Pytorch学习笔记——Batch Norm方法

1.自定义BatchNorm类

import time
import torch
from torch import nn,optim
import torch.nn.functional as F
import torchvision

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

def batch_norm(is_training,X,gamma,beta,moving_mean,moving_var,eps,momentum):
    if not is_training:
        X_hat = (X - moving_mean) / torch.sqrt(moving_var + eps)
    else:
        assert len(X.shape) in (2,4)
        if len(X.shape) == 2:
            mean = X.mean(dim=0)
            var = ((X-mean)**2).mean(dim=0)
        else:
            mean = X.mean(dim=0,keepdim=True).mean(dim=2,keepdim=True).mean(dim=3,keepdim=True)
            var = ((X-mean)**2).mean(dim=0,keepdim=True).mean(dim=2,keepdim=True).mean(dim=3,keepdim=True)
        X_hat = (X-mean) / torch.sqrt(var+eps)
        moving_mean = momentum * moving_mean + (1.0 - momentum) * mean
        moving_var = momentum * moving_var + (1.0 - momentum) *var
    Y = gamma * X_hat + beta
    return Y,moving_mean,moving_var

class BatchNorm(nn.Module):
    def __init__(self,num_features,num_dims):
        super(BatchNorm,self).__init__()
        if num_dims == 2:
            shape = (1,num_features)
        else:
            shape = (1,num_features,1,1)
        self.gamma = nn.Parameter(torch.ones(shape))
        self.beta = nn.Parameter(torch.zeros(shape))
        self.moving_mean = torch.zeros(shape)
        self.moving_var = torch.zeros(shape)

    def forward(self,X):
        if self.moving_mean.device != X.device:
            self.moving_mean = self.moving_mean.to(X.device)
            self.moving_var = self.moving_var.to(X.device)
        Y,self.moving_mean,self.moving_var = batch_norm(self.training,X,self.gamma,self.beta,self.moving_mean,self.moving_var,eps=1e-5,momentum=0.9)
        return Y

class FlattenLayer(nn.Module):
    def __init__(self):
        super(FlattenLayer,self).__init__()
    def forward(self,x):
        return x.view(x.shape[0],-1)

net = nn.Sequential(nn.Conv2d(1,6,5),
                    BatchNorm(6,num_dims=4),
                    nn.Sigmoid(),
                    nn.MaxPool2d(2,2),
                    nn.Conv2d(6,16,5),
                    BatchNorm(16,num_dims=4),
                    nn.Sigmoid(),
                    nn.MaxPool2d(2,2),
                    FlattenLayer(),
                    nn.Linear(16*4*4,120),
                    BatchNorm(120,num_dims=2),
                    nn.Sigmoid(),
                    nn.Linear(120,84),
                    BatchNorm(84,num_dims=2),
                    nn.Sigmoid(),
                    nn.Linear(84,10))

def evaluate_accuracy(data_iter,net,device=torch.device('cuda' if torch.cuda.is_available() else 'cpu')):
    acc_sum,n = 0.0,0
    with torch.no_grad():
        for X,y in data_iter:
            if isinstance(net,torch.nn.Module):
                net.eval()
                acc_sum += (net(X.to(device)).argmax(dim=1) == y.to(device)).float().sum().cpu().item()
                net.train()
            else:
                if('is_training' in net.__code__.co_varnames):
                    acc_sum += (net(X,is_training=False).argmax(dim=1) == y).float().sum().item()
                else:
                    acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()
            n += y.shape[0]
    return acc_sum/n

def load_data_fashion_mnist(batch_size,resize=None,root='~/Datasets/FashionMNIST'):
    trans = []
    if resize:
        trans.append(torchvision.transforms.Resize(size=resize))
    trans.append(torchvision.transforms.ToTensor())

    transform = torchvision.transforms.Compose(trans)
    mnist_train = torchvision.datasets.FashionMNIST(root=root,train=True,download=True,transform=transform)
    mnist_test = torchvision.datasets.FashionMNIST(root=root,train=False,download=True,transform=transform)

    train_iter = torch.utils.data.DataLoader(mnist_train,batch_size=batch_size,shuffle=True,num_workers=4)
    test_iter = torch.utils.data.DataLoader(mnist_test,batch_size=batch_size,shuffle=False,num_workers=4)

    return train_iter,test_iter

def train_ch5(net,train_iter,test_iter,batch_size,optimizer,device,num_epochs):
    net = net.to(device)
    print("training on ",device)
    loss = torch.nn.CrossEntropyLoss()
    batch_count = 0
    for epoch in range(num_epochs):
        train_l_sum,train_acc_sum,n,start = 0.0,0.0,0,time.time()
        for X,y in train_iter:
            X = X.to(device)
            y = y.to(device)
            y_hat = net(X)
            l = loss(y_hat,y)
            optimizer.zero_grad()
            l.backward()
            optimizer.step()
            train_l_sum += l.cpu().item()
            train_acc_sum += (y_hat.argmax(dim=1) == y).sum().cpu().item()
            n += y.shape[0]
            batch_count += 1
        test_acc = evaluate_accuracy(test_iter,net)
        print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f, time %.1f sec' %(epoch+1,train_l_sum/batch_count,train_acc_sum/n,test_acc,time.time()-start))

batch_size = 256
train_iter,test_iter = load_data_fashion_mnist(batch_size=batch_size)

lr,num_epochs = 0.001,5
optimizer = torch.optim.Adam(net.parameters(),lr=lr)
train_ch5(net,train_iter,test_iter,batch_size,optimizer,device,num_epochs)

print(net[1].gamma.view((-1,)))
print(net[1].beta.view((-1,)))

2.结果
3.Pytorch自带类

import time
import torch
from torch import nn,optim
import torch.nn.functional as F
import torchvision

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

def batch_norm(is_training,X,gamma,beta,moving_mean,moving_var,eps,momentum):
    if not is_training:
        X_hat = (X - moving_mean) / torch.sqrt(moving_var + eps)
    else:
        assert len(X.shape) in (2,4)
        if len(X.shape) == 2:
            mean = X.mean(dim=0)
            var = ((X-mean)**2).mean(dim=0)
        else:
            mean = X.mean(dim=0,keepdim=True).mean(dim=2,keepdim=True).mean(dim=3,keepdim=True)
            var = ((X-mean)**2).mean(dim=0,keepdim=True).mean(dim=2,keepdim=True).mean(dim=3,keepdim=True)
        X_hat = (X-mean) / torch.sqrt(var+eps)
        moving_mean = momentum * moving_mean + (1.0 - momentum) * mean
        moving_var = momentum * moving_var + (1.0 - momentum) *var
    Y = gamma * X_hat + beta
    return Y,moving_mean,moving_var

class BatchNorm(nn.Module):
    def __init__(self,num_features,num_dims):
        super(BatchNorm,self).__init__()
        if num_dims == 2:
            shape = (1,num_features)
        else:
            shape = (1,num_features,1,1)
        self.gamma = nn.Parameter(torch.ones(shape))
        self.beta = nn.Parameter(torch.zeros(shape))
        self.moving_mean = torch.zeros(shape)
        self.moving_var = torch.zeros(shape)

    def forward(self,X):
        if self.moving_mean.device != X.device:
            self.moving_mean = self.moving_mean.to(X.device)
            self.moving_var = self.moving_var.to(X.device)
        Y,self.moving_mean,self.moving_var = batch_norm(self.training,X,self.gamma,self.beta,self.moving_mean,self.moving_var,eps=1e-5,momentum=0.9)
        return Y

class FlattenLayer(nn.Module):
    def __init__(self):
        super(FlattenLayer,self).__init__()
    def forward(self,x):
        return x.view(x.shape[0],-1)

def evaluate_accuracy(data_iter,net,device=torch.device('cuda' if torch.cuda.is_available() else 'cpu')):
    acc_sum,n = 0.0,0
    with torch.no_grad():
        for X,y in data_iter:
            if isinstance(net,torch.nn.Module):
                net.eval()
                acc_sum += (net(X.to(device)).argmax(dim=1) == y.to(device)).float().sum().cpu().item()
                net.train()
            else:
                if('is_training' in net.__code__.co_varnames):
                    acc_sum += (net(X,is_training=False).argmax(dim=1) == y).float().sum().item()
                else:
                    acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()
            n += y.shape[0]
    return acc_sum/n

def load_data_fashion_mnist(batch_size,resize=None,root='~/Datasets/FashionMNIST'):
    trans = []
    if resize:
        trans.append(torchvision.transforms.Resize(size=resize))
    trans.append(torchvision.transforms.ToTensor())

    transform = torchvision.transforms.Compose(trans)
    mnist_train = torchvision.datasets.FashionMNIST(root=root,train=True,download=True,transform=transform)
    mnist_test = torchvision.datasets.FashionMNIST(root=root,train=False,download=True,transform=transform)

    train_iter = torch.utils.data.DataLoader(mnist_train,batch_size=batch_size,shuffle=True,num_workers=4)
    test_iter = torch.utils.data.DataLoader(mnist_test,batch_size=batch_size,shuffle=False,num_workers=4)

    return train_iter,test_iter

def train_ch5(net,train_iter,test_iter,batch_size,optimizer,device,num_epochs):
    net = net.to(device)
    print("training on ",device)
    loss = torch.nn.CrossEntropyLoss()
    batch_count = 0
    for epoch in range(num_epochs):
        train_l_sum,train_acc_sum,n,start = 0.0,0.0,0,time.time()
        for X,y in train_iter:
            X = X.to(device)
            y = y.to(device)
            y_hat = net(X)
            l = loss(y_hat,y)
            optimizer.zero_grad()
            l.backward()
            optimizer.step()
            train_l_sum += l.cpu().item()
            train_acc_sum += (y_hat.argmax(dim=1) == y).sum().cpu().item()
            n += y.shape[0]
            batch_count += 1
        test_acc = evaluate_accuracy(test_iter,net)
        print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f, time %.1f sec' %(epoch+1,train_l_sum/batch_count,train_acc_sum/n,test_acc,time.time()-start))

net = nn.Sequential(nn.Conv2d(1,6,5),
                    nn.BatchNorm2d(6),
                    nn.Sigmoid(),
                    nn.MaxPool2d(2,2),
                    nn.Conv2d(6,16,5),
                    nn.BatchNorm2d(16),
                    nn.Sigmoid(),
                    nn.MaxPool2d(2,2),
                    FlattenLayer(),
                    nn.Linear(16*4*4,120),
                    nn.BatchNorm1d(120),
                    nn.Sigmoid(),
                    nn.Linear(120,84),
                    nn.BatchNorm1d(84),
                    nn.Sigmoid(),
                    nn.Linear(84,10))

batch_size = 256
train_iter,test_iter = load_data_fashion_mnist(batch_size=batch_size)

lr,num_epochs = 0.001,5
optimizer = torch.optim.Adam(net.parameters(),lr=lr)
train_ch5(net,train_iter,test_iter,batch_size,optimizer,device,num_epochs)

4.结果（训练速度更快）