作业
你需要记住的内容:
预处理数据集的常见步骤是:
- 找出数据的尺寸和维度(m_train,m_test,num_px等)(图片都是lenght,height,3)
- 重塑数据集,以使每个示例都是大小为(num_px \ num_px \ 3,1)的向量(就是利用reshape函数)
- “标准化”数据(这里就是简单的将每张图片除以255)
以下是logistic回归的代码,判断图片是否为猫
import numpy as np
import matplotlib.pyplot as plt
import h5py
import scipy
from PIL import Image
from scipy import ndimage
from lr_utils import load_dataset
def sigmoid(x):
return 1 / (1 + np.exp(-x))
def initialize_with_zeros(dim):
w = np.zeros((dim, 1))
b = 0
assert (w.shape == (dim, 1))
assert (isinstance(b, float) or isinstance(b, int))
# 断言用于判断是否为这个条件,不是的话就直接报错,是的话就继续执行
# 这里断言可有可无,保险起见而已
return w, b
# 实现函数propagate()来计算损失函数及其梯度。
def propagate(w, b, X, Y):
"""
Implement the cost function and its gradient for the propagation explained above
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)
Y -- true "label" vector (containing 0 if non-cat, 1 if cat) of size (1, number of examples)
"""
m = X.shape[1]
A = sigmoid(np.dot(w.T, X) + b) # compute activation
cost = -1 / m * np.sum(Y * np.log(A) + (1 - Y) * np.log(1 - A)) # compute cost
dw = 1 / m * np.dot(X, (A - Y).T)
db = 1 / m * np.sum(A - Y)
assert (dw.shape == w.shape)
assert (db.dtype == float)
cost = np.squeeze(cost) # 这句可要可不要
assert (cost.shape == ())
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
if i % 100 == 0:
costs.append(cost)
# Print the cost every 100 training examples
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
def predict(w, b, X):
m = X.shape[1]
Y_prediction = np.zeros((1, m))
w = w.reshape(X.shape[0], 1) # 这句其实没起作用 w还是原来的w
# Compute vector "A" predicting the probabilities of a cat being present in the picture
### START CODE HERE ### (≈ 1 line of code)
A = sigmoid(np.dot(w.T, X) + b)
### END CODE HERE ###
for i in range(A.shape[1]):
# Convert probabilities A[0,i] to actual predictions p[0,i]
### START CODE HERE ### (≈ 4 lines of code)
if A[0, i] <= 0.5:
Y_prediction[0, i] = 0
else:
Y_prediction[0, i] = 1
### END CODE HERE ###
assert (Y_prediction.shape == (1, m))
return Y_prediction
def model(X_train, Y_train, X_test, Y_test, num_iterations, learning_rate, print_cost):
w, b = initialize_with_zeros(X_train.shape[0])
# Gradient descent (≈ 1 line of code)
parameters, grads, costs = optimize(w, b, X_train, Y_train, num_iterations, learning_rate, print_cost)
# Retrieve parameters w and b from dictionary "parameters"
w = parameters["w"]
b = parameters["b"]
# Predict test/train set examples (≈ 2 lines of code)
Y_prediction_test = predict(w, b, X_test)
Y_prediction_train = predict(w, b, X_train)
### END CODE HERE ###
# Print train/test Errors
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
train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = load_dataset()
# index = 49
# plt.imshow(test_set_x_orig[index])
# plt.show()
# train_set_x_flatten = train_set_x_orig.reshape(64*64*3, 209) 等价于下方的
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
train_set_x = train_set_x_flatten/255.
test_set_x = test_set_x_flatten/255.
d = model(train_set_x, train_set_y, test_set_x, test_set_y, 2000, 0.005, True)