目录
神经网络运作流程
上图所示是一个简单的二层神经网络结构，猫和狗的图片作为输入，依次是输入层，隐层，输出层。每张图片作为输入经过模型得到输出判别是猫还是狗，将输入与真实值之间求误差，再对误差求梯度优化参数w和b，使最后得到的误差尽可能小。
回顾
上一个博客中我们讲到，我们将输入X经过一个线性模型得再通过ReLU激活函数得到H1，在经过一次ReLU得到H2，最后一层通常并不使用ReLU激活函数，常见的有sigmoid，softmax的函数，这里我们直接通过一个线性模型得到H3，即为最终的预测输出。
识别的四个步骤
1.首先通过pytorch自带函数完成minist数据集的下载，解析，读取图片
2.建立如上图所示的三层非线性模型
3.输入训练集完成参数的优化
4.输入测试集对训练好的模型进行评估
实现代码
辅助代码utils.py
import torch
from matplotlib import pyplot as plt
def plot_curve(data):#绘制曲线
fig = plt.figure()#创建一个图片
plt.plot(range(len(data)), data, color='blue')
#图片横坐标为0-数据长度 纵坐标为数据 颜色蓝色
plt.legend(['value'], loc='upper right')
plt.xlabel('step')
plt.ylabel('value')
#图片横纵坐标的label
plt.show()
#显示图片
def plot_image(img, label, name):#显示图片
fig = plt.figure()#创建一个图片对象
for i in range(6):
plt.subplot(2, 3, i + 1)#子图
plt.tight_layout()#自动调整子图参数 未必会工作
plt.imshow(img[i][0]*0.3081+0.1307, cmap='gray', interpolation='none')
#之前做了标准化 这里把他恢复
plt.title("{}: {}".format(name, label[i].item()))
#label[i].item()把tensor类型转换为python格式类型
plt.xticks([])
plt.yticks([])
plt.show()
def one_hot(label, depth=10):#实现一位热编码
out = torch.zeros(label.size(0), depth)
idx = torch.LongTensor(label).view(-1, 1)
out.scatter_(dim=1, index=idx, value=1)
return out
核心代码mnist.py
import torch
from torch import nn
from torch.nn import functional as F
from torch import optim
import torchvision
from matplotlib import pyplot as plt
from utils import plot_image, plot_curve, one_hot
batch_size = 512
# step1. load dataset
train_loader = torch.utils.data.DataLoader(
torchvision.datasets.MNIST('mnist_data', train=True, download=True,
transform=torchvision.transforms.Compose([
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize(
(0.1307,), (0.3081,))
])),
batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(
torchvision.datasets.MNIST('mnist_data/', train=False, download=True,
transform=torchvision.transforms.Compose([
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize(
(0.1307,), (0.3081,))
])),
batch_size=batch_size, shuffle=False)
x, y = next(iter(train_loader))
print(x.shape, y.shape, x.min(), x.max())
plot_image(x, y, 'image sample')
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
# xw+b
self.fc1 = nn.Linear(28*28, 256)
self.fc2 = nn.Linear(256, 64)
self.fc3 = nn.Linear(64, 10)
def forward(self, x):
# x: [b, 1, 28, 28]
# h1 = relu(xw1+b1)
x = F.relu(self.fc1(x))
# h2 = relu(h1w2+b2)
x = F.relu(self.fc2(x))
# h3 = h2w3+b3
x = self.fc3(x)
return x
net = Net()
# [w1, b1, w2, b2, w3, b3]
optimizer = optim.SGD(net.parameters(), lr=0.01, momentum=0.9)
train_loss = []
for epoch in range(3):
for batch_idx, (x, y) in enumerate(train_loader):
# x: [b, 1, 28, 28], y: [512]
# [b, 1, 28, 28] => [b, 784]
x = x.view(x.size(0), 28*28)
# => [b, 10]
out = net(x)
# [b, 10]
y_onehot = one_hot(y)
# loss = mse(out, y_onehot)
loss = F.mse_loss(out, y_onehot)
optimizer.zero_grad()
loss.backward()
# w' = w - lr*grad
optimizer.step()
train_loss.append(loss.item())
if batch_idx % 10==0:
print(epoch, batch_idx, loss.item())
plot_curve(train_loss)
# we get optimal [w1, b1, w2, b2, w3, b3]
total_correct = 0
for x,y in test_loader:
x = x.view(x.size(0), 28*28)
out = net(x)
# out: [b, 10] => pred: [b]
pred = out.argmax(dim=1)
correct = pred.eq(y).sum().float().item()
total_correct += correct
total_num = len(test_loader.dataset)
acc = total_correct / total_num
print('test acc:', acc)
x, y = next(iter(test_loader))
out = net(x.view(x.size(0), 28*28))
pred = out.argmax(dim=1)
plot_image(x, pred, 'test')
来源：CSDN
作者：南风渐起
链接：https://blog.csdn.net/weixin_43886278/article/details/104108617