Keras模型为make_moons数据创建线性分类

时间:2016-09-27 08:03:15

标签: machine-learning tensorflow keras

我尝试在此WildML - Implementing a Neural Network From Scratch教程中重现模型,但使用的是Keras。我尝试使用与教程相同的所有配置,但即使在调整隐藏层中的纪元数,批量大小,激活函数和单元数后,我仍然会进行线性分类:

classification graph

这是我的代码:

from keras.models import Sequential
from keras.layers import Dense, Activation
from keras.utils.visualize_util import plot
from keras.utils.np_utils import to_categorical

import  numpy as np
import  matplotlib.pyplot as plt

import  sklearn
from    sklearn import datasets, linear_model

# Build model
model = Sequential()
model.add(Dense(input_dim=2, output_dim=3, activation="tanh", init="normal"))
model.add(Dense(output_dim=2, activation="softmax"))
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])

# Train
np.random.seed(0)
X, y = sklearn.datasets.make_moons(200, noise=0.20)
y_binary = to_categorical(y)
model.fit(X, y_binary, nb_epoch=100)

# Helper function to plot a decision boundary.
# If you don't fully understand this function don't worry, it just generates the contour plot below.
def plot_decision_boundary(pred_func):
    # Set min and max values and give it some padding
    x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
    y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
    h = 0.01
    # Generate a grid of points with distance h between them
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
    # Predict the function value for the whole gid
    Z = pred_func(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)
    # Plot the contour and training examples
    plt.contourf(xx, yy, Z, cmap=plt.cm.Spectral)
    plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.Spectral)

# Predict and plot
plot_decision_boundary(lambda x: model.predict_classes(x, batch_size=200))
plt.title("Decision Boundary for hidden layer size 3")
plt.show()

2 个答案:

答案 0 :(得分:1)

我相信我弄明白了这个问题。如果我删除np.random.seed(0)并训练2000个纪元,则输出并不总是线性的,偶尔会达到90%以上的准确率:

enter image description here

一定是np.random.seed(0)导致参数播种效果不佳,而且由于我正在修理随机播种,我每次都会看到相同的图形。

答案 1 :(得分:0)

我想我已经解决了这个问题,但是我不知道为什么要解决它。如果将输出层的激活功能更改为'sigmoid'而不是'softmax',则系统将正常工作。

model = Sequential()
model.add(Dense(50, input_dim=2, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics= . ['accuracy'])

由此,我可以达到95%或更高的精度。如果将上面的代码留在 softmax 中,则线性分类器仍然存在。