dl_task01

线性回归

# 线性回归模型从零开始的实现
# import packages and modules
import matplotlib
# %matplotlib inline
import torch
from IPython import display
from matplotlib import pyplot as plt
import numpy as np
import random

print(torch.__version__)

# 生成数据集
# 使用线性模型来生成数据集，生成一个1000个样本的数据集，下面是用来生成数据的线性关系：
# price=warea⋅area+wage⋅age+b

# set input feature number
num_inputs = 2
# set example number
num_examples = 1000

# set true weight and bias in order to generate corresponded label
true_w = [2, -3.4]
true_b = 4.2

features = torch.randn(num_examples, num_inputs, dtype=torch.float32)

print(features)
print(features[:, 0])

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.float32)
# 使用图像来展示生成的数据
plt.scatter(features[:, 1].numpy(), labels.numpy(), 1)
plt.show()


# 读取数据集
def data_iter(batch_size, features, labels):
    num_examples2 = len(features)
    indices = list(range(num_examples2))
    random.shuffle(indices)  # random read 10 samples
    for i in range(0, num_examples2, batch_size):
        j = torch.LongTensor(
            indices[i: min(i + batch_size, num_examples2)])  # the last time may be not enough for a whole batch
        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, '\n', y)
    break


# 初始化模型参数
w = torch.tensor(np.random.normal(0, 0.01, (num_inputs, 1)), dtype=torch.float32)
b = torch.zeros(1, dtype=torch.float32)

w.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True)

softmax 回归

多层感知机