Created
May 8, 2018 17:27
-
-
Save koshian2/4b26f582fa3bbcc0ab28e119e3cbda8b to your computer and use it in GitHub Desktop.
Coursera Machine LearningをPythonで実装 - [Week5]ニューラルネットワーク(2) [2]組み込み
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
import matplotlib.pyplot as plt | |
from scipy.io import loadmat | |
from sklearn.neural_network import MLPClassifier | |
# データの読み込み | |
def load_data1(): | |
data = loadmat("ex4data1") | |
return np.array(data['X']), np.ravel(np.array(data['y'])) | |
X_data, y = load_data1() | |
m = len(X_data[:, 1]) | |
## ネットワークの可視化 | |
def display_data(X, alpha, accuracy): | |
fig = plt.figure(figsize = (5, 5)) | |
fig.subplots_adjust(hspace=0.05, wspace=0.05) | |
for i in range(X.shape[0]): | |
ax = fig.add_subplot(5, 5, i+1, xticks=[], yticks=[]) | |
ax.imshow(X[i, :].reshape(20, 20, order="F"), cmap="gray") | |
plt.suptitle(f"Alpha = {alpha}, Accuracy = {accuracy}") | |
plt.show() | |
# 正則化の値を変えてみる | |
alphas = [0.0001, 1, 50, 1e10] | |
for a in alphas: | |
print("Alpha =", a) | |
clf = MLPClassifier(hidden_layer_sizes=(26, ), solver="adam", random_state=114514, max_iter=500, alpha=a) | |
clf.fit(X_data, y) | |
accuracy = clf.score(X_data, y)*100 | |
print("Training Set Accuracy:" , accuracy) | |
print() | |
display_data(clf.coefs_[0][:, 1:].T, a, np.round(accuracy, 3)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment