用pycharm进行编程实现的,具体细节可参考:
https://blog.csdn.net/qq_34290470/article/details/99849514
百度云pycharm项目源码:https://pan.baidu.com/s/12q_Er1vJpeo-O8h_KQYgCQ
完整python代码:
import numpy as np
import matplotlib.pyplot as plt
import h5py
def load_dataset():
train_dataset = h5py.File('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('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
index=25
train_set_x_orig , train_set_y , test_set_x_orig , test_set_y , classes = load_dataset() # 加载数据集
plt.imshow(train_set_x_orig[index]) # 查看训练集中的图片
plt.show()
# 打印出当前的训练标签值
# train_set_y是二维数组,使用np.squeeze的目的是压缩维度,即去掉shape中的1
# classe[0]='non-cat',classes[1]='cat'
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_x_orig.shape[0] # 训练集内的图片数量
m_test=test_set_x_orig.shape[0] # 测试集内的图片数量
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)
print("训练集中的数量:m_train=",m_train)
print("测试集中的数量:m_test=",m_test)
print("每张图片的宽/高:num_px=",num_px)
print("每张图片的大小:",train_set_x_orig[0].shape)
print("训练集_图片的维数:",train_set_x_orig.shape)
print("训练集_标签的维数: ",train_set_y.shape)
print("测试集_图片的维数:",test_set_x_orig.shape)
print("测试集_标签的维数:",test_set_y.shape)
# 向量化
# 每张图片的维度是(64,64,3),我们需要将维度降为(64x64x3,1);因此每列代表一张平坦的图片
# 将训练集和测试集都转化为如上形式
train_set_x_flatten=train_set_x_orig.reshape(train_set_x_orig.shape[0],-1).T
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))
# 数据标准化,由于RGB实际是值为0到255的三个向量。因此数据直接除以255,就可以将值缩放到0到1之间
train_set_x=train_set_x_flatten/255
test_set_x=test_set_x_flatten/255
# sigmoid函数
def sigmoid(z):
return 1 / (1 + np.exp(-z))
# 初始化参数
def initialize_with_zeros(dim):
'''
此函数为w创建一个维度为(dim,1)的向量,并将b初始化为0
参数
dim - w的矢量大小
返回
w - 维度为(dim,1)的初始化向量(对应权重)
b - 初始化标量(对应偏差)
'''
w = np.zeros((dim, 1))
b = 0
# 利用断言来确保使用数据的正确
assert (w.shape == (dim, 1))
assert (isinstance(b, int) or isinstance(b, float))
return (w, b)
def propagate(w, b, X, Y):
'''
实现前向和后向传播的成本函数及其梯度
参数
w - 权重,维度(num_p * num_px * 3,1)
b - 偏差,标量
X - 训练集,维度(num_p * num_px * 3,m_train)
Y - 真实标签,维度(1,m_train)
返回
cost- 逻辑回归的负对数似然成本
dw - 相对于w的损失梯度,维度与w相同
db - 相对于b的损失梯度,维度与b相同
'''
m = X.shape[1]
# 正向传播
A = sigmoid(np.dot(w.T, X) + b)
cost = (-1 / m) * np.sum((1 - Y) * np.log(1 - A) + Y * np.log(A))
cost = np.squeeze(cost)
# 反向传播
dw = (1 / m) * np.dot(X, (A - Y).T)
db = (1 / m) * np.sum(A - Y)
# 使用断言确保数据的准确性
assert (dw.shape == w.shape)
assert (db.dtype == float)
# 创建一个字典存储dw和db
grads = {
'dw': dw,
'db': db
}
return (grads, cost)
def optimize(w, b, X, Y, num_iterations, learning_rate, print_cost):
'''此函数通过运行梯度下降算法来优化w和b
参数:
w - 权重,大小不等的数组(num_px * num_px * 3,1)
b - 偏差,一个标量
X - 维度为(num_px * num_px * 3,训练数据的数量)的数组。
Y - 真正的“标签”矢量(如果非猫则为0,如果是猫则为1),矩阵维度为(1,训练数据的数量)
num_iterations - 优化循环的迭代次数
learning_rate - 梯度下降更新规则的学习率
print_cost - 每100步打印一次损失值
返回:
params - 包含权重w和偏差b的字典
grads - 包含权重和偏差相对于成本函数的梯度的字典
成本 - 优化期间计算的所有成本列表,将用于绘制学习曲线。'''
costs = [] # 用于存储每一百次迭代的误差
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
# 可以选择每迭代一百次就打印一次误差
if i % 100 == 0:
costs.append(cost)
if (print_cost) and (i % 100 == 0):
print("迭代次数:", i, "误差:", cost)
params = {
"w": w,
"b": b
}
grads = {
'dw': dw,
'db': db
}
return (params, grads, costs)
def predict(w, b, X):
'''
使用学习逻辑回归参数logistic (w,b)预测标签是0还是1,
参数:
w - 权重,大小不等的数组(num_px * num_px * 3,1)
b - 偏差,一个标量
X - 维度为(num_px * num_px * 3,训练数据的数量)的数据
返回:
Y_prediction - 包含X中所有图片的所有预测【0 | 1】的一个numpy数组(向量)'''
m = X.shape[1]
Y_prediction = np.zeros((1, m)) # 用于存储预测值
w = w.reshape(X.shape[0], 1)
A = sigmoid(np.dot(w.T, X) + b) # 预测猫在图片中实际出现的概率
for i in range(A.shape[1]):
Y_prediction[0, i] = 1 if A[0, i] > 0.5 else 0 # 将概率转化为实际值
assert (Y_prediction.shape == (1, m))
return Y_prediction
def model(X_train, Y_train, X_test, Y_test, num_iterations=2000, learning_rate=0.5, print_cost=False):
"""
通过调用之前实现的函数来构建逻辑回归模型
参数:
X_train - numpy的数组,维度为(num_px * num_px * 3,m_train)的训练集
Y_train - numpy的数组,维度为(1,m_train)(矢量)的训练标签集
X_test - numpy的数组,维度为(num_px * num_px * 3,m_test)的测试集
Y_test - numpy的数组,维度为(1,m_test)的(向量)的测试标签集
num_iterations - 表示用于优化参数的迭代次数的超参数
learning_rate - 表示optimize()更新规则中使用的学习速率的超参数
print_cost - 设置为true以每100次迭代打印成本
返回:
d - 包含有关模型信息的字典。
"""
w, b = initialize_with_zeros(X_train.shape[0]) # 初始化参数
paramters, grads, costs = optimize(w, b, X_train, Y_train, num_iterations, learning_rate, print_cost)
w, b = paramters['w'], paramters['b']
Y_prediction_train = predict(w, b, X_train)
Y_prediction_test = predict(w, b, X_test)
print("测试集的准确性:", format(100 - np.mean(np.abs(Y_prediction_test - Y_test))), "%")
print("训练集的准确性:", format(100 - np.mean(np.abs(Y_prediction_train - Y_train))), "%")
d = {
"costs": costs,
"Y_prediction_test": Y_prediction_test,
"Y_prediction_train": Y_prediction_train,
"w": w,
"b": b,
"learning_rate": learning_rate,
"num_iterations": num_iterations,
}
return d
# 测试一下训练结果
d=model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations = 2000, learning_rate = 0.005, print_cost = True)
# 可视化
costs=d['costs']
plt.plot(costs)
plt.title("Learning rate = 0.005")
plt.xlabel("iterations (per hundreds)")
plt.ylabel("Cost")
plt.show()
learning_rates = [0.01, 0.001, 0.0001]
models = {}
for i in learning_rates:
print ("learning rate is: " + str(i))
models[str(i)] = model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations = 1500, learning_rate = i, print_cost = False)
print ('\n' + "-------------------------------------------------------" + '\n')
for i in learning_rates:
plt.plot(np.squeeze(models[str(i)]["costs"]), label= str(models[str(i)]["learning_rate"]))
plt.ylabel('cost')
plt.xlabel('iterations')
legend = plt.legend(loc='upper center', shadow=True)
frame = legend.get_frame()
frame.set_facecolor('0.90')
plt.show()