在Mnist数据集中,我们要得到的输出是0-9,共有十类,这种情况下我们希望输出0-9的概率都大于0,且和为1。
神经网络希望输出之间是带有竞争性的,即所有概率之和为1,且所有概率均大于0,softmax可以实现这两点。
import torch
from torchvision import transforms # transforms针对图像进行一些处理
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F # relu激活函数
import torch.optim as optim # 优化器
#一个没有激活函数的神经网络将只不过是一个线性回归模型(Linear regression Model)罢了,
# 它功率有限,并且大多数情况下执行得并不好。我们希望我们的神经网络不仅仅可以学习和计算线性函数,
#而且还要比这复杂得多。同样是因为没有激活函数,我们的神经网络将无法学习和模拟其他复杂类型的数据,
# 例如图像、视频、音频、语音等。
batch_size = 64
transform = transforms.Compose([transforms.ToTensor(),
transforms.Normalize((0.1307, ), (0.3081, ))])
#将原始像素数据归一到(0,1)中 并基于均值0.1307和标准差0.3081来对数据进行标准化处理
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)
class 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) # 变成二阶张量,-1表示自动算batchsize,列数为784
x = 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()
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
def train(epoch):
running_loss = 0.0
for batch_idx, data in enumerate(train_loader, 0):
inputs, target = data
optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs, target)
loss.backward()
optimizer.step()
running_loss += loss.item()
# 每300次迭代输出一次
if batch_idx % 300 == 299:
print('[%d,%5d] loss:%.3f' % (
epoch + 1, batch_idx + 1, running_loss / 300))
running_loss = 0.0
def test():
correct = 0
total = 0
with torch.no_grad():
for data in test_loader:
images, labels = data
outputs = model(images)
# 沿着第一维度(按行寻找)找最大值的下标
_, predicted = torch.max(outputs.data, dim=1) # _ 是占位符,表示有值,但是用不着
total += labels.size(0) # (N, 1)取第0个元素N
correct += (predicted == labels).sum().item()
print('Accuracy on test set:%d %%' % (100 * correct / total))
# 实例化训练和测试
if __name__ == '__main__':
# 训练10轮
for epoch in range(10):
train(epoch)
test()
作业如下:
# 导入依赖库
import pandas as pd
import numpy as np
import torch
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
import torch.optim as optim
# 数据预处理
# 定义函数将类别标签转为id表示,方便后面计算交叉熵
def labels2id(labels):
target_id = [] # 给所有target建立一个词典
target_labels = ['Class_1','Class_2','Class_3','Class_4','Class_5','Class_6','Class_7','Class_8','Class_9'] #自定义9个标签
for label in labels: # 遍历labels中的所有label
target_id.append(target_labels.index(label)) #添加label对应的索引项到target_labels中
return target_id
class OttogroupDataset(Dataset): # 准备数据集
def __init__(self, filepath):
data = pd.read_csv(filepath)
labels = data['target']
self.len = data.shape[0] # 多少行多少列
# 处理特征和标签
self.x_data = torch.tensor(np.array(data)[:, 1:-1].astype(float)) # 1:-1 左闭右开
self.y_data = labels2id(labels)
def __getitem__(self, index): # 魔法方法 支持dataset[index]
return self.x_data[index], self.y_data[index]
def __len__(self): # 魔法函数 len() 返回长度
return self.len
#载入训练集
train_dataset = OttogroupDataset('data/train.csv/train.csv')
#建立数据加载器
train_loader= DataLoader(dataset=train_dataset, batch_size=64, shuffle=True, num_workers=0)
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.l1 = torch.nn.Linear(93, 64) # 93个feature
self.l2 = torch.nn.Linear(64, 32)
self.l3 = torch.nn.Linear(32, 16)
self.l4 = torch.nn.Linear(16, 9)
self.relu = torch.nn.ReLU() # 激活函数
def forward(self, x): # 正向传播
x = self.relu(self.l1(x))
x = self.relu(self.l2(x))
x = self.relu(self.l3(x))
return self.l4(x) # 最后一层不做激活,不进行非线性变换
def predict(self, x): # 预测函数
with torch.no_grad(): # 梯度清零 不累计梯度
x = self.relu(self.l1(x))
x = self.relu(self.l2(x))
x = self.relu(self.l3(x))
x = self.relu(self.l4(x))
# 这里先取出最大概率的索引,即是所预测的类别。
_, predicted = torch.max(x, dim=1)
# 将预测的类别转为one-hot表示,方便保存为预测文件。
y = pd.get_dummies(predicted)
return y
model = Net()
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr = 0.01, momentum=0.5) #冲量,冲过鞍点和局部最优
def train(epoch): # 单次循环 epoch决定循环多少次
running_loss = 0.0
for batch_idx, data in enumerate(train_loader):
inputs, target = data # 输入数据
inputs = inputs.float()
optimizer.zero_grad() # 优化器归零
# 前馈+反馈+更新
outputs = model(inputs)
loss = criterion(outputs, target)
loss.backward()
optimizer.step()
running_loss += loss.item() # 累计的损失
if batch_idx % 300 == 299: # 每300轮输出一次
print('[%d,%5d] loss:%.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))
running_loss = 0.0
if __name__ =='__main__':
for epoch in range(50):
train(epoch)
# 定义预测保存函数,用于保存预测结果。
def predict_save():
test_data = pd.read_csv('data/train.csv/train.csv')
test_inputs = torch.tensor(np.array(test_data)[:, 1:].astype(float)) # test_data是series,要转为array;[1:]指的是第一列开始到最后,左闭右开,去掉‘id’列
out = model.predict(test_inputs.float()) # 调用预测函数,并将inputs 改为float格式
# 自定义新的标签
labels = ['Class_1', 'Class_2', 'Class_3', 'Class_4', 'Class_5', 'Class_6',
'Class_7', 'Class_8', 'Class_9']
# 添加列标签
out.columns = labels
# 插入id行
out.insert(0, 'id', test_data['id'])
output = pd.DataFrame(out)
output.to_csv('my_predict.csv', index=False)
return output
predict_save()