lu_utils.py文件
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
assignmenet2_2
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
%matplotlib inline
# Loading the data (cat/non-cat)
train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = load_dataset()
# Example of a picture
index = 3
plt.imshow(train_set_x_orig[index])
print ("y = " + str(train_set_y[:, index]) + ", it's a '" + classes[np.squeeze(train_set_y[:, index])].decode("utf-8") + "' picture.")
# Find the values
m_train = train_set_x_orig.shape[0]
m_test = test_set_x_orig.shape[0]
num_px = train_set_x_orig.shape[1]
# Reshape the training and test examples
### START CODE HERE ### (≈ 2 lines of code)
'''
A trick when you want to flatten a matrix X of shape (a,b,c,d) to a matrix X_flatten of shape (b*c*d, a) is to use:
X_flatten = X.reshape(X.shape[0], -1).T # X.T is the transpose of X
每一列是一个图像的RGB颜色的数据
'''
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
# center and standardize your dataset
train_set_x = train_set_x_flatten/255.
test_set_x = test_set_x_flatten/255.
# GRADED FUNCTION: sigmoid
def sigmoid(z):
s = 1 / (1 + np.exp(-z))
return s
# GRADED FUNCTION: initialize_with_zeros
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))
return w, b
# GRADED FUNCTION: propagate 计算每一次梯度下降的dw,db
def propagate(w, b, X, Y):
m = X.shape[1]
z = np.dot(w.T , X) + b
A = sigmoid(z)
cost = -np.sum(Y * np.log(A) + (1-Y) * np.log(1-A)) / m
dz = A - Y
dw = np.dot(X , dz.T) / m
db = np.sum(dz) / m
assert(dw.shape == w.shape)
assert(db.dtype == float)
cost = np.squeeze(cost)
assert(cost.shape == ())
grads = {"dw": dw,
"db": db}
return grads, cost
# GRADED FUNCTION: optimize
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)
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
# GRADED FUNCTION: predict
def predict(w, b, 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[0,i] >= 0.5:
Y_prediction[0,i] = 1
else:
Y_prediction[0,i] = 0
assert(Y_prediction.shape == (1, m))
return Y_prediction
# GRADED FUNCTION: model整合以上函数
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]) # 每一个像素都配上一个参数theta
params, grads, costs = optimize(w, b, X_train, Y_train, num_iterations, learning_rate, print_cost)
w , b = params['w'], params['b']
Y_prediction_train = predict(w , b , X_train)
Y_prediction_test = predict(w , b , X_test)
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
# Run the following cell to train your model.
d = model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations = 2000, learning_rate = 0.005, print_cost = True)
# Example of a picture that was wrongly classified.
index = 40
plt.imshow(test_set_x[:,index].reshape((num_px, num_px, 3)))
print ("y = " + str(test_set_y[0,index]) + ", you predicted that it is a \"" + classes[int(d["Y_prediction_test"][0,index])].decode("utf-8") + "\" picture.")
# Plot learning curve (with costs)
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()
# Choice of learning rate
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()
## START CODE HERE ## (PUT YOUR IMAGE NAME)
my_image = 'my_image3.jpg'
## END CODE HERE ##
# We preprocess the image to fit your algorithm.
fname = "images/" + my_image
with Image.open(fname) as img:
# 调整图像大小
resized_img = img.resize((num_px, num_px), resample=Image.BILINEAR)
# 将 PIL 图像转换为 NumPy 数组,并从 HWC 转换为 CHW 格式(适用于某些深度学习框架)
image_array = np.array(resized_img).transpose((2, 0, 1))
# 重塑为 (1, num_px*num_px*3) 形状,并转置
my_image = image_array.reshape((1, num_px * num_px * 3)).T
my_predicted_image = predict(d["w"], d["b"], my_image)
plt.imshow(img)
print("y = " + str(np.squeeze(my_predicted_image)) + ", your algorithm predicts a \"" + classes[int(np.squeeze(my_predicted_image)),].decode("utf-8") + "\" picture.")
(每个像素的RGB参数都配上一个参数theta)非常简单的模型,存在过拟合、模型简单测试率低等问题。