pytorch深度学习实践

B站-刘二大人

参考-PyTorch 深度学习实践_错错莫的博客-CSDN博客

线性模型

import numpy as np
import matplotlib.pyplot as pltx_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]def forward(x):return x * wdef loss(x, y):y_pred = forward(x)return (y_pred - y) ** 2# 穷举法
w_list = []
mse_list = []
for w in np.arange(0.0, 4.1, 0.1):print("w=", w)l_sum = 0for x_val, y_val in zip(x_data, y_data):y_pred_val = forward(x_val)loss_val = loss(x_val, y_val)l_sum += loss_valprint('\t', x_val, y_val, y_pred_val, loss_val)print('MSE=', l_sum / 3)w_list.append(w)mse_list.append(l_sum / 3)plt.plot(w_list, mse_list)
plt.ylabel('Loss')
plt.xlabel('w')
plt.show()    

线性模型作业

import numpy as np
import matplotlib.pyplot as pltx_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]def forward(x):return x * wdef loss(x, y):y_pred = forward(x)return (y_pred - y) ** 2# 穷举法
w_list = []
mse_list = []
for w in np.arange(0.0, 4.1, 0.1):print("w=", w)l_sum = 0for x_val, y_val in zip(x_data, y_data):y_pred_val = forward(x_val)loss_val = loss(x_val, y_val)l_sum += loss_valprint('\t', x_val, y_val, y_pred_val, loss_val)print('MSE=', l_sum / 3)w_list.append(w)mse_list.append(l_sum / 3)plt.plot(w_list, mse_list)
plt.ylabel('Loss')
plt.xlabel('w')
plt.show()    

梯度下降

import matplotlib.pyplot as plt# prepare the training set
x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]# initial guess of weight
w = 1.0# define the model linear model y = w*x
def forward(x):return x * w# define the cost function MSE
def cost(xs, ys):cost = 0for x, y in zip(xs, ys):y_pred = forward(x)cost += (y_pred - y) ** 2return cost / len(xs)# define the gradient function  gd
def gradient(xs, ys):grad = 0for x, y in zip(xs, ys):grad += 2 * x * (x * w - y)return grad / len(xs)epoch_list = []
cost_list = []
print('predict (before training)', 4, forward(4))
for epoch in range(100):cost_val = cost(x_data, y_data)grad_val = gradient(x_data, y_data)w -= 0.01 * grad_val  # 0.01 learning rateprint('epoch:', epoch, 'w=', w, 'loss=', cost_val)epoch_list.append(epoch)cost_list.append(cost_val)print('predict (after training)', 4, forward(4))plt.plot(epoch_list, cost_list)
plt.ylabel('cost')
plt.xlabel('epoch')
plt.show()

随机梯度下降

import matplotlib.pyplot as pltx_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]w = 1.0def forward(x):return x * w# calculate loss function
def loss(x, y):y_pred = forward(x)return (y_pred - y) ** 2# define the gradient function  sgd
def gradient(x, y):return 2 * x * (x * w - y)epoch_list = []
loss_list = []
print('predict (before training)', 4, forward(4))
for epoch in range(100):for x, y in zip(x_data, y_data):grad = gradient(x, y)w = w - 0.01 * grad  # update weight by every grad of sample of training setprint("\tgrad:", x, y, grad)l = loss(x, y)print("progress:", epoch, "w=", w, "loss=", l)epoch_list.append(epoch)loss_list.append(l)print('predict (after training)', 4, forward(4))
plt.plot(epoch_list, loss_list)
plt.ylabel('loss')
plt.xlabel('epoch')
plt.show()

pytorch线性回归

import torch
import matplotlib.pyplot as plt
import numpy as np# prepare dataset
# x,y是矩阵，3行1列 也就是说总共有3个数据，每个数据只有1个特征
x_data = torch.tensor([[1.0], [2.0], [3.0]])
y_data = torch.tensor([[2.0], [4.0], [6.0]])# design model using class
"""
our model class should be inherit from nn.Module, which is base class for all neural network modules.
member methods __init__() and forward() have to be implemented
class nn.linear contain two member Tensors: weight and bias
class nn.Linear has implemented the magic method __call__(),which enable the instance of the class can
be called just like a function.Normally the forward() will be called 
"""class LinearModel(torch.nn.Module):def __init__(self):super(LinearModel, self).__init__()# (1,1)是指输入x和输出y的特征维度，这里数据集中的x和y的特征都是1维的# 该线性层需要学习的参数是w和b  获取w/b的方式分别是~linear.weight/linear.biasself.linear = torch.nn.Linear(1, 1)def forward(self, x):y_pred = self.linear(x)return y_predmodel = LinearModel()# construct loss and optimizer
# criterion = torch.nn.MSELoss(size_average = False)
criterion = torch.nn.MSELoss(reduction='sum')
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)  # model.parameters()自动完成参数的初始化操作，这个地方我可能理解错了# training cycle forward, backward, update
for epoch in range(1000):y_pred = model(x_data)  # forward:predictloss = criterion(y_pred, y_data)  # forward: lossprint(epoch, loss.item())optimizer.zero_grad()  # the grad computer by .backward() will be accumulated. so before backward, remember set the grad to zeroloss.backward()  # backward: autograd，自动计算梯度optimizer.step()  # update 参数，即更新w和b的值print('w = ', model.linear.weight.item())
print('b = ', model.linear.bias.item())x_test = torch.tensor([[4.0]])
y_test = model(x_test)
print('y_pred = ', y_test.data)

logistic回归

import torch# import torch.nn.functional as F# prepare dataset
x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[0], [0], [1]])# design model using class
class LogisticRegressionModel(torch.nn.Module):def __init__(self):super(LogisticRegressionModel, self).__init__()self.linear = torch.nn.Linear(1, 1)def forward(self, x):# y_pred = F.sigmoid(self.linear(x))y_pred = torch.sigmoid(self.linear(x))return y_predmodel = LogisticRegressionModel()# construct loss and optimizer
# 默认情况下，loss会基于element平均，如果size_average=False的话，loss会被累加。
criterion = torch.nn.BCELoss(size_average=False)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)# training cycle forward, backward, update
for epoch in range(1000):y_pred = model(x_data)loss = criterion(y_pred, y_data)print(epoch, loss.item())optimizer.zero_grad()loss.backward()optimizer.step()print('w = ', model.linear.weight.item())
print('b = ', model.linear.bias.item())x_test = torch.Tensor([[4.0]])
y_test = model(x_test)
print('y_pred = ', y_test.data)

多特征输入

import numpy as np
import torch
import matplotlib.pyplot as plt# prepare dataset
xy = np.loadtxt('diabetes.csv.gz', delimiter=',', dtype=np.float32)
x_data = torch.from_numpy(xy[:, :-1])  # 第一个‘：’是指读取所有行，第二个‘：’是指从第一列开始，最后一列不要
y_data = torch.from_numpy(xy[:, [-1]])  # [-1] 最后得到的是个矩阵# design model using classclass Model(torch.nn.Module):def __init__(self):super(Model, self).__init__()self.linear1 = torch.nn.Linear(8, 6)  # 输入数据x的特征是8维，x有8个特征self.linear2 = torch.nn.Linear(6, 4)self.linear3 = torch.nn.Linear(4, 1)self.sigmoid = torch.nn.Sigmoid()  # 将其看作是网络的一层，而不是简单的函数使用def forward(self, x):x = self.sigmoid(self.linear1(x))x = self.sigmoid(self.linear2(x))x = self.sigmoid(self.linear3(x))  # y hatreturn xmodel = Model()# construct loss and optimizer
# criterion = torch.nn.BCELoss(size_average = True)
criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)epoch_list = []
loss_list = []
# training cycle forward, backward, update
for epoch in range(100):y_pred = model(x_data)loss = criterion(y_pred, y_data)print(epoch, loss.item())epoch_list.append(epoch)loss_list.append(loss.item())optimizer.zero_grad()loss.backward()optimizer.step()plt.plot(epoch_list, loss_list)
plt.ylabel('loss')
plt.xlabel('epoch')
plt.show()

加载数据

import torch
import numpy as np
from torch.utils.data import Dataset
from torch.utils.data import DataLoader# prepare datasetclass DiabetesDataset(Dataset):def __init__(self, filepath):xy = np.loadtxt(filepath, delimiter=',', dtype=np.float32)self.len = xy.shape[0]  # shape(多少行，多少列)self.x_data = torch.from_numpy(xy[:, :-1])self.y_data = torch.from_numpy(xy[:, [-1]])def __getitem__(self, index):return self.x_data[index], self.y_data[index]def __len__(self):return self.lendataset = DiabetesDataset('diabetes.csv.gz')
train_loader = DataLoader(dataset=dataset, batch_size=32, shuffle=True, num_workers=0)  # num_workers 多线程# design model using classclass Model(torch.nn.Module):def __init__(self):super(Model, self).__init__()self.linear1 = torch.nn.Linear(8, 6)self.linear2 = torch.nn.Linear(6, 4)self.linear3 = torch.nn.Linear(4, 1)self.sigmoid = torch.nn.Sigmoid()def forward(self, x):x = self.sigmoid(self.linear1(x))x = self.sigmoid(self.linear2(x))x = self.sigmoid(self.linear3(x))return xmodel = Model()# construct loss and optimizer
criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)# training cycle forward, backward, update
if __name__ == '__main__':for epoch in range(100):for i, data in enumerate(train_loader, 0):  # train_loader 是先shuffle后mini_batchinputs, labels = datay_pred = model(inputs)loss = criterion(y_pred, labels)print(epoch, i, loss.item())optimizer.zero_grad()loss.backward()optimizer.step()

加载数据划分数据集

import torch
import numpy as np
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
from sklearn.model_selection import train_test_split# 读取原始数据，并划分训练集和测试集
raw_data = np.loadtxt('diabetes.csv.gz', delimiter=',', dtype=np.float32)
X = raw_data[:, :-1]
y = raw_data[:, [-1]]
Xtrain, Xtest, Ytrain, Ytest = train_test_split(X, y, test_size=0.3)
Xtest = torch.from_numpy(Xtest)
Ytest = torch.from_numpy(Ytest)# 将训练数据集进行批量处理
# prepare datasetclass DiabetesDataset(Dataset):def __init__(self, data, label):self.len = data.shape[0]  # shape(多少行，多少列)self.x_data = torch.from_numpy(data)self.y_data = torch.from_numpy(label)def __getitem__(self, index):return self.x_data[index], self.y_data[index]def __len__(self):return self.lentrain_dataset = DiabetesDataset(Xtrain, Ytrain)
train_loader = DataLoader(dataset=train_dataset, batch_size=32, shuffle=True, num_workers=0)  # num_workers 多线程# design model using classclass Model(torch.nn.Module):def __init__(self):super(Model, self).__init__()self.linear1 = torch.nn.Linear(8, 6)self.linear2 = torch.nn.Linear(6, 4)self.linear3 = torch.nn.Linear(4, 2)self.linear4 = torch.nn.Linear(2, 1)self.sigmoid = torch.nn.Sigmoid()def forward(self, x):x = self.sigmoid(self.linear1(x))x = self.sigmoid(self.linear2(x))x = self.sigmoid(self.linear3(x))x = self.sigmoid(self.linear4(x))return xmodel = Model()# construct loss and optimizer
criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)# training cycle forward, backward, updatedef train(epoch):train_loss = 0.0count = 0for i, data in enumerate(train_loader, 0):inputs, labels = datay_pred = model(inputs)loss = criterion(y_pred, labels)optimizer.zero_grad()loss.backward()optimizer.step()train_loss += loss.item()count = iif epoch % 2000 == 1999:print("train loss:", train_loss / count, end=',')def test():with torch.no_grad():y_pred = model(Xtest)y_pred_label = torch.where(y_pred >= 0.5, torch.tensor([1.0]), torch.tensor([0.0]))acc = torch.eq(y_pred_label, Ytest).sum().item() / Ytest.size(0)print("test acc:", acc)if __name__ == '__main__':for epoch in range(10000):train(epoch)if epoch % 2000 == 1999:test()

多分类问题（softmax）

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim# prepare datasetbatch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])  # 归一化,均值和方差train_dataset = datasets.MNIST(root='./dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='./dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)# design model using classclass Net(torch.nn.Module):def __init__(self):super(Net, self).__init__()self.l1 = torch.nn.Linear(784, 512)self.l2 = torch.nn.Linear(512, 256)self.l3 = torch.nn.Linear(256, 128)self.l4 = torch.nn.Linear(128, 64)self.l5 = torch.nn.Linear(64, 10)def forward(self, x):x = x.view(-1, 784)  # -1其实就是自动获取mini_batchx = F.relu(self.l1(x))x = F.relu(self.l2(x))x = F.relu(self.l3(x))x = F.relu(self.l4(x))return self.l5(x)  # 最后一层不做激活，不进行非线性变换model = Net()# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# training cycle forward, backward, updatedef train(epoch):running_loss = 0.0for batch_idx, data in enumerate(train_loader, 0):# 获得一个批次的数据和标签inputs, target = dataoptimizer.zero_grad()# 获得模型预测结果(64, 10)outputs = model(inputs)# 交叉熵代价函数outputs(64,10),target（64）loss = criterion(outputs, target)loss.backward()optimizer.step()running_loss += loss.item()if batch_idx % 300 == 299:print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))running_loss = 0.0def test():correct = 0total = 0with torch.no_grad():for data in test_loader:images, labels = dataoutputs = model(images)_, predicted = torch.max(outputs.data, dim=1)  # dim = 1 列是第0个维度，行是第1个维度total += labels.size(0)correct += (predicted == labels).sum().item()  # 张量之间的比较运算print('accuracy on test set: %d %% ' % (100 * correct / total))if __name__ == '__main__':for epoch in range(10):train(epoch)test()

卷积神经网络

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim# prepare datasetbatch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])train_dataset = datasets.MNIST(root='./dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='./dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)# design model using classclass Net(torch.nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5)self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=5)self.pooling = torch.nn.MaxPool2d(2)self.fc = torch.nn.Linear(320, 10)def forward(self, x):# flatten data from (n,1,28,28) to (n, 784)batch_size = x.size(0)x = F.relu(self.pooling(self.conv1(x)))x = F.relu(self.pooling(self.conv2(x)))x = x.view(batch_size, -1)  # -1 此处自动算出的是320x = self.fc(x)return xmodel = Net()# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# training cycle forward, backward, updatedef train(epoch):running_loss = 0.0for batch_idx, data in enumerate(train_loader, 0):inputs, target = dataoptimizer.zero_grad()outputs = model(inputs)loss = criterion(outputs, target)loss.backward()optimizer.step()running_loss += loss.item()if batch_idx % 300 == 299:print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))running_loss = 0.0def test():correct = 0total = 0with torch.no_grad():for data in test_loader:images, labels = dataoutputs = model(images)_, predicted = torch.max(outputs.data, dim=1)total += labels.size(0)correct += (predicted == labels).sum().item()print('accuracy on test set: %d %% ' % (100 * correct / total))if __name__ == '__main__':for epoch in range(10):train(epoch)test()

卷积神经网络-GPU

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim
import matplotlib.pyplot as plt# prepare datasetbatch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])train_dataset = datasets.MNIST(root='./dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='./dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)# design model using classclass Net(torch.nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5)self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=5)self.pooling = torch.nn.MaxPool2d(2)self.fc = torch.nn.Linear(320, 10)def forward(self, x):# flatten data from (n,1,28,28) to (n, 784)batch_size = x.size(0)x = F.relu(self.pooling(self.conv1(x)))x = F.relu(self.pooling(self.conv2(x)))x = x.view(batch_size, -1)  # -1 此处自动算出的是320# print("x.shape",x.shape)x = self.fc(x)return xmodel = Net()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# training cycle forward, backward, updatedef train(epoch):running_loss = 0.0for batch_idx, data in enumerate(train_loader, 0):inputs, target = datainputs, target = inputs.to(device), target.to(device)optimizer.zero_grad()outputs = model(inputs)loss = criterion(outputs, target)loss.backward()optimizer.step()running_loss += loss.item()if batch_idx % 300 == 299:print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))running_loss = 0.0def test():correct = 0total = 0with torch.no_grad():for data in test_loader:images, labels = dataimages, labels = images.to(device), labels.to(device)outputs = model(images)_, predicted = torch.max(outputs.data, dim=1)total += labels.size(0)correct += (predicted == labels).sum().item()print('accuracy on test set: %d %% ' % (100 * correct / total))return correct / totalif __name__ == '__main__':epoch_list = []acc_list = []for epoch in range(10):train(epoch)acc = test()epoch_list.append(epoch)acc_list.append(acc)plt.plot(epoch_list, acc_list)plt.ylabel('accuracy')plt.xlabel('epoch')plt.show()

Inception Moudel

import torch
import torch.nn as nn
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim# prepare datasetbatch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])  # 归一化,均值和方差train_dataset = datasets.MNIST(root='./dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='./dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)# design model using class
class InceptionA(nn.Module):def __init__(self, in_channels):super(InceptionA, self).__init__()self.branch1x1 = nn.Conv2d(in_channels, 16, kernel_size=1)self.branch5x5_1 = nn.Conv2d(in_channels, 16, kernel_size=1)self.branch5x5_2 = nn.Conv2d(16, 24, kernel_size=5, padding=2)self.branch3x3_1 = nn.Conv2d(in_channels, 16, kernel_size=1)self.branch3x3_2 = nn.Conv2d(16, 24, kernel_size=3, padding=1)self.branch3x3_3 = nn.Conv2d(24, 24, kernel_size=3, padding=1)self.branch_pool = nn.Conv2d(in_channels, 24, kernel_size=1)def forward(self, x):branch1x1 = self.branch1x1(x)branch5x5 = self.branch5x5_1(x)branch5x5 = self.branch5x5_2(branch5x5)branch3x3 = self.branch3x3_1(x)branch3x3 = self.branch3x3_2(branch3x3)branch3x3 = self.branch3x3_3(branch3x3)branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)branch_pool = self.branch_pool(branch_pool)outputs = [branch1x1, branch5x5, branch3x3, branch_pool]return torch.cat(outputs, dim=1)  # b,c,w,h  c对应的是dim=1class Net(nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = nn.Conv2d(1, 10, kernel_size=5)self.conv2 = nn.Conv2d(88, 20, kernel_size=5)  # 88 = 24x3 + 16self.incep1 = InceptionA(in_channels=10)  # 与conv1 中的10对应self.incep2 = InceptionA(in_channels=20)  # 与conv2 中的20对应self.mp = nn.MaxPool2d(2)self.fc = nn.Linear(1408, 10)def forward(self, x):in_size = x.size(0)x = F.relu(self.mp(self.conv1(x)))x = self.incep1(x)x = F.relu(self.mp(self.conv2(x)))x = self.incep2(x)x = x.view(in_size, -1)x = self.fc(x)return xmodel = Net()# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# training cycle forward, backward, updatedef train(epoch):running_loss = 0.0for batch_idx, data in enumerate(train_loader, 0):inputs, target = dataoptimizer.zero_grad()outputs = model(inputs)loss = criterion(outputs, target)loss.backward()optimizer.step()running_loss += loss.item()if batch_idx % 300 == 299:print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))running_loss = 0.0def test():correct = 0total = 0with torch.no_grad():for data in test_loader:images, labels = dataoutputs = model(images)_, predicted = torch.max(outputs.data, dim=1)total += labels.size(0)correct += (predicted == labels).sum().item()print('accuracy on test set: %d %% ' % (100 * correct / total))if __name__ == '__main__':for epoch in range(10):train(epoch)test()

ResidualBlock

import torch
import torch.nn as nn
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim# prepare datasetbatch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])  # 归一化,均值和方差train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)# design model using class
class ResidualBlock(nn.Module):def __init__(self, channels):super(ResidualBlock, self).__init__()self.channels = channelsself.conv1 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)self.conv2 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)def forward(self, x):y = F.relu(self.conv1(x))y = self.conv2(y)return F.relu(x + y)class Net(nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = nn.Conv2d(1, 16, kernel_size=5)self.conv2 = nn.Conv2d(16, 32, kernel_size=5)  # 88 = 24x3 + 16self.rblock1 = ResidualBlock(16)self.rblock2 = ResidualBlock(32)self.mp = nn.MaxPool2d(2)self.fc = nn.Linear(512, 10)  # 暂时不知道1408咋能自动出来的def forward(self, x):in_size = x.size(0)x = self.mp(F.relu(self.conv1(x)))x = self.rblock1(x)x = self.mp(F.relu(self.conv2(x)))x = self.rblock2(x)x = x.view(in_size, -1)x = self.fc(x)return xmodel = Net()# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# training cycle forward, backward, updatedef train(epoch):running_loss = 0.0for batch_idx, data in enumerate(train_loader, 0):inputs, target = dataoptimizer.zero_grad()outputs = model(inputs)loss = criterion(outputs, target)loss.backward()optimizer.step()running_loss += loss.item()if batch_idx % 300 == 299:print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))running_loss = 0.0def test():correct = 0total = 0with torch.no_grad():for data in test_loader:images, labels = dataoutputs = model(images)_, predicted = torch.max(outputs.data, dim=1)total += labels.size(0)correct += (predicted == labels).sum().item()print('accuracy on test set: %d %% ' % (100 * correct / total))if __name__ == '__main__':for epoch in range(10):train(epoch)test()