PyTorch深度学习实践——2 线性模型（课后作业）

尘小风

已于 2023-07-05 17:45:29 修改

阅读量70

点赞数

文章标签：深度学习 pytorch 人工智能 python

于 2023-07-04 21:36:30 首次发布

本文链接：https://blog.csdn.net/Qcherry/article/details/131543715

版权

UP：B站-刘二大人

原视频链接：2.线性模型_哔哩哔哩_bilibili

from mpl_toolkits.mplot3d import Axes3D
import numpy as np
import matplotlib.pyplot as plt

x_data = [1.0, 2.0, 3.0]
y_data = [5.0, 8.0, 11.0] # y=3*x+2

def forward(x):
    return x * w + b

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

W = np.arange(0.0, 4.1, 0.1)
B = np.arange(0.0, 4.1, 0.1)
mse_list = []

'''
语法：x,y = meshgrid(a,b)
作用：输入两个一维数组，输出两个二维数组x,y。其中矩阵x的行向量是向量a的简单复制，而矩阵y的列向量是向量b的简单复制。
a = np.linspace(0,2,3) # a = [0, 1, 2]
b = np.linspace(0,2,3) # b = [0, 1, 2]
x, y = np.meshgrid(a,b)
print(x)
# [[ 0.  1.  2.]
#  [ 0.  1.  2.]
#  [ 0.  1.  2.]]
print(y)
# [[ 0.  0.  0.]
#  [ 1.  1.  1.]
#  [ 2.  2.  2.]]
>>> c = [0, 1, 2]
>>> d = [0, 1]
>>> np.meshgrid(c,d)
[array([[0, 1, 2],[0, 1, 2]]), array([[0, 0, 0],[1, 1, 1]])]
'''

w, b = np.meshgrid(W, B)
loss_sum = 0
for x_val, y_val in zip(x_data, y_data):
    y_pred_val = forward(x_val)
    loss_val = loss(x_val, y_val)
    loss_sum += loss_val
print("mse=", loss_sum/len(x_data))
mse_list.append(loss_sum/len(x_data))

fig = plt.figure()
ax = Axes3D(fig)
ax.plot_surface(w, b, loss_sum/len(x_data), cmap='rainbow')
plt.show()