import numpy as np
import matplotlib.pyplot as plt
import h5py
import scipy
from PIL import Image
from scipy import ndimage
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
# sigmoid函数
def sigmoid(z):
return 1 / (1 + np.exp(-z))
# 参数初始化函数
def initialize_with_zeros(dim):
w = np.zeros((dim, 1)) # 权重
b = 0 # 偏置
assert (w.shape == (dim, 1))
assert (isinstance(b, float) or isinstance(b, int))
return w, b
# 反向、前向传播函数
def propagate(w, b, X, Y):
"""
w -- weights, a numpy array of size (num_px * num_px * 3, 1)
b -- bias, a scalar
X -- data of size (num_px * num_px * 3, number of examples)
Y -- true "label" vector (containing 0 if non-cat, 1 if cat) of size (1, number of examples)
Return:
cost -- negative log-likelihood cost for logistic regression
dw -- gradient of the loss with respect to w, thus same shape as w
db -- gradient of the loss with respect to b, thus same shape as b
"""
m = X.shape[1] # 样本数目
A = sigmoid(np.dot(w.T, X) + b) # 激活函数
cost = -np.sum(np.dot(Y, np.log(A).T) + np.dot((1 - Y), np.log(1 - A).T)) / m # 计算cost
dw = np.dot(X, (A - Y).T) / m # 计算w的梯度
db = np.sum(A - Y) / m # 计算b的梯度
assert (dw.shape == w.shape)
assert (db.dtype == float)
cost = np.squeeze(cost)
assert (cost.shape == ())
grads = {"dw": dw, "db": db}
return grads, cost
# 最优化函数
def optimize(w, b, X, Y, num_iterations, learning_rate, print_cost=False):
"""
This function optimizes w and b by running a gradient descent algorithm
Arguments:
w -- weights, a numpy array of size (num_px * num_px * 3, 1)
b -- bias, a scalar
X -- data of shape (num_px * num_px * 3, number of examples)
Y -- true "label" vector (containing 0 if non-cat, 1 if cat), of shape (1, number of examples)
num_iterations -- number of iterations of the optimization loop
learning_rate -- learning rate of the gradient descent update rule
print_cost -- True to print the loss every 100 steps
Returns:
params -- dictionary containing the weights w and bias b
grads -- dictionary containing the gradients of the weights and bias with respect to the cost function
costs -- list of all the costs computed during the optimization, this will be used to plot the learning curve.
"""
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 # 更新权重
b = b - learning_rate * db # 更新偏置
if i % 100 == 0:
costs.append(cost)
if print_cost and i % 100 == 0:
print("Cost after iteration %i: %f" % (i, cost))
params = {"w": w, "b": b}
grads = {"dw": dw, "db": db}
return params, grads, costs
# 预测函数
def predict(w, b, X):
'''
Predict whether the label is 0 or 1 using learned logistic regression parameters (w, b)
Arguments:
w -- weights, a numpy array of size (num_px * num_px * 3, 1)
b -- bias, a scalar
X -- data of size (num_px * num_px * 3, number of examples)
Returns:
Y_prediction -- a numpy array (vector) containing all predictions (0/1) for the examples in X
'''
m = X.shape[1]
Y_prediction = np.zeros((1, m))
w = w.reshape(X.shape[0], 1)
A = sigmoid(np.dot(w.T, X) + b)
for i in range(A.shape[1]):
if A[:, i] > 0.5:
Y_prediction[:, i] = 1
else:
Y_prediction[:, i] = 0
assert (Y_prediction.shape == (1, m))
return Y_prediction
# 模型打包
def model(X_train, Y_train, X_test, Y_test, num_iterations=2000, learning_rate=0.5, print_cost=False):
"""
Builds the logistic regression model by calling the function you've implemented previously
Arguments:
X_train -- training set represented by a numpy array of shape (num_px * num_px * 3, m_train)
Y_train -- training labels represented by a numpy array (vector) of shape (1, m_train)
X_test -- test set represented by a numpy array of shape (num_px * num_px * 3, m_test)
Y_test -- test labels represented by a numpy array (vector) of shape (1, m_test)
num_iterations -- hyperparameter representing the number of iterations to optimize the parameters
learning_rate -- hyperparameter representing the learning rate used in the update rule of optimize()
print_cost -- Set to true to print the cost every 100 iterations
Returns:
d -- dictionary containing information about the model.
"""
w, b = initialize_with_zeros(64 * 64 * 3) # 参数初始化
parameters, grads, costs = optimize(w, b, X_train, Y_train, num_iterations, learning_rate, print_cost=False)
w = parameters["w"]
b = parameters["b"]
Y_prediction_test = predict(w, b, X_test)
Y_prediction_train = predict(w, b, X_train)
print("train accuracy: {} %".format(100 - np.mean(np.abs(Y_prediction_train - Y_train)) * 100))
print("test accuracy: {} %".format(100 - np.mean(np.abs(Y_prediction_test - Y_test)) * 100))
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
# 载入数据,处理数据
train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = load_dataset()
m_train = train_set_x_orig.shape[0] # 训练样本数目
m_test = test_set_x_orig.shape[0] # 测试样本数目
num_px = train_set_x_orig.shape[1] # 图像的高度(高度=宽度)
# 图片为彩色三通道,将三通道像素展开成1维
train_set_x_flatten = train_set_x_orig.reshape(m_train, -1).T
test_set_x_flatten = test_set_x_orig.reshape(m_test, -1).T
# 标准化数据
train_set_x = train_set_x_flatten/255.
test_set_x = test_set_x_flatten/255.
#训练并预测 一种学习率下的学习效果
d = model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations = 2000, learning_rate = 0.005, print_cost = True)
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()
# 训练并预测 多种学习率下的学习效果
# 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()
单学习率:
train accuracy: 99.04306220095694 %
test accuracy: 70.0 %
多学习率:
learning rate is: 0.01
train accuracy: 99.52153110047847 %
test accuracy: 68.0 %
-------------------------------------------------------
learning rate is: 0.001
train accuracy: 88.99521531100478 %
test accuracy: 64.0 %
-------------------------------------------------------
learning rate is: 0.0001
train accuracy: 68.42105263157895 %
test accuracy: 36.0 %
-------------------------------------------------------