pytorch 入门笔记 | 谈谈pytorch的框架特色

pytorch 可以说是深度学习入门首选的框架，语法特点特别接近numpy，上手简单。作为一门流行的框架，总有它流行的原因，笔者认为这是pytorch框架的一些特色所决定的，以下内容来源笔者在入门学习中的体会，因此作文总结。

近期我简单入门了一下深度学习，对 pytorch 有了一定的掌握和认识，不得不感慨 pytorch 大法好，对深度学习新手特别友好，和numpy有着相似的语法特点，但有一些专门为深度学习设计的框架特色，以下结合个人所学和体会，得出以下两大特色：

1. 声明张量矩阵，可以自动计算梯度，省去了许多计算代码；
2. 快速搭建神经网络，提供简单易懂的模型算法接口

 

自动计算梯度

在 pytorch 中矩阵变量是以张量（tensor）来声明定义的，我们可以在声明张量的时候，决定该变量是否自动计算梯度。

以下给出简单的例子。

简单的线性模型 - 1

import torch
import torchvision 
import torch.nn as nn
import numpy as np
import torchvision.transforms as transforms

x = torch.tensor(1., requires_grad = True)
w = torch.tensor(2., requires_grad = True)
b = torch.tensor(3., requires_grad = True)
print(x, w, b)
y = w * x + b
print(y)

print(x.grad)
print(w.grad)
print(b.grad)

# compute gradient
y.backward()

print(x.grad)
print(w.grad)
print(b.grad)

输出结果如下：

简单线性模型 - 2

import torch
import torch.nn as nn
import numpy as np
import matplotlib.pyplot as plt


# Hyper-parameters
input_size = 1
output_size = 1
num_epochs = 60
learning_rate = 0.001

# Toy dataset
x_train = np.array([[3.3], [4.4], [5.5], [6.71], [6.93], [4.168], 
                    [9.779], [6.182], [7.59], [2.167], [7.042], 
                    [10.791], [5.313], [7.997], [3.1]], dtype=np.float32)

y_train = np.array([[1.7], [2.76], [2.09], [3.19], [1.694], [1.573], 
                    [3.366], [2.596], [2.53], [1.221], [2.827], 
                    [3.465], [1.65], [2.904], [1.3]], dtype=np.float32)

# Linear regression model
model = nn.Linear(input_size, output_size)

# Define the loss function
criterion = nn.MSELoss()
# Define the optimiter to solve
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)  

# Train the model
for epoch in range(num_epochs):
    # Convert numpy arrays to torch tensors
    inputs = torch.from_numpy(x_train)
    targets = torch.from_numpy(y_train)

    # Forward pass
    outputs = model(inputs)
    
    # calculate loss fucntion value.
    loss = criterion(outputs, targets)
    
    # Backward and optimize
    optimizer.zero_grad()
    loss.backward()
    
    # update the parameter
    optimizer.step()
    
    if (epoch+1) % 5 == 0:
        print ('Epoch [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, loss.item()))

# Plot the graph
predicted = model(torch.from_numpy(x_train)).detach().numpy()
plt.plot(x_train, y_train, 'ro', label='Original data')
plt.plot(x_train, predicted, label='Fitted line')
plt.legend()
plt.show()

# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')

 

快速搭建神经网络

pytorch 提供的nn模块可以帮助我们很快定义好一个网络结构，主要有几个步骤：

1. 定义模型，损失函数，优化求解方法
2. 开始训练，输出预测结果，计算损失函数值，反向更新参数
3. 直到迭代结束，模型训练成功。

以下给出一个简单的三层神经网络结构。

import torch
import matplotlib.pyplot as plt

# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10

# Create random Tensors to hold inputs and outputs
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)

# Use the nn package to define our model and loss function.
model = torch.nn.Sequential(
    torch.nn.Linear(D_in, H),
    torch.nn.ReLU(),
    torch.nn.Linear(H, D_out),
)
loss_fn = torch.nn.MSELoss(reduction='sum')

# Use the optim package to define an Optimizer that will update the weights of
# the model for us. Here we will use Adam; the optim package contains many other
# optimization algoriths. The first argument to the Adam constructor tells the
# optimizer which Tensors it should update.
learn_rate = 1e-4
optimizer = torch.optim.Adam(model.parameters(), lr = learn_rate)

t_list = []
loss_list = []

for t in range(500):
    # output the predicted value
    y_pred = model(x)
    
    # calculate loss function value
    loss = loss_fn(y_pred, y)
    
    # for visualization
    t_list.append(t)
    loss_list.append(loss)
    
    # make the optimizer's gradient to be zero
    optimizer.zero_grad()
    
    # calculate gradient and update parameter
    loss.backward()
    optimizer.step()
    
plt.plot(t_list, loss_list， label = 'loss')
plt.show()

随迭代次数的增加，损失函数值逐渐变小。

 

pytorch 的魅力远不止如此，本菜以后更熟练的时候在总结！