目录
- 一、Python代码
- 二、个人理解
- 三、lr_utils文件
一、Python代码
import numpy as np
import matplotlib.pyplot as plt
import h5py
from lr_utils import load_dataset
def sigmoid(z):
s = 1 / (1 + np.exp(-z))
return s
######################
def model(X_train, Y_train, X_test, Y_test, num_iterations=2000, learning_rate=0.5, print_cost=False):
w, b = initialize_with_zeros(X_train.shape[0])
parameters, grads, costs = optimize(w, b, X_train, Y_train, num_iterations, learning_rate, print_cost)
# 从字典“参数”中检索参数w和b
w, b = parameters["w"], parameters["b"]
# 预测测试/训练集的例子
Y_prediction_test = predict(w, b, X_test)
Y_prediction_train = predict(w, b, X_train)
# 打印训练后的准确性
print("训练集准确性：", format(100 - np.mean(np.abs(Y_prediction_train - Y_train)) * 100), "%")
print("测试集准确性：", format(100 - np.mean(np.abs(Y_prediction_test - Y_test)) * 100), "%")
d = {
"costs": costs,
"Y_prediction_test": Y_prediction_test,
"Y_prediciton_train": Y_prediction_train,
"w": w,
"b": b,
"learning_rate": learning_rate,
"num_iterations": num_iterations}
return d
#######################
def initialize_with_zeros(dim):
w = np.zeros(shape=(dim, 1))
b = 0
# 使用断言来确保我要的数据是正确的
assert (w.shape == (dim, 1)) # w的维度是(dim,1)
assert (isinstance(b, float) or isinstance(b, int)) # b的类型是float或者是int
return (w, b)
####################
def predict(w, b, X):
m = X.shape[1] # 图片的数量
Y_prediction = np.zeros((1, m))
w = w.reshape(X.shape[0], 1)
# 计预测猫在图片中出现的概率
A = sigmoid(np.dot(w.T, X) + b)
for i in range(A.shape[1]):
# 将概率a [0，i]转换为实际预测p [0，i]
Y_prediction[0, i] = 1 if A[0, i] > 0.5 else 0
# 使用断言
assert (Y_prediction.shape == (1, m))
return Y_prediction
###################
def propagate(w, b, X, Y):
m = X.shape[1]
# 正向传播
A = sigmoid(np.dot(w.T, X) + b) # 计算激活值，请参考公式2。
cost = (- 1 / m) * np.sum(Y * np.log(A) + (1 - Y) * (np.log(1 - A))) # 计算成本，请参考公式3和4。
# 反向传播
dw = (1 / m) * np.dot(X, (A - Y).T) # 请参考视频中的偏导公式。
db = (1 / m) * np.sum(A - Y) # 请参考视频中的偏导公式。
# 使用断言确保我的数据是正确的
assert (dw.shape == w.shape)
assert (db.dtype == float)
cost = np.squeeze(cost)
assert (cost.shape == ())
# 创建一个字典，把dw和db保存起来。
grads = {
"dw": dw,
"db": db
}
return (grads, cost)
###################
def optimize(w, b, X, Y, num_iterations, learning_rate, print_cost=False):
costs = []
for i in range(num_iterations):
grads, cost = propagate(w, b, X, Y)
dw = grads["dw"]
db = grads["db"]
w = w - learning_rate * dw
b = b - learning_rate * db
# 记录成本
if i % 100 == 0:
costs.append(cost)
# 打印成本数据
if (print_cost) and (i % 100 == 0):
print("迭代的次数: %i ， 误差值： %f" % (i, cost))
params = {
"w": w,
"b": b}
grads = {
"dw": dw,
"db": db}
return (params, grads, costs)
###################
###################
if __name__ == '__main__':
train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = load_dataset()
index = 25
# plt.imshow(train_set_x_orig[index])
# plt.show()
print("y=" + str(train_set_y[:,index]) + ", it's a " + classes[np.squeeze(train_set_y[:,index])].decode("utf-8") + "' picture")
m_train = train_set_y.shape[1] #训练集里图片的数量。
m_test = test_set_y.shape[1] #测试集里图片的数量。
num_px = train_set_x_orig.shape[1] #训练、测试集里面的图片的宽度和高度（均为64x64）。
#现在看一看我们加载的东西的具体情况
print ("训练集的数量: m_train = " + str(m_train))
print ("测试集的数量 : m_test = " + str(m_test))
print ("每张图片的宽/高 : num_px = " + str(num_px))
print ("每张图片的大小 : (" + str(num_px) + ", " + str(num_px) + ", 3)")
print ("训练集_图片的维数 : " + str(train_set_x_orig.shape))
print ("训练集_标签的维数 : " + str(train_set_y.shape))
print ("测试集_图片的维数: " + str(test_set_x_orig.shape))
print ("测试集_标签的维数: " + str(test_set_y.shape))
#X_flatten = X.reshape(X.shape [0]，-1).T ＃X.T是X的转置
#将训练集的维度降低并转置。
train_set_x_flatten = train_set_x_orig.reshape(train_set_x_orig.shape[0],-1).T
#将测试集的维度降低并转置。
test_set_x_flatten = test_set_x_orig.reshape(test_set_x_orig.shape[0], -1).T
print ("训练集降维最后的维度： " + str(train_set_x_flatten.shape))
print ("训练集_标签的维数 : " + str(train_set_y.shape))
print ("测试集降维之后的维度: " + str(test_set_x_flatten.shape))
print ("测试集_标签的维数 : " + str(test_set_y.shape))
#数据集的标准化
train_set_x = train_set_x_flatten / 255
test_set_x = test_set_x_flatten / 255
#测试sigmoid()
print ("sigmoid(0) = " + str(sigmoid(0)))
print ("sigmoid(9.2) = " + str(sigmoid(9.2)))
#测试一下propagate
#初始化一些参数
w, b, X, Y = np.array([[1], [2]]), 2, np.array([[1,2], [3,4]]), np.array([[1, 0]])
grads, cost = propagate(w, b, X, Y)
print ("dw = " + str(grads["dw"]))
print ("db = " + str(grads["db"]))
print ("cost = " + str(cost))
#测试optimize
w, b, X, Y = np.array([[1], [2]]), 2, np.array([[1,2], [3,4]]), np.array([[1, 0]])
params , grads , costs = optimize(w , b , X , Y , num_iterations=100 , learning_rate = 0.009 , print_cost = False)
print ("w = " + str(params["w"]))
print ("b = " + str(params["b"]))
print ("dw = " + str(grads["dw"]))
print ("db = " + str(grads["db"]))
#测试predict
w, b, X, Y = np.array([[1], [2]]), 2, np.array([[1,2], [3,4]]), np.array([[1, 0]])
print("predictions = " + str(predict(w, b, X)))
#这里加载的是真实的数据，请参见上面的代码部分。
d = model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations = 2000, learning_rate = 0.005, print_cost = True)
#绘制图
costs = np.squeeze(d['costs'])
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('iterations (per hundreds)')
plt.title("Learning rate =" + str(d["learning_rate"]))
plt.show()二、个人理解
对于这样的一个神经网络，我初步的理解是将识别图片的过程转化成了一个概率论上的似然函数，通过求取似然函数的极值来取得最优解(使用的方法为梯度下降法)。
三、lr_utils文件
有一个lr_utils文件，需要大家自己添加到工程目录下。
import numpy as np
import h5py
def load_dataset():
train_dataset = h5py.File('datasets/train_catvnoncat.h5', "r")
train_set_x_orig = np.array(train_dataset["train_set_x"][:]) # your train set features
train_set_y_orig = np.array(train_dataset["train_set_y"][:]) # your train set labels
test_dataset = h5py.File('datasets/test_catvnoncat.h5', "r")
test_set_x_orig = np.array(test_dataset["test_set_x"][:]) # your test set features
test_set_y_orig = np.array(test_dataset["test_set_y"][:]) # your test set labels
classes = np.array(test_dataset["list_classes"][:]) # the list of classes
train_set_y_orig = train_set_y_orig.reshape((1, train_set_y_orig.shape[0]))
test_set_y_orig = test_set_y_orig.reshape((1, test_set_y_orig.shape[0]))
return train_set_x_orig, train_set_y_orig, test_set_x_orig, test_set_y_orig, classes
本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
