python中使用matplotlib画神经网络损失函数图像

1.代码

from matplotlib import pyplot as plt
import numpy as np
w = np.linspace(-1.15,1.15,10000)
Loss = (w**1 - 1)**2
plt.plot(w, Loss, label = "2 layers NN")
plt.xlabel("w")
plt.ylabel("Loss")
plt.legend(loc="best")
plt.text(-0.5,3,r"$Loss=(w^1 - 1)^2$",fontsize=20,color="red")
plt.show()

2.图像结果

补充教程：

https://www.runoob.com/w3cnote/matplotlib-tutorial.html

import numpy as np
import matplotlib.pyplot as plt

X = np.linspace(-np.pi, np.pi, 256, endpoint=True)
C,S = np.cos(X), np.sin(X)


# color为线条颜色，label为图例
plt.plot(X,C, color="blue",label="cosine")
plt.plot(X,S, color="red", label="sine")
plt.legend(loc = "upper left") # 增加图例
plt.show()