pytorch加载预训练模型与自己模型不匹配的解决方案

model = ResNet18(1)
model_dict1 = torch.load('resnet18.pth')
model_dict2 = model.state_dict()
model_list1 = list(model_dict1.keys())
model_list2 = list(model_dict2.keys())
len1 = len(model_list1)
len2 = len(model_list2)
minlen = min(len1, len2)
for n in range(minlen):
    if model_dict1[model_list1[n]].shape != model_dict2[model_list2[n]].shape:
        err = 1

model = ResNet18(1)
model_dict1 = torch.load('resnet18.pth')
model_dict2 = model.state_dict()
model_list1 = list(model_dict1.keys())
model_list2 = list(model_dict2.keys())
len1 = len(model_list1)
len2 = len(model_list2)
minlen = min(len1, len2)
for n in range(minlen):
    if model_dict1[model_list1[n]].shape != model_dict2[model_list2[n]].shape:
        continue
    model_dict1[model_list1[n]] = model_dict2[model_list2[n]]
model.load_state_dict(model_dict2)

model_dict1 = torch.load('yolov5.pth')
model_dict2 = model.state_dict()
model_list1 = list(model_dict1.keys())
model_list2 = list(model_dict2.keys())
len1 = len(model_list1)
len2 = len(model_list2)
m, n = 0, 0
while True:
    if m >= len1 or n >= len2:
        break
    layername1, layername2 = model_list1[m], model_list2[n]
    w1, w2 = model_dict1[layername1], model_dict2[layername2]
    if w1.shape != w2.shape:
        continue
    model_dict2[layername2] = model_dict1[layername1]
    m += 1
    n += 1
model.load_state_dict(model_dict2)

#打算取VGG19的第二个全连接层的输出，那么就需要构建一个类，这个类要包含VGG的全部卷积层，
#以及到第二个全连接层的全部网络还有他们对应的参数
class Classification_att(nn.Module):
    def __init__(self, rgb_range):
        super(Classification_att, self).__init__()
        self.vgg19 =models.vgg19(pretrained=True)
        vgg = models.vgg19(pretrained=True).features
        conv_modules = [m for m in vgg]
        self.vgg_conv = nn.Sequential(*conv_modules[:37])
        classfi = models.vgg19(pretrained=True).classifier
        classif_modules = [n for n in classfi]
        self.vgg_class = nn.Sequential(*classif_modules[:4])
        vgg_mean = (0.485, 0.456, 0.406)
        vgg_std = (0.229 * rgb_range, 0.224 * rgb_range, 0.225 * rgb_range)
        self.sub_mean = common.MeanShift(rgb_range, vgg_mean, vgg_std)
        for p in self.vgg_conv.parameters():
            p.requires_grad = False
        for p in self.vgg_class.parameters():
            p.requires_grad = False
        self.classifi = nn.Sequential(
            nn.Linear(4096, 1024),
            nn.ReLU(True),
            nn.Linear(1024, 256),
            nn.ReLU(True),
            nn.Linear(256, 64),
        )
 
    def forward(self, x):
        x = F.interpolate(x, size=[224, 224], scale_factor=None, mode='bilinear', 
        align_corners=False)
        x = self.sub_mean(x)
        x = self.vgg_conv(x)  
        x = self.vgg_class(x)  #执行这部报错，说张量不匹配

x = self.features(x)
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.classifier(x)
#自己的代码没有torch.flatten(x, 1)这步

x = torch.flatten(x, 1)