3.3 linear regression simple realization

3.3.1 generated data set

Mxnet

num_inputs = 2
num_examples = 1000
true_w = [2, -3.4]
true_b = 4.2

features = nd.random.normal(scale=1, shape=(num_examples, num_inputs))
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] + true_b
labels += nd.random.normal(scale=0.01, shape=labels.shape)

Pytorch

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)

3.3.2 read data

Mxnet

from mxnet.gluon import data as gdata

batch_size = 10
# 将训练数据的特征和标签组合
dataset = gdata.ArrayDataset(features, labels)
# 随机读取小批量
data_iter = gdata.DataLoader(dataset, batch_size, shuffle=True)

Pytorch

import torch.utils.data as Data

batch_size = 10
# 将训练数据的特征和标签组合
dataset = Data.TensorDataset(features, labels)
# 把 dataset 放入 DataLoader
data_iter = Data.DataLoader(
    dataset=dataset,      # torch TensorDataset format
    batch_size=batch_size,      # mini batch size
    shuffle=True,               # 要不要打乱数据 (打乱比较好)
    num_workers=2,              # 多线程来读数据
)

3.3.3 Definition Model

Mxnet

from mxnet.gluon import nn

net = nn.Sequential()

net.add(nn.Dense(1))

Pytorch

net = nn.Sequential(
    nn.Linear(num_inputs, 1)

3.3.4 initialization parameter model

Mxnet

from mxnet import init

net.initialize(init.Normal(sigma=0.01))

Pytorch

from torch.nn import init

init.normal_(net[0].weight, mean=0.0, std=0.01)
init.constant_(net[0].bias, val=0.0)  # 也可以直接修改bias的data: net[0].bias.data.fill_(0)

3.3.5 defined loss function

Mxnet

from mxnet.gluon import loss as gloss

loss = gloss.L2Loss()  # 平方损失又称L2范数损失

Pytorch

loss = nn.MSELoss()

3.3.6 custom optimization algorithm

Mxnet

from mxnet import gluon

trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': 0.03})

Pytorch

import torch.optim as optim

optimizer = optim.SGD(net.parameters(), lr=0.03)

3.3.7 training model

Mxnet

num_epochs = 3
for epoch in range(1, num_epochs + 1):
    for X, y in data_iter:
        with autograd.record():
            l = loss(net(X), y)
        l.backward()
        trainer.step(batch_size)
    l = loss(net(features), labels)
    print('epoch %d, loss: %f' % (epoch, l.mean().asnumpy()))

Pytorch

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() # 梯度清零，等价于net.zero_grad()
        l.backward()
        optimizer.step()
    print('epoch %d, loss: %f' % (epoch, l.item()))