Skip to content

Instantly share code, notes, and snippets.

@kcha4github
Created October 28, 2018 21:35
Show Gist options
  • Star 2 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save kcha4github/928f7937daff8ca587df07a26d25b87b to your computer and use it in GitHub Desktop.
Save kcha4github/928f7937daff8ca587df07a26d25b87b to your computer and use it in GitHub Desktop.
ゼロから作るDeep Learning 4.3.3 偏微分のグラフ
import numpy as np
import matplotlib.pylab as plt
# 4.3.3
# 関数 f(x0, x1) = x0 ** 2 + x1 ** 2 の実装:2変数関数であることに注意
# 引数に numpy 配列を想定
def function_2(x):
return x[0] ** 2 + x[1] ** 2
from mpl_toolkits.mplot3d import Axes3D
x0 = np.arange(-3, 3, 0.1)
x1 = np.arange(-3, 3, 0.1)
X0, X1 = np.meshgrid(x0, x1)
y = function_2(np.array([X0, X1]))
fig = plt.figure()
ax = Axes3D(fig)
ax.set_xlabel("x0")
ax.set_ylabel("x1")
ax.set_zlabel("f(x0, x1)")
ax.plot_wireframe(X0, X1, y)
plt.show()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment