Pytorch从入门到精通(一)：线性模型

我们先来看一个问题，然后看人工智能如何计算出最后的答案。

问题很简单：一个人学习时长（单位：小时）和他成绩的对应关系如下，求出他在学习四小时后的成绩。

其实这个问题一个5岁小孩都能一眼看出来，但是如何让人工智能计算出来呢。

我们借助Python的numpy包，然后用梯度下降法计算出结果：

import numpy as np
x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]

w = 1.0  # a random guess: random value

# our model forward pass


def forward(x):
    return x * w


# Loss function
def loss(x, y):
    y_pred = forward(x)
    return (y_pred - y) * (y_pred - y)


# compute gradient
def gradient(x, y):  # d_loss/d_w
    return 2 * x * (x * w - y)

# Before training
print("predict (before training)",  4, forward(4))

# Training loop
for epoch in range(10):
    for x_val, y_val in zip(x_data, y_data):
        grad = gradient(x_val, y_val)
        w = w - 0.01 * grad
        print("\tgrad: ", x_val, y_val, round(grad, 2))
        l = loss(x_val, y_val)

    print("progress:", epoch, "w=", round(w, 2), "loss=", round(l, 2))

# After training
print("predict (after training)",  "4 hours", forward(4))

再使用pytorch，来实现一样的功能：

import torch
from torch.autograd import Variable

x_data = Variable(torch.Tensor([[1.0], [2.0], [3.0]]))
y_data = Variable(torch.Tensor([[2.0], [4.0], [6.0]]))


class Model(torch.nn.Module):

    def __init__(self):
        """
        In the constructor we instantiate two nn.Linear module
        """
        super(Model, self).__init__()
        self.linear = torch.nn.Linear(1, 1)  # One in and one out

    def forward(self, x):
        """
        In the forward function we accept a Variable of input data and we must return
        a Variable of output data. We can use Modules defined in the constructor as
        well as arbitrary operators on Variables.
        """
        y_pred = self.linear(x)
        return y_pred

# our model
model = Model()


# Construct our loss function and an Optimizer. The call to model.parameters()
# in the SGD constructor will contain the learnable parameters of the two
# nn.Linear modules which are members of the model.
criterion = torch.nn.MSELoss(size_average=False)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Training loop
for epoch in range(500):
        # Forward pass: Compute predicted y by passing x to the model
    y_pred = model(x_data)

    # Compute and print loss
    loss = criterion(y_pred, y_data)
    print(epoch, loss.data[0])

    # Zero gradients, perform a backward pass, and update the weights.
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()


# After training
hour_var = Variable(torch.Tensor([[4.0]]))
y_pred = model(hour_var)
print("predict (after training)",  4, model(hour_var).data[0][0])