numpy 梯度下降法 线性回归
import numpy as np
import matplotlib.pyplot as plt
def get_fake_data(batch_size=8):
''' 产生随机数据:y=x*2+3,加上了一些噪声'''
x = np.random.rand(batch_size, 1) * 5
y = x * 2 + 3 + np.random.rand(batch_size, 1)*2
return x, y
def get_gradient(theta,x,y):
m=x.shape[0]
Y_estimate=np.dot(x,theta)
assert (Y_estimate.shape==(m,))
error=Y_estimate-y
assert (error.shape==(m,))
cost =1.0/(2*m)*np.sum(error**2)
grad = (1.0 / m) * np.dot(error,x)
return grad,cost
def gradient_descent(x,y,iterations,alpha):
theta=np.random.randn(2)
costs=[]
for i in range(iterations):
grad,cost=get_gradient(theta,x,y)
new_theta=theta-alpha*grad
if i%100==0:
print('{} iterations cost={}'.format(i,cost))
costs.append(cost)
theta=new_theta
return costs,theta
def vis_data():
x, y = get_fake_data(batch_size=16)
print(x.shape)
print(y.shape)
plt.scatter(np.squeeze(x), np.squeeze(y))
plt.show()
if __name__=='__main__':
batch_size=32
data_x, data_y = get_fake_data(batch_size=batch_size)
data_x=np.hstack((data_x,np.ones_like(data_x)))
print(data_x)
print(data_x.shape)
costs,theta=gradient_descent(data_x,np.squeeze(data_y),iterations=50000,alpha=0.002)
print(data_y.shape)
y_predict=np.dot(data_x,theta)
print(y_predict.shape)
plt.figure()
print(data_x[:2])
plt.scatter(data_x[:,0],np.squeeze(data_y),c='red')
plt.plot(data_x[:,0],y_predict)
plt.show()
pytorch 梯度下降法 线性回归
%matplotlib inline
import torch
from IPython import display
import numpy as np
from matplotlib import pyplot as plt
import random
torch.set_default_tensor_type('torch.FloatTensor')
num_inputs = 2
num_examples = 1000
true_w = [2, -3.4]
true_b = 4.2
features = torch.randn(num_examples, num_inputs)
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] + true_b
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()), dtype=torch.float)
print(features[0], labels[0])
def use_svg_display():
display.set_matplotlib_formats('svg')
def set_figsize(figsize=(3.5, 2.5)):
use_svg_display()
plt.rcParams['figure.figsize'] = figsize
set_figsize()
plt.scatter(features[:, 1].numpy(), labels.numpy(), 1);
def data_iter(batch_size, features, labels):
num_examples = len(features)
indices = list(range(num_examples))
random.shuffle(indices)
for i in range(0, num_examples, batch_size):
j = torch.LongTensor(indices[i: min(i + batch_size, num_examples)])
yield features.index_select(0, j), labels.index_select(0, j)
batch_size = 10
for X, y in data_iter(batch_size, features, labels):
print(X, y)
break
w = torch.tensor(np.random.normal(0, 0.01, (num_inputs, 1)), dtype=torch.float)
b = torch.zeros(1)
w.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True)
def linreg(X, w, b):
return torch.mm(X, w) + b
def squared_loss(y_hat, y):
return (y_hat - y.view(y_hat.size())) ** 2 / 2
def sgd(params, lr, batch_size):
for param in params:
param.data -= lr * param.grad / batch_size
lr = 0.03
num_epochs = 3
net = linreg
loss = squared_loss
for epoch in range(num_epochs):
for X, y in data_iter(batch_size, features, labels):
l = loss(net(X, w, b), y).sum()
l.backward()
sgd([w, b], lr, batch_size)
w.grad.data.zero_()
b.grad.data.zero_()
train_l = loss(net(features, w, b), labels)
print('epoch %d, loss %f' % (epoch + 1, train_l.mean().item()))
print(true_w, '\n', w)
print(true_b, '\n', b)
pytorch实现一个简单的神经网络
import torch
from torch import nn
import numpy as np
torch.manual_seed(1)
print(torch.__version__)
torch.set_default_tensor_type('torch.FloatTensor')
num_inputs = 2
num_examples = 1000
true_w = [2, -3.4]
true_b = 4.2
features = torch.tensor(np.random.normal(0, 1, (num_examples, num_inputs)), dtype=torch.float)
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] + true_b
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()), dtype=torch.float)
import torch.utils.data as Data
batch_size = 10
dataset = Data.TensorDataset(features, labels)
data_iter = Data.DataLoader(
dataset=dataset,
batch_size=batch_size,
shuffle=True,
num_workers=2,
)
for X, y in data_iter:
print(X, '\n', y)
break
class LinearNet(nn.Module):
def __init__(self, n_feature):
super(LinearNet, self).__init__()
self.linear = nn.Linear(n_feature, 1)
def forward(self, x):
y = self.linear(x)
return y
net = LinearNet(num_inputs)
print(net)
net = nn.Sequential()
net.add_module('linear', nn.Linear(num_inputs, 1))
for param in net.parameters():
print(param)
from torch.nn import init
init.normal_(net[0].weight, mean=0.0, std=0.01)
init.constant_(net[0].bias, val=0.0)
for param in net.parameters():
print(param)
loss = nn.MSELoss()
import torch.optim as optim
optimizer = optim.SGD(net.parameters(), lr=0.03)
print(optimizer)
num_epochs = 3
for epoch in range(1, num_epochs + 1):
for X, y in data_iter:
output = net(X)
l = loss(output, y.view(-1, 1))
optimizer.zero_grad()
l.backward()
optimizer.step()
print('epoch %d, loss: %f' % (epoch, l.item()))
dense = net[0]
print(true_w, dense.weight.data)
print(true_b, dense.bias.data)