def weight_init(m):
# 使用isinstance来判断m属于什么类型
  if isinstance(m, nn.Conv2d):
    n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
    m.weight.data.normal_(0, math.sqrt(2. / n))
  elif isinstance(m, nn.BatchNorm2d):
# m中的weight，bias其实都是Variable，为了能学习参数以及后向传播
    m.weight.data.fill_(1)
    m.bias.data.zero_()

model = torchvision.models.resnet18(pretrained=True)
for param in model.parameters():
  param.requires_grad = False
# 替换最后的全连接层， 改为训练100类
# 新构造的模块的参数默认requires_grad为True
model.fc = nn.Linear(512, 100)

# 只优化最后的分类层
optimizer = optim.SGD(model.fc.parameters(), lr=1e-2, momentum=0.9)

ignored_params = list(map(id, model.fc.parameters()))
base_params = filter(lambda p: id(p) not in ignored_params,
           model.parameters())

optimizer = torch.optim.SGD([
      {'params': base_params},
      {'params': model.fc.parameters(), 'lr': 1e-3}
      ], lr=1e-2, momentum=0.9)