 1], arch='C', **kwargs)if pretrained:model.load_state_dict(model_zoo.load_url(model_urls['drn-c-26']))return modeldef drn_c_42(pretrained=False, **kwargs):model = DRN(BasicBlock, [1, 1, 3, 4, 6, 3, 1, 1], arch='C', **kwargs)if pretrained:model.load_state_dict(model_zoo.load_url(model_urls['drn-c-42']))return modeldef drn_c_58(pretrained=False, **kwargs):model = DRN(Bottleneck, [1, 1, 3, 4, 6, 3, 1, 1], arch='C', **kwargs)if pretrained:model.load_state_dict(model_zoo.load_url(model_urls['drn-c-58']))return modeldef drn_d_22(pretrained=False, **kwargs):model = DRN(BasicBlock, [1, 1, 2, 2, 2, 2, 1, 1], arch='D', **kwargs)if pretrained:model.load_state_dict(model_zoo.load_url(model_urls['drn-d-22']))return modeldef drn_d_24(pretrained=False, **kwargs):model = DRN(BasicBlock, [1, 1, 2, 2, 2, 2, 2, 2], arch='D', **kwargs)if pretrained:model.load_state_dict(model_zoo.load_url(model_urls['drn-d-24']))return modeldef drn_d_38(pretrained=False, **kwargs):model = DRN(BasicBlock, [1, 1, 3, 4, 6, 3, 1, 1], arch='D', **kwargs)if pretrained:model.load_state_dict(model_zoo.load_url(model_urls['drn-d-38']))return modeldef drn_d_40(pretrained=False, **kwargs):model = DRN(BasicBlock, [1, 1, 3, 4, 6, 3, 2, 2], arch='D', **kwargs)if pretrained:model.load_state_dict(model_zoo.load_url(model_urls['drn-d-40']))return modeldef drn_d_54(pretrained=False, **kwargs):model = DRN(Bottleneck, [1, 1, 3, 4, 6, 3, 1, 1], arch='D', **kwargs)if pretrained:model.load_state_dict(model_zoo.load_url(model_urls['drn-d-54']))return modeldef drn_d_56(pretrained=False, **kwargs):model = DRN(Bottleneck, [1, 1, 3, 4, 6, 3, 2, 2], arch='D', **kwargs)if pretrained:model.load_state_dict(model_zoo.load_url(model_urls['drn-d-56']))return modeldef drn_d_105(pretrained=False, **kwargs):model = DRN(Bottleneck, [1, 1, 3, 4, 23, 3, 1, 1], arch='D', **kwargs)if pretrained:model.load_state_dict(model_zoo.load_url(model_urls['drn-d-105']))return modeldef drn_d_107(pretrained=False, **kwargs):model = DRN(Bottleneck, [1, 1, 3, 4, 23, 3, 2, 2], arch='D', **kwargs)if pretrained:model.load_state_dict(model_zoo.load_url(model_urls['drn-d-107']))return model

drn_seg

import math
import torch
import torch.nn as nn
from networks.drn import drn_c_26def fill_up_weights(up):w = up.weight.dataf = math.ceil(w.size(2) / 2)c = (2 * f - 1 - f % 2) / (2. * f)for i in range(w.size(2)):for j in range(w.size(3)):w[0, 0, i, j] = \(1 - math.fabs(i / f - c)) * (1 - math.fabs(j / f - c))for c in range(1, w.size(0)):w[c, 0, :, :] = w[0, 0, :, :]class DRNSeg(nn.Module):def __init__(self, classes, pretrained_drn=False,pretrained_model=None, use_torch_up=False):super(DRNSeg, self).__init__()model = drn_c_26(pretrained=pretrained_drn)self.base = nn.Sequential(*list(model.children())[:-2])if pretrained_model:self.load_pretrained(pretrained_model)self.seg = nn.Conv2d(model.out_dim, classes,kernel_size=1, bias=True)m = self.segn = m.kernel_size[0] * m.kernel_size[1] * m.out_channelsm.weight.data.normal_(0, math.sqrt(2. / n))m.bias.data.zero_()if use_torch_up:self.up = nn.UpsamplingBilinear2d(scale_factor=8)else:up = nn.ConvTranspose2d(classes, classes, 16, stride=8, padding=4,output_padding=0, groups=classes,bias=False)fill_up_weights(up)up.weight.requires_grad = Falseself.up = updef forward(self, x):x = self.base(x)x = self.seg(x)y = self.up(x)return ydef optim_parameters(self, memo=None):for param in self.base.parameters():yield paramfor param in self.seg.parameters():yield paramdef load_pretrained(self, pretrained_model):print("loading the pretrained drn model from %s" % pretrained_model)state_dict = torch.load(pretrained_model, map_location='cpu')if hasattr(state_dict, '_metadata'):del state_dict._metadata# filter out unnecessary keyspretrained_dict = state_dict['model']pretrained_dict = {k[5:]: v for k, v in pretrained_dict.items() if k.split('.')[0] == 'base'}# load the pretrained state dictself.base.load_state_dict(pretrained_dict)class DRNSub(nn.Module):def __init__(self, num_classes, pretrained_model=None, fix_base=False):super(DRNSub, self).__init__()drnseg = DRNSeg(2)if pretrained_model:print("loading the pretrained drn model from %s" % pretrained_model)state_dict = torch.load(pretrained_model, map_location='cpu')drnseg.load_state_dict(state_dict['model'])self.base = drnseg.baseif fix_base:for param in self.base.parameters():param.requires_grad = Falseself.avgpool = nn.AdaptiveAvgPool2d((1, 1))self.fc = nn.Linear(512, num_classes)def forward(self, x):x = self.base(x)x = self.avgpool(x)x = x.view(x.size(0), -1)x = self.fc(x)return x