pyTorch 第一次课学习
文章目录
- 一、线性回归实战
- 二、手写数字辨识体验
-
- 1，加载数据
-
- utils
- train
- 2、创建网络
- 三、完整的代码
-
- 预测结果
- 总结
一、线性回归实战
import numpy as np
def compute_error_for_line_given_points(b,w,points):
toralError = 0
for i in range(0,len(points)):
x = points[i,0]
y = points[i,1]
toralError +=(y - (w * x + b)) **2
return toralError / float(len(points))
def step_gradient(b_current,w_current,points,learningRate):
b_gradient = 0
w_gradient = 0
N = float(len(points))
for i in range(0,len(points)):
x = points[i,0]
y = points[i,1]
b_gradient += -(2/N) * (y - ((w_current * x) + b_current))
w_gradient += -(2/N) * x * (y - ((w_current * x) + b_current))
new_b = b_current - (learningRate * b_gradient)
new_w = w_current -(learningRate * w_gradient)
return [new_b,new_w]
def gradient_decent_runner(points,starting_b,starting_m,learning_rate,num_iterations):
b = starting_b
m = starting_m
for i in range(num_iterations):
b,m = step_gradient(b,m,np.array(points),learning_rate)
return [b,m]
def run():
points = np.genfromtxt("data.csv",delimiter=",")
learning_rate = 0.0001
initial_b = 0
initial_m = 0
num_iterations = 1000
print("starting gradient descent at b = {0},m = {1},error = {2}"
.format(initial_b,initial_m,compute_error_for_line_given_points(initial_b,initial_m,points))
)
print("running")
[b,m] = gradient_decent_runner(points,initial_b,initial_m,learning_rate,num_iterations)
print("after {0} iterations b = {1},m = {2},error = {3}"
.format(num_iterations,b,m,compute_error_for_line_given_points(b,m,points))
)
if __name__ == '__main__':
run()
二、手写数字辨识体验
1，加载数据
utils
import torch
from matplotlib import pyplot as plt
def plot_curve(data):
fig = plt.figure()
plt.plot(range(len(data)), data, color='blue')
plt.legend(['value'], loc='upper right')
plt.xlabel('step')
plt.ylabel('value')
plt.show()
def plot_image(img, label, name):
fig = plt.figure()
for i in range(6):
plt.subplot(2, 3, i + 1)
plt.tight_layout()
plt.imshow(img[i][0]*0.3081+0.1307, cmap='gray', interpolation='none')
plt.title("{}: {}".format(name, label[i].item()))
plt.xticks([])
plt.yticks([])
plt.show()
def one_hot(label, depth=10):
out = torch.zeros(label.size(0), depth)
idx = torch.LongTensor(label).view(-1, 1)
out.scatter_(dim=1, index=idx, value=1)
return out
train
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')
做了normalize最后，最大值和最小值 在0的附近。
plot_image(x, y, 'image sample')
2、创建网络
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()
for epoch in range(3):
for batch_idx,(x,y) in enumerate(train_loader):
# x :[b,1,28,28],y:[512]
print(x.shape,y.shape)
break
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)
三、完整的代码
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')
预测结果
