鏈接:https://pan.baidu.com/s/1ENynOEU33LFsoEln3HeZGw
提取碼:0spc
本次作業是完成 一個“識別貓”的神經網絡網絡搭建。
代碼:
import numpy as np
import matplotlib.pyplot as plt
from lr_utils import load_dataset
train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = load_dataset()
m_train = train_set_y.shape[1]
m_test = test_set_y.shape[1]
num_px = train_set_x_orig[1]
# 降維
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
# 標準化數據,讓數據在【0,1】之間
train_set_x = train_set_x_flatten / 255
test_set_x = test_set_x_flatten / 255
# 建立神經網絡的主要步驟是:
# 1. 定義模型結構(例如輸入特徵的數量)
# 2. 初始化模型的參數
# 3. 循環:
# 3.1 計算當前損失(正向傳播)
# 3.2 計算當前梯度(反向傳播)
# 3.3 更新參數(梯度下降)
def sigmoid(z):
return 1 / (1 + np.exp(-z))
# 初始化w,b
def iniialize_with_zeros(dim):
"""
:param dim: 所要的w的維度
:return: w,b
"""
b = 0
w = np.zeros(shape=(dim, 1))
# 斷言保證格式的正確
assert (w.shape == (dim, 1))
assert (isinstance(b, float) or isinstance(b, int))
return (w, b)
def propagate(w, b, X, Y):
"""
:param w: 權重
:param b: 偏差
:param X: 訓練集
:param Y: 標籤
:return: cost,w,b
"""
m = X.shape[1]
# 正向傳播
A = sigmoid(np.dot(w.T, X) + b)
cost = -np.sum(Y * np.log(A) + (1 - Y) * np.log(1 - A)) / m
# 反向傳播
dw = np.dot(X, (A - Y).T) / m
db = np.sum(A - Y) / m
assert (dw.shape == w.shape)
assert (db.dtype == float)
cost = np.squeeze(cost)
assert (cost.shape == ())
# 創建一個字典保存w,b
grads = {
'dw': dw,
'db': db
}
return (grads, cost)
def optimize(w, b, X, Y, num_iterations, learning_rate, print_cost=False):
"""
此函數通過運行梯度下降算法來優化w和b
:param X:輸入的訓練集
:param Y:標籤
:param w:權重
:param b:偏差
:param num_iterations:迭代次數
:param learning_rate:學習率
:param print_cost:打印時間
:return:w,b,dw,db
costs:優化期間計算的所有成本列表,將用於繪製學習曲線
"""
costs = []
for i in range(num_iterations):
grads, cost = propagate(w, b, X, Y)
dw = grads['dw']
db = grads['db']
# 更新參數
w = w - learning_rate * dw
b = b - learning_rate * db
# 記錄成本
if i % 100 == 0:
costs.append(cost)
if (print_cost) and (i % 100 == 0):
print("迭代的次數: %i , 誤差值: %f" % (i, cost))
params = {
'w': w,
'b': b
}
grads = {
'dw': dw,
'db': db
}
return (params, grads, costs)
def predict(w, b, X):
"""
:param w:權重
:param b:偏差
:param X:訓練集
:return:Y_prediction - 包含X中所有圖片的所有預測【0 | 1】的一個numpy數組(向量)
"""
m = X.shape[1]
w = w.reshape(X.shape[0], 1)
Y_prediction = np.zeros((1, m))
# 預測貓在圖像中出現的概率
A = sigmoid(np.dot(w.T, X) + b)
for i in range(A.shape[1]):
Y_prediction[0, i] = 1 if A[0, i] > 0.5 else 0
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):
"""
:param X_train:訓練集
:param Y_train:訓練集標籤
:param X_test:測試集
:param Y_test:測試集標籤
:param num_iterations:迭代次數
:param learning_rate:學習率
:param print_cost:是否打印
:return:有關於所有信息的字典
"""
w, b = iniialize_with_zeros(X_train.shape[0])
params, grads, costs=optimize(w,b,X_train,Y_train,num_iterations,learning_rate,print_cost)
#檢索w,b
w=params['w']
b=params['b']
#預測訓練集和測試集
Y_prediction_train=predict(w,b,X_train)
Y_prediction_test=predict(w,b,X_test)
#打印訓練後的準確性
print("訓練集準確性:", format(100 - np.mean(np.abs(Y_prediction_train - Y_train)) * 100), "%")
print("測試集準確性:", format(100 - np.mean(np.abs(Y_prediction_test - Y_test)) * 100), "%")
d={
'costs':costs,
'Y_prediction_train':Y_prediction_train,
'Y_prediction_test':Y_prediction_test,
'w':w,
'b':b,
'learning_rate':learning_rate,
'num_iterations':num_iterations
}
return d
d = model(train_set_x, train_set_y, test_set_x, test_set_y, num_iterations = 2000, learning_rate = 0.005, print_cost = True)
參考網址:https://blog.csdn.net/u013733326/article/details/79827273