刘二大人 PyTorch深度学习实践 笔记 P9 多分类问题
P9 多分类问题
1、softmax函数
糖尿病数据集分类为0和1，MNIST数据集有10个分类怎么办？输出时输出10个y？
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。
图中绿色框中就是指包括softmax的计算过程：
; 2、作业：CrossEntropyLoss vs NULLoss
I NLLLoss损失函数
代码实现如下：
import numpy as np
y = np.array([1, 0, 0])
z = np.array([0.2, 0.1, -0.1])
y_pred = np.exp(z) / np.exp(z).sum()
loss = (- y * np.log(y_pred)).sum()
print(loss)
输出：
0.9729189131256584
II CrossEntropyLoss损失函数
CrossEntropyLoss损失函数 = Softmax + NLLLoss损失函数
神经网络的最后一层不需要做激活(经过Softmax层的计算)，直接输入到CrossEntropyLoss损失函数中就可以。
代码实现如下：
import torch
y = torch.LongTensor([0])
z = torch.Tensor([[0.2, 0.1, -0.1]])
criterion = torch.nn.CrossEntropyLoss()
loss = criterion(z, y)
print(loss)
输出：
tensor(0.9729)
III 举例
import torch
criterion = torch.nn.CrossEntropyLoss()
Y = torch.LongTensor([2, 0, 1])
Y_pred1 = torch.Tensor([[0.1, 0.2, 0.9],
[1.1, 0.1, 0.2],
[0.2, 2.1, 0.1]])
Y_pred2 = torch.Tensor([[0.8, 0.2, 0.3],
[0.2, 0.3, 0.5],
[0.2, 0.2, 0.5]])
l1 = criterion(Y_pred1, Y)
l2 = criterion(Y_pred2, Y)
print("Batch Loss1 = ", l1.data, "\nBatch Loss2 = ", l2.data)
输出：
Batch Loss1 = tensor(0.4966)
Batch Loss2 = tensor(1.2389)
3、应用在MINIST数据集
I 实现过程
- 准备数据集
- 设计模型
- 构造损失函数和优化器
- 训练+测试(前馈、反馈、更新)
II 实现代码
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
batch_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)
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)
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)
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()
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)
_, 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()
输出：
[1, 300] loss:2.256
[1, 600] loss:1.102
[1, 900] loss:0.432
Accuracy on test set:89 %
[2, 300] loss:0.331
[2, 600] loss:0.279
[2, 900] loss:0.238
Accuracy on test set:93 %
[3, 300] loss:0.198
[3, 600] loss:0.180
[3, 900] loss:0.158
Accuracy on test set:95 %
[4, 300] loss:0.137
[4, 600] loss:0.124
[4, 900] loss:0.119
Accuracy on test set:96 %
[5, 300] loss:0.102
[5, 600] loss:0.101
[5, 900] loss:0.093
Accuracy on test set:96 %
[6, 300] loss:0.083
[6, 600] loss:0.072
[6, 900] loss:0.078
Accuracy on test set:97 %
[7, 300] loss:0.063
[7, 600] loss:0.060
[7, 900] loss:0.064
Accuracy on test set:97 %
[8, 300] loss:0.047
[8, 600] loss:0.052
[8, 900] loss:0.054
Accuracy on test set:97 %
[9, 300] loss:0.040
[9, 600] loss:0.040
[9, 900] loss:0.042
Accuracy on test set:97 %
[10, 300] loss:0.030
[10, 600] loss:0.031
[10, 900] loss:0.035
Accuracy on test set:97 %
损失不断降低，准确率高达97%，但是到最后准确率就上不去了，是因为对图像用全连接神经网络忽略了对局部信息的利用，把所有的元素都全连接了，处理时权重不够高，处理图像时更关心高级别的特征。
如果可以先做特征提取，再做分类训练，效果可能会好些。
人工特征(wavelet )提取方法：FFT傅里叶变换、小波变化
自动特征提取：CNN
5、作业
代码：
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
def labels2id(labels):
target_id = []
target_labels = ['Class_1','Class_2','Class_3','Class_4','Class_5','Class_6','Class_7','Class_8','Class_9']
for label in labels:
target_id.append(target_labels.index(label))
return target_id
class OttogroupDataset(Dataset):
def __init__(self, filepath):
data = pd.read_csv(filepath)
labels = data['target']
self.len = data.shape[0]
self.x_data = torch.tensor(np.array(data)[:, 1:-1].astype(float))
self.y_data = labels2id(labels)
def __getitem__(self, index):
return self.x_data[index], self.y_data[index]
def __len__(self):
return self.len
train_dataset = OttogroupDataset('dataset/otto-group/train.csv')
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)
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()
def forward(self, x):
x = self.relu(self.l1(x))
x = self.relu(self.l2(x))
x = self.relu(self.l3(x))
return self.l4(x)
def predict(self, x):
with torch.no_grad():
x = self.relu(self.l1(x))
x = self.relu(self.l2(x))
x = self.relu(self.l3(x))
x = self.relu(self.l4(x))
_, predicted = torch.max(x, dim=1)
y = pd.get_dummies(predicted)
return y
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):
inputs, target = data
inputs = inputs.float()
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 = 0.0
if __name__ =='__main__':
for epoch in range(50):
train(epoch)
def predict_save():
test_data = pd.read_csv('dataset/otto-group/test.csv')
test_inputs = torch.tensor(np.array(test_data)[:, 1:].astype(float))
out = model.predict(test_inputs.float())
labels = ['Class_1', 'Class_2', 'Class_3', 'Class_4', 'Class_5', 'Class_6',
'Class_7', 'Class_8', 'Class_9']
out.columns = labels
out.insert(0, 'id', test_data['id'])
output = pd.DataFrame(out)
output.to_csv('my_predict.csv', index=False)
return output
predict_save()
Original: https://blog.csdn.net/qq_44948213/article/details/126480753
Author: 小白*进阶ing
Title: 刘二大人 PyTorch深度学习实践 笔记 P9 多分类问题
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/710455/
转载文章受原作者版权保护。转载请注明原作者出处！