forward 和 normal_train代码分析

forward 和 normal_train代码

2021SC@SDUSC

Forward

现定义好网络，实现前向传播
class Network(nn.Module):
def init(self):
super().init()
self.conv1 = nn.Conv2d(in_channels=1,out_channels=6,kernel_size=5)
self.conv2 = nn.Conv2d(in_channels=6,out_channels=12,kernel_size=5)

    self.fc1 = nn.Linear(in_features=12*4*4,out_features=120)
    self.fc2 =nn.Linear(in_features=120,out_features=60)
    self.out = nn.Linear(in_features=60,out_features=10)

输入层

def forward(self,t):
        t = t

隐藏cov层

 t = self.conv1(t)
        t = F.relu(t)
        t = F.max_pool2d(t,kernel_size=2,stride=2)

**

normal_train 代码分析

add_argument() 方法
ArgumentParser.add_argument(name or flags…[, action][, nargs][, const][, default][, type][, choices][, required][, help][, metavar][, dest])

创建对象

parser = argparse.ArgumentParser(description='Testing...') 

添加单个命令参数

parser.add_argument('test',type=int)

输入指定类型

parser.add_argument('test_1',type=float)

default 在没有命令输入时的默认值

parser.add_argument('-test_2','-i',type=float,default=2) 

使参数创建并生效

args = parser.parse_args()

实例代码如下：

parser.add_argument('--epochs', default=50, type=int, metavar='N',
                    help='number of total epochs to run')
parser.add_argument('--batch-size', default=4, type=int, metavar='N',
                    help='train batchsize')
parser.add_argument('--batch-size-u', default=24, type=int, metavar='N',
                    help='train batchsize')

parser.add_argument('--lrmain', '--learning-rate-bert', default=0.00001, type=float,
                    metavar='LR', help='initial learning rate for bert')
parser.add_argument('--lrlast', '--learning-rate-model', default=0.001, type=float,
                    metavar='LR', help='initial learning rate for models')