pytorch基本流程

数据集的预处理模块

1. tensor格式转换
   主要是讲numpy格式转换为tensor格式
   x_train, y_train, x_valid, y_valid = map( torch.tensor, (x_train, y_train, x_valid, y_valid) )

2. torch.nn.finction模块与torch.nn.Module模块

   torch.nn.functional中有很多功能，后续会常用的。那什么时候使用nn.Module，什么时候使用nn.functional呢？一般情况下，如果模型有可学习的参数，最好用nn.Module，其他情况nn.functional相对更简单一些

#例如一些损失函数，激活层等使用torch.Function
import torch.nn.Function as F
loss_fun = F.cross_entropy

from torch import nn
#在建立一些网络模块时直接使用torch.Module，且只需要写前向传播，在使用module模块时已经提前初始化好变量。
class Minist_NN(nn.Module):
	def __init__(self):
		super().__init__()	
		self.hidden1 = nn.Linear(784, 128)
	        self.hidden2 = nn.Linear(128, 256)
	        self.out  = nn.Linear(256, 10)	
	 def forward(self, x):
	        x = F.relu(self.hidden1(x))
	        x = F.relu(self.hidden2(x))
	        x = self.out(x)
	        return x
#实例化后可进行打印
net = Mnist_NN()
print(net)
--------------------------------------------------
Mnist_NN(
  (hidden1): Linear(in_features=784, out_features=128, bias=True)
  (hidden2): Linear(in_features=128, out_features=256, bias=True)
  (out): Linear(in_features=256, out_features=10, bias=True)
)
				

TensorDataset和DataLoader模块简化数据集处理以及batchsize的设置。

from torch.utils.data import TensorDataset
from torch.utils.data import DataLoader

train_ds = TensorDataset(x_train, y_train)
train_dl = DataLoader(train_ds, batch_size=bs, shuffle=True)

valid_ds = TensorDataset(x_valid, y_valid)
valid_dl = DataLoader(valid_ds, batch_size=bs * 2)

def get_data(train_ds, valid_ds, bs):
    return (
        DataLoader(train_ds, batch_size=bs, shuffle=True),
        DataLoader(valid_ds, batch_size=bs * 2),
    )

进行模型的组装

#相关辅助函数
from torch import optim
def get_model():	
	model = Mnist_NN()
	#优化器函数中要传入所优化的参数
    return model, optim.SGD(model.parameters(), lr=0.001)

def loss_batch(model, loss_func, xb, yb, opt=None):
    loss = loss_func(model(xb), yb)
    if opt is not None:
	    loss.backward()
	    opt.step()
	    opt.zero_grad(）	
    return loss.item(), len(xb)

import numpy as np
def fit(steps, model, loss_func, opt, train_dl, valid_dl):
    for step in range(steps):
        #训练的时候加上model.train在训练过程中进行normalize相关操作
        model.train()
        for xb, yb in train_dl:
            loss_batch(model, loss_func, xb, yb, opt)
                    model.eval()
        with torch.no_grad():
            losses, nums = zip(
                *[loss_batch(model, loss_func, xb, yb) for xb, yb in valid_dl]
            )
        val_loss = np.sum(np.multiply(losses, nums)) / np.sum(nums)
        print('当前step:'+str(step), '验证集损失：'+str(val_loss))

结果输出

train_dl, valid_dl = get_data(train_ds, valid_ds, bs)
model, opt = get_model()
fit(20, model, loss_func, opt, train_dl, valid_dl)
-----------------------------------------------------------------
当前step:0 验证集损失：2.281271044921875
当前step:1 验证集损失：2.2509783180236815
当前step:2 验证集损失：2.203812783432007
当前step:3 验证集损失：2.1252328746795652
当前step:4 验证集损失：1.9954518688201903
当前step:5 验证集损失：1.7956134561538697
当前step:6 验证集损失：1.5333285322189332
当前step:7 验证集损失：1.261820195388794
当前step:8 验证集损失：1.0405126466751098
当前step:9 验证集损失：0.880806344127655
当前step:10 验证集损失：0.7669796929359436
当前step:11 验证集损失：0.6844435347557067
当前step:12 验证集损失：0.6225414663314819
当前step:13 验证集损失：0.5751254560470581
当前step:14 验证集损失：0.5374272463321685
当前step:15 验证集损失：0.5071435091495514
当前step:16 验证集损失：0.48235899238586427
当前step:17 验证集损失：0.46154185042381285
当前step:18 验证集损失：0.44456041851043704
当前step:19 验证集损失：0.42940848422050476