任务:
1. 分割数据集
2. 优化梯度下降算法:
2.1 不使用任何优化算法
2.2 mini-batch梯度下降法
2.3 使用具有动量的梯度下降算法
2.4 使用Adam算法
包含动量的梯度下降
Adam算法
最终程序展示
opt_utils.py:工具类,实现基本的向前传播,计算cost,向后传播,更新参数等。
# -*- coding: utf-8 -*-
import numpy as np
import matplotlib.pyplot as plt
import sklearn
import sklearn.datasets
def sigmoid(x):
"""
Compute the sigmoid of x
Arguments:
x -- A scalar or numpy array of any size.
Return:
s -- sigmoid(x)
"""
s = 1 / (1 + np.exp(-x))
return s
def relu(x):
"""
Compute the relu of x
Arguments:
x -- A scalar or numpy array of any size.
Return:
s -- relu(x)
"""
s = np.maximum(0, x)
return s
def load_params_and_grads(seed=1):
np.random.seed(seed)
W1 = np.random.randn(2, 3)
b1 = np.random.randn(2, 1)
W2 = np.random.randn(3, 3)
b2 = np.random.randn(3, 1)
dW1 = np.random.randn(2, 3)
db1 = np.random.randn(2, 1)
dW2 = np.random.randn(3, 3)
db2 = np.random.randn(3, 1)
return W1, b1, W2, b2, dW1, db1, dW2, db2
def initialize_parameters(layer_dims):
"""
Arguments:
layer_dims -- python array (list) containing the dimensions of each layer in our network
Returns:
parameters -- python dictionary containing your parameters "W1", "b1", ..., "WL", "bL":
W1 -- weight matrix of shape (layer_dims[l], layer_dims[l-1])
b1 -- bias vector of shape (layer_dims[l], 1)
Wl -- weight matrix of shape (layer_dims[l-1], layer_dims[l])
bl -- bias vector of shape (1, layer_dims[l])
Tips:
- For example: the layer_dims for the "Planar Data classification model" would have been [2,2,1].
This means W1's shape was (2,2), b1 was (1,2), W2 was (2,1) and b2 was (1,1). Now you have to generalize it!
- In the for loop, use parameters['W' + str(l)] to access Wl, where l is the iterative integer.
"""
np.random.seed(3)
parameters = {}
L = len(layer_dims) # number of layers in the network
for l in range(1, L):
parameters['W' + str(l)] = np.random.randn(layer_dims[l], layer_dims[l - 1]) * np.sqrt(2 / layer_dims[l - 1])
parameters['b' + str(l)] = np.zeros((layer_dims[l], 1))
# assert (parameters['W' + str(l)].shape == layer_dims[l], layer_dims[l - 1])
# assert (parameters['W' + str(l)].shape == layer_dims[l], 1)
return parameters
def forward_propagation(X, parameters):
"""
Implements the forward propagation (and computes the loss) presented in Figure 2.
Arguments:
X -- input dataset, of shape (input size, number of examples)
parameters -- python dictionary containing your parameters "W1", "b1", "W2", "b2", "W3", "b3":
W1 -- weight matrix of shape ()
b1 -- bias vector of shape ()
W2 -- weight matrix of shape ()
b2 -- bias vector of shape ()
W3 -- weight matrix of shape ()
b3 -- bias vector of shape ()
Returns:
loss -- the loss function (vanilla logistic loss)
"""
# retrieve parameters
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
W3 = parameters["W3"]
b3 = parameters["b3"]
# LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SIGMOID
z1 = np.dot(W1, X) + b1
a1 = relu(z1)
z2 = np.dot(W2, a1) + b2
a2 = relu(z2)
z3 = np.dot(W3, a2) + b3
a3 = sigmoid(z3)
cache = (z1, a1, W1, b1, z2, a2, W2, b2, z3, a3, W3, b3)
return a3, cache
def backward_propagation(X, Y, cache):
"""
Implement the backward propagation presented in figure 2.
Arguments:
X -- input dataset, of shape (input size, number of examples)
Y -- true "label" vector (containing 0 if cat, 1 if non-cat)
cache -- cache output from forward_propagation()
Returns:
gradients -- A dictionary with the gradients with respect to each parameter, activation and pre-activation variables
"""
m = X.shape[1]
(z1, a1, W1, b1, z2, a2, W2, b2, z3, a3, W3, b3) = cache
dz3 = 1. / m * (a3 - Y)
dW3 = np.dot(dz3, a2.T)
db3 = np.sum(dz3, axis=1, keepdims=True)
da2 = np.dot(W3.T, dz3)
dz2 = np.multiply(da2, np.int64(a2 > 0))
dW2 = np.dot(dz2, a1.T)
db2 = np.sum(dz2, axis=1, keepdims=True)
da1 = np.dot(W2.T, dz2)
dz1 = np.multiply(da1, np.int64(a1 > 0))
dW1 = np.dot(dz1, X.T)
db1 = np.sum(dz1, axis=1, keepdims=True)
gradients = {"dz3": dz3, "dW3": dW3, "db3": db3,
"da2": da2, "dz2": dz2, "dW2": dW2, "db2": db2,
"da1": da1, "dz1": dz1, "dW1": dW1, "db1": db1}
return gradients
def compute_cost(a3, Y):
"""
Implement the cost function
Arguments:
a3 -- post-activation, output of forward propagation
Y -- "true" labels vector, same shape as a3
Returns:
cost - value of the cost function
"""
m = Y.shape[1]
logprobs = np.multiply(-np.log(a3), Y) + np.multiply(-np.log(1 - a3), 1 - Y)
cost = 1. / m * np.sum(logprobs)
return cost
def predict(X, y, parameters):
"""
This function is used to predict the results of a n-layer neural network.
Arguments:
X -- data set of examples you would like to label
parameters -- parameters of the trained model
Returns:
p -- predictions for the given dataset X
"""
m = X.shape[1]
p = np.zeros((1, m), dtype=np.int)
# Forward propagation
a3, caches = forward_propagation(X, parameters)
# convert probas to 0/1 predictions
for i in range(0, a3.shape[1]):
if a3[0, i] > 0.5:
p[0, i] = 1
else:
p[0, i] = 0
# print results
# print ("predictions: " + str(p[0,:]))
# print ("true labels: " + str(y[0,:]))
print("Accuracy: " + str(np.mean((p[0, :] == y[0, :]))))
return p
def predict_dec(parameters, X):
"""
Used for plotting decision boundary.
Arguments:
parameters -- python dictionary containing your parameters
X -- input data of size (m, K)
Returns
predictions -- vector of predictions of our model (red: 0 / blue: 1)
"""
# Predict using forward propagation and a classification threshold of 0.5
a3, cache = forward_propagation(X, parameters)
predictions = (a3 > 0.5)
return predictions
def plot_decision_boundary(model, X, y):
# Set min and max values and give it some padding
x_min, x_max = X[0, :].min() - 1, X[0, :].max() + 1
y_min, y_max = X[1, :].min() - 1, X[1, :].max() + 1
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 grid
Z = model(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.ylabel('x2')
plt.xlabel('x1')
plt.scatter(X[0, :], X[1, :], c=np.squeeze(y), cmap=plt.cm.Spectral)
plt.show()
def load_dataset(is_plot=True):
np.random.seed(3)
train_X, train_Y = sklearn.datasets.make_moons(n_samples=300, noise=.2) # 300 #0.2
# Visualize the data
if is_plot:
plt.scatter(train_X[:, 0], train_X[:, 1], c=train_Y, s=40, cmap=plt.cm.Spectral)
plt.show()
train_X = train_X.T
train_Y = train_Y.reshape((1, train_Y.shape[0]))
return train_X, train_Y
testCase.py:实现基本参数的初始化工作
# -*- coding: utf-8 -*-
import numpy as np
def update_parameters_with_gd_test_case():
np.random.seed(1)
learning_rate = 0.01
W1 = np.random.randn(2, 3)
b1 = np.random.randn(2, 1)
W2 = np.random.randn(3, 3)
b2 = np.random.randn(3, 1)
dW1 = np.random.randn(2, 3)
db1 = np.random.randn(2, 1)
dW2 = np.random.randn(3, 3)
db2 = np.random.randn(3, 1)
parameters = {"W1": W1, "b1": b1, "W2": W2, "b2": b2}
grads = {"dW1": dW1, "db1": db1, "dW2": dW2, "db2": db2}
return parameters, grads, learning_rate
"""
def update_parameters_with_sgd_checker(function, inputs, outputs):
if function(inputs) == outputs:
print("Correct")
else:
print("Incorrect")
"""
def random_mini_batches_test_case():
np.random.seed(1)
mini_batch_size = 64
X = np.random.randn(12288, 148)
Y = np.random.randn(1, 148) < 0.5
return X, Y, mini_batch_size
def initialize_velocity_test_case():
np.random.seed(1)
W1 = np.random.randn(2, 3)
b1 = np.random.randn(2, 1)
W2 = np.random.randn(3, 3)
b2 = np.random.randn(3, 1)
parameters = {"W1": W1, "b1": b1, "W2": W2, "b2": b2}
return parameters
def update_parameters_with_momentum_test_case():
np.random.seed(1)
W1 = np.random.randn(2, 3)
b1 = np.random.randn(2, 1)
W2 = np.random.randn(3, 3)
b2 = np.random.randn(3, 1)
dW1 = np.random.randn(2, 3)
db1 = np.random.randn(2, 1)
dW2 = np.random.randn(3, 3)
db2 = np.random.randn(3, 1)
parameters = {"W1": W1, "b1": b1, "W2": W2, "b2": b2}
grads = {"dW1": dW1, "db1": db1, "dW2": dW2, "db2": db2}
v = {'dW1': np.array([[0., 0., 0.], [0., 0., 0.]]),
'dW2': np.array([[0., 0., 0.], [0., 0., 0.], [0., 0., 0.]]),
'db1': np.array([[0.], [0.]]),
'db2': np.array([[0.], [0.], [0.]])}
return parameters, grads, v
def initialize_adam_test_case():
np.random.seed(1)
W1 = np.random.randn(2, 3)
b1 = np.random.randn(2, 1)
W2 = np.random.randn(3, 3)
b2 = np.random.randn(3, 1)
parameters = {"W1": W1, "b1": b1, "W2": W2, "b2": b2}
return parameters
def update_parameters_with_adam_test_case():
np.random.seed(1)
v, s = ({'dW1': np.array([[0., 0., 0.],
[0., 0., 0.]]), 'dW2': np.array([[0., 0., 0.],
[0., 0., 0.],
[0., 0., 0.]]), 'db1': np.array([[0.],
[0.]]),'db2': np.array([[0.],
[0.],
[0.]])},
{'dW1': np.array([[0., 0., 0.],
[0., 0., 0.]]), 'dW2': np.array([[0., 0., 0.],
[0., 0., 0.],
[0., 0., 0.]]),
'db1': np.array([[0.],
[0.]]), 'db2': np.array([[0.],
[0.],
[0.]])})
W1 = np.random.randn(2, 3)
b1 = np.random.randn(2, 1)
W2 = np.random.randn(3, 3)
b2 = np.random.randn(3, 1)
dW1 = np.random.randn(2, 3)
db1 = np.random.randn(2, 1)
dW2 = np.random.randn(3, 3)
db2 = np.random.randn(3, 1)
parameters = {"W1": W1, "b1": b1, "W2": W2, "b2": b2}
grads = {"dW1": dW1, "db1": db1, "dW2": dW2, "db2": db2}
return parameters, grads, v, s
testacases1:实现3:gd优化,momtum优化,adam优化
#!/usr/bin/env python
# _*_ coding:utf-8 _*_
'''
在正式开始之前,我们需要做的是分割数据集和优化梯度下降算法,所以我们需要做以下几件事:
1. 分割数据集
2. 优化梯度下降算法:
2.1 不使用任何优化算法
2.2 mini-batch梯度下降法
2.3 使用具有动量的梯度下降算法
2.4 使用Adam算法
'''
import numpy as np
import matplotlib.pyplot as plt
import scipy.io
import math
import sklearn
import sklearn.datasets
import opt_utils
import testCase
plt.rcParams['figure.figsize'] = (7.0, 4.0)
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'
def update_parameters_with_gd(parameters, grads, learning_rate):
# 网络层数
L = len(parameters) // 2
for i in range(L):
parameters["W" + str(i + 1)] = parameters["W" + str(i + 1)] - learning_rate * grads["dW" + str(i + 1)]
parameters["b" + str(i + 1)] = parameters["b" + str(i + 1)] - learning_rate * grads["db" + str(i + 1)]
return parameters
def random_mini_batches(X, Y, mini_batch_size=64, seed=0):
np.random.seed(seed)
m = X.shape[1]
mini_batches = []
# 1.打乱顺序
permutation = list(np.random.permutation(m))
shuffled_X = X[:, permutation]
shuffled_Y = Y[:, permutation].reshape((1, m))
# 2.分割
num_complete_minibatches = math.floor(m / mini_batch_size)
for k in range(0, num_complete_minibatches):
mini_batch_X = shuffled_X[:, k * mini_batch_size:(k + 1) * mini_batch_size]
mini_batch_Y = shuffled_Y[:, k * mini_batch_size:(k + 1) * mini_batch_size]
mini_batch = (mini_batch_X, mini_batch_Y)
mini_batches.append(mini_batch)
if m % mini_batch_size != 0:
mini_batch_X = shuffled_X[:, mini_batch_size * num_complete_minibatches:]
mini_batch_Y = shuffled_Y[:, mini_batch_size * num_complete_minibatches:]
mini_batch = (mini_batch_X, mini_batch_Y)
mini_batches.append(mini_batch)
return mini_batches
# 初始化影响梯度的值v
def initialize_velocity(parameters):
L = len(parameters) // 2
v = {}
for i in range(L):
v["dW" + str(i + 1)] = np.zeros_like(parameters["W" + str(i + 1)])
v["db" + str(i + 1)] = np.zeros_like(parameters["b" + str(i + 1)])
return v
# 使用momentun更新参数
def update_parameters_with_momentum(parameters, grads, v, beta, learning_rate):
L = len(parameters) // 2
for i in range(L):
v["dW" + str(i + 1)] = beta * v["dW" + str(i + 1)] + (1 - beta) * grads["dW" + str(i + 1)]
v["db" + str(i + 1)] = beta * v["db" + str(i + 1)] + (1 - beta) * grads["db" + str(i + 1)]
# 更新参数
parameters["W" + str(i + 1)] = parameters["W" + str(i + 1)] - learning_rate * v["dW" + str(i + 1)]
parameters["b" + str(i + 1)] = parameters["b" + str(i + 1)] - learning_rate * v["db" + str(i + 1)]
return parameters, v
# 算法测试
# 测试update_parameters_with_momentun
# print("-------------测试update_parameters_with_momentun-------------")
# parameters,grads,v = testCase.update_parameters_with_momentum_test_case()
# update_parameters_with_momentun(parameters,grads,v,beta=0.9,learning_rate=0.01)
#
# print("W1 = " + str(parameters["W1"]))
# print("b1 = " + str(parameters["b1"]))
# print("W2 = " + str(parameters["W2"]))
# print("b2 = " + str(parameters["b2"]))
# print('v["dW1"] = ' + str(v["dW1"]))
# print('v["db1"] = ' + str(v["db1"]))
# print('v["dW2"] = ' + str(v["dW2"]))
# print('v["db2"] = ' + str(v["db2"]))
# 初始化adam所需要的参数
def initialize_adam(parameters):
L = len(parameters) // 2
v = {}
s = {}
for i in range(1, L + 1):
v["dW" + str(i)] = np.zeros_like(parameters["W" + str(i)])
v["db" + str(i)] = np.zeros_like(parameters["b" + str(i)])
s["dW" + str(i)] = np.zeros_like(parameters["W" + str(i)])
s["db" + str(i)] = np.zeros_like(parameters["b" + str(i)])
return (v, s)
# 根据参数更新公式来更新参数
def update_parameters_with_adam(parameters, grads, v, s, t, learning_rate=0.01, beta1=0.9, beta2=0.999, epsilon=1e-8):
"""
使用Adam更新参数
参数:
parameters - 包含了以下字段的字典:
parameters['W' + str(l)] = Wl
parameters['b' + str(l)] = bl
grads - 包含了梯度值的字典,有以下key值:
grads['dW' + str(l)] = dWl
grads['db' + str(l)] = dbl
v - Adam的变量,第一个梯度的移动平均值,是一个字典类型的变量
s - Adam的变量,平方梯度的移动平均值,是一个字典类型的变量
t - 当前迭代的次数
learning_rate - 学习率
beta1 - 动量,超参数,用于第一阶段,使得曲线的Y值不从0开始(参见天气数据的那个图)
beta2 - RMSprop的一个参数,超参数
epsilon - 防止除零操作(分母为0)
返回:
parameters - 更新后的参数
v - 第一个梯度的移动平均值,是一个字典类型的变量
s - 平方梯度的移动平均值,是一个字典类型的变量
"""
L = len(parameters) // 2
v_corrected = {}
s_corrected = {}
for i in range(1, L + 1):
v["dW" + str(i)] = beta1 * v["dW" + str(i)] + (1 - beta1) * grads["dW" + str(i)]
v["db" + str(i)] = beta1 * v["db" + str(i)] + (1 - beta1) * grads["db" + str(i)]
v_corrected["dW" + str(i)] = v["dW" + str(i)] / (1 - np.power(beta1, t))
v_corrected["db" + str(i)] = v["db" + str(i)] / (1 - np.power(beta1, t))
s["dW" + str(i)] = beta2 * s["dW" + str(i)] + (1 - beta2) * np.square(grads["dW" + str(i)])
s["db" + str(i)] = beta2 * s["db" + str(i)] + (1 - beta2) * np.square(grads["db" + str(i)])
s_corrected["dW" + str(i)] = s["dW" + str(i)] / (1 - np.power(beta2, t))
s_corrected["db" + str(i)] = s["db" + str(i)] / (1 - np.power(beta2, t))
parameters["W" + str(i)] = parameters["W" + str(i)] - learning_rate * (
v_corrected["dW" + str(i)] / np.sqrt(s_corrected["dW" + str(i)] + epsilon))
parameters["b" + str(i)] = parameters["b" + str(i)] - learning_rate * (
v_corrected["db" + str(i)] / np.sqrt(s_corrected["db" + str(i)] + epsilon))
return (parameters, v, s)
# 测试
# 测试update_with_parameters_with_adam
# print("-------------测试update_with_parameters_with_adam-------------")
# parameters, grads, v, s = testCase.update_parameters_with_adam_test_case()
# update_parameters_with_adam(parameters, grads, v, s, t=2)
#
# print("W1 = " + str(parameters["W1"]))
# print("b1 = " + str(parameters["b1"]))
# print("W2 = " + str(parameters["W2"]))
# print("b2 = " + str(parameters["b2"]))
# print('v["dW1"] = ' + str(v["dW1"]))
# print('v["db1"] = ' + str(v["db1"]))
# print('v["dW2"] = ' + str(v["dW2"]))
# print('v["db2"] = ' + str(v["db2"]))
# print('s["dW1"] = ' + str(s["dW1"]))
# print('s["db1"] = ' + str(s["db1"]))
# print('s["dW2"] = ' + str(s["dW2"]))
# print('s["db2"] = ' + str(s["db2"]))
# =======================测试
# 1.加载数据集
train_X,train_Y=opt_utils.load_dataset(is_plot=True)
# 2.定义模型
def model(X,Y,layer_dims,optimizer,learning_rate=0.0007,mini_batch_size=64,beta=0.9,beta1=0.9,beta2=0.999,epsilon=1e-8,num_epochs=10000,print_cost=True,is_plot=True):
"""
可以运行在不同优化器模式下的3层神经网络模型。
参数:
X - 输入数据,维度为(2,输入的数据集里面样本数量)
Y - 与X对应的标签
layers_dims - 包含层数和节点数量的列表
optimizer - 字符串类型的参数,用于选择优化类型,【 "gd" | "momentum" | "adam" 】
learning_rate - 学习率
mini_batch_size - 每个小批量数据集的大小
beta - 用于动量优化的一个超参数
beta1 - 用于计算梯度后的指数衰减的估计的超参数
beta1 - 用于计算平方梯度后的指数衰减的估计的超参数
epsilon - 用于在Adam中避免除零操作的超参数,一般不更改
num_epochs - 整个训练集的遍历次数,(视频2.9学习率衰减,1分55秒处,视频中称作“代”),相当于之前的num_iteration
print_cost - 是否打印误差值,每遍历1000次数据集打印一次,但是每100次记录一个误差值,又称每1000代打印一次
is_plot - 是否绘制出曲线图
返回:
parameters - 包含了学习后的参数
"""
L=len(layer_dims)
costs=[]
t=0 #每次学完一个mini_batch就增加1
seed=10# 随机种子
# 初始化参数
parameters=opt_utils.initialize_parameters(layer_dims)
# 选择优化器
if optimizer=="gd":
pass
elif optimizer=="momentum":
v=initialize_velocity(parameters)
elif optimizer=="adam":
v,s=initialize_adam(parameters)
else:
print("optimizer参数初始化错误,程序退出")
exit(1)
# 开始学习
for i in range(num_epochs):
# 随机定义minibatches,我们在每次遍历数据集之后增加种子以重新排列数据集,使每次数据的顺序都不同
seed=seed+1
minibatches=random_mini_batches(X,Y,mini_batch_size,seed)
for minibatch in minibatches:
# 选择一个minibatch
minibatch_X,minibatche_Y=minibatch
# 前向学习
A3,cache=opt_utils.forward_propagation(minibatch_X,parameters)
# 计算误差
cost=opt_utils.compute_cost(A3,minibatche_Y)
# 反向传播
grads=opt_utils.backward_propagation(minibatch_X,minibatche_Y,cache)
# 更新参数
if optimizer=="gd":
parameters=update_parameters_with_gd(parameters,grads,learning_rate)
elif optimizer=="momentum":
parameters,v=update_parameters_with_momentum(parameters,grads,v,beta,learning_rate)
elif optimizer=="adam":
t=t+1
parameters,v,s=update_parameters_with_adam(parameters,grads,v,s,t,learning_rate,beta1,beta2,epsilon)
if i%100==0:
costs.append(cost)
if print_cost and i % 1000 == 0:
print("第" + str(i) + "次遍历整个数据集,当前误差值:" + str(cost))
# 是否绘制曲线图
if is_plot:
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('epochs (per 100)')
plt.title("Learning rate = " + str(learning_rate))
plt.show()
return parameters
# 梯度下降测试
# layers_dims=[train_X.shape[0],5,2,1]
# parameters=model(train_X,train_Y,layers_dims, optimizer="gd",is_plot=True)
# # 梯度下降绘制分类情况
# preditions=opt_utils.predict(train_X,train_Y,parameters)
#
# #绘制分类图
# plt.title("Model with Gradient Descent optimization")
# axes = plt.gca()
# axes.set_xlim([-1.5, 2.5])
# axes.set_ylim([-1, 1.5])
# opt_utils.plot_decision_boundary(lambda x: opt_utils.predict_dec(parameters, x.T), train_X, train_Y)
# 具有动量的梯度下降测试
layers_dims=[train_X.shape[0],5,2,1]
parameters=model(train_X,train_Y,layers_dims,beta=0.9, optimizer="momentum",is_plot=True)
# 梯度下降绘制分类情况
preditions=opt_utils.predict(train_X,train_Y,parameters)
#绘制分类图
plt.title("Model with Gradient Descent optimization")
axes = plt.gca()
axes.set_xlim([-1.5, 2.5])
axes.set_ylim([-1, 1.5])
opt_utils.plot_decision_boundary(lambda x: opt_utils.predict_dec(parameters, x.T), train_X, train_Y)
#adam梯度下降测试
# layers_dims = [train_X.shape[0], 5, 2, 1]
# #使用Adam优化的梯度下降
# parameters = model(train_X, train_Y, layers_dims, optimizer="adam",is_plot=True)
# #预测
# preditions = opt_utils.predict(train_X,train_Y,parameters)
#
# #绘制分类图
# plt.title("Model with Adam optimization")
# axes = plt.gca()
# axes.set_xlim([-1.5, 2.5])
# axes.set_ylim([-1, 1.5])
# opt_utils.plot_decision_boundary(lambda x: opt_utils.predict_dec(parameters, x.T), train_X, train_Y)