Wu deeplearning.ai C1W3 assignment3

Planar data classification with one hidden layer

Welcome to your week 3 programming assignment. It's time to build your first neural network, which will have a hidden layer. You will see a big difference between this model and the one you implemented using logistic regression. 

You will learn how to:

• Implement a 2-class classification neural network with a single hidden layer
• Use units with a non-linear activation function, such as tanh 
• Compute the cross entropy loss 
• Implement forward and backward propagation

这次主要是构建一个one hidden layer的简单神经网络，并且完成数据分类的工作，下面分成几点来进行说明。

1）本次作业的坑点以及修改调试过程（是十分的坑啊）

2）模型的构建过程

3）测试结果

1.作业的坑点

从数据的导入开始说起，导入必要的packages

# Package imports
import numpy as np
import matplotlib.pyplot as plt
from testCases import *
import sklearn
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets

%matplotlib inline

np.random.seed(1) # set a seed so that the results are consistent

#load date-set
X, Y = load_planar_dataset() 

#visualize the date
plt.scatter(X[0, :], X[1, :], c=np.squeeze(Y), s=40, cmap=plt.cm.Spectral);

这边在原来给的代码中，为了可视化我们的数据集，调用了plt.scatter。原来吴恩达给的代码是c = Y，如果直接运行的话会出现如下错误 

 因为一开始我们Y的维度是（1，400）而在使用绘图函数的时候，需要进行降维度处理，去除冗余的维度。通常算法的结果是可以表示向量的数组（即包含两对