gradient_checking_funcyion.py
import numpy as np
import gc_utils
#一維線性
def forward_propagation(x,theta):
"""
實現圖中呈現的線性前向傳播(計算J)(J(theta)= theta * x)
參數:
x - 一個實值輸入
theta - 參數,也是一個實數返回:
J - 函數J的值,用公式J(theta)= theta * x計算
"""
J = np.dot(theta,x)
return J
def backward_propagation(x,theta):
"""
計算J相對於θ的導數。參數:
x - 一個實值輸入
theta - 參數,也是一個實數返回:
dtheta - 相對於θ的成本梯度
"""
dtheta = x
return dtheta
def gradient_check(x,theta,epsilon=1e-7):
"""實現圖中的反向傳播。
參數:
x - 一個實值輸入
theta - 參數,也是一個實數
epsilon - 使用公式(3)計算輸入的微小偏移以計算近似梯度返回:
近似梯度和後向傳播梯度之間的差異
"""#使用公式(3)的左側計算gradapprox。
thetaplus = theta + epsilon # Step 1
thetaminus = theta - epsilon # Step 2
J_plus = forward_propagation(x, thetaplus) # Step 3
J_minus = forward_propagation(x, thetaminus) # Step 4
gradapprox = (J_plus - J_minus) / (2 * epsilon) # Step 5
#檢查gradapprox是否足夠接近backward_propagation()的輸出
grad = backward_propagation(x, theta)numerator = np.linalg.norm(grad - gradapprox) # Step 1'
denominator = np.linalg.norm(grad) + np.linalg.norm(gradapprox) # Step 2'
difference = numerator / denominator # Step 3'if difference < 1e-7:
print("梯度檢查:梯度正常!")
else:
print("梯度檢查:梯度超出閾值!")return difference
#高維
def forward_propagation_n(X,Y,parameters):
"""
實現圖中的前向傳播(並計算成本)。
參數:
X - 訓練集爲m個例子
Y - m個示例的標籤
parameters - 包含參數“W1”,“b1”,“W2”,“b2”,“W3”,“b3”的python字典:
W1 - 權重矩陣,維度爲(5,4)
b1 - 偏向量,維度爲(5,1)
W2 - 權重矩陣,維度爲(3,5)
b2 - 偏向量,維度爲(3,1)
W3 - 權重矩陣,維度爲(1,3)
b3 - 偏向量,維度爲(1,1)
返回:
cost - 成本函數(logistic)
"""
m = X.shape[1]
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
W3 = parameters["W3"]
b3 = parameters["b3"]Z1 = np.dot(W1,X)+b1
A1 = gc_utils.relu(Z1)
Z2 = np.dot(W2,A1)+b2
A2 = gc_utils.relu(Z2)
Z3 = np.dot(W3, A2) + b3
A3 = gc_utils.sigmoid(Z3)# 計算成本
logprobs = np.multiply(-np.log(A3), Y) + np.multiply(-np.log(1 - A3), 1 - Y)
cost = (1 / m) * np.sum(logprobs)cache = (Z1, A1, W1, b1, Z2, A2, W2, b2, Z3, A3, W3, b3)
return cost, cache
def backward_propagation_n(X,Y,cache):
"""
實現圖中所示的反向傳播。參數:
X - 輸入數據點(輸入節點數量,1)
Y - 標籤
cache - 來自forward_propagation_n()的cache輸出返回:
gradients - 一個字典,其中包含與每個參數、激活和激活前變量相關的成本梯度。
"""
m = X.shape[1]
(Z1, A1, W1, b1, Z2, A2, W2, b2, Z3, A3, W3, b3) = cache
dZ3 = A3-Y
dW3 = 1./m * np.dot(dZ3,A2.T)
db3 = 1./m * np.sum(dZ3,axis=1,keepdims=True)dA2 = np.dot(W3.T,dZ3)
dZ2 = np.multiply(dA2,np.int64(A2>0))
dW2 = 1. / m * np.dot(dZ2, A1.T)
db2 = 1. / m * np.sum(dZ2, axis=1, keepdims=True)dA1 = np.dot(W2.T, dZ2)
dZ1 = np.multiply(dA1, np.int64(A1 > 0))
dW1 = 1. / m * np.dot(dZ1, X.T)
db1 = 1. / m * np.sum(dZ1, axis=1, keepdims=True)gradients = {"dZ3": dZ3, "dW3": dW3, "db3": db3,
"dA2": dA2, "dZ2": dZ2, "dW2": dW2, "db2": db2,
"dA1": dA1, "dZ1": dZ1, "dW1": dW1, "db1": db1}return gradients
def gradient_check_n(parameters,gradients,X,Y,epsilon=1e-7):
"""
檢查backward_propagation_n是否正確計算forward_propagation_n輸出的成本梯度參數:
parameters - 包含參數“W1”,“b1”,“W2”,“b2”,“W3”,“b3”的python字典:
grad_output_propagation_n的輸出包含與參數相關的成本梯度。
x - 輸入數據點,維度爲(輸入節點數量,1)
y - 標籤
epsilon - 計算輸入的微小偏移以計算近似梯度返回:
difference - 近似梯度和後向傳播梯度之間的差異
"""
#初始化參數
parameters_values,keys = gc_utils.dictionary_to_vector(parameters)
grad = gc_utils.gradients_to_vector(gradients)
num_parameters = parameters_values.shape[0]
J_plus = np.zeros((num_parameters,1))
J_minus = np.zeros((num_parameters,1))
gradapprox = np.zeros((num_parameters,1))for i in range(num_parameters):
# 計算J_plus [i]。輸入:“parameters_values,epsilon”。輸出=“J_plus [i]”
thetaplus = np.copy(parameters_values) # Step 1
thetaplus[i][0] = thetaplus[i][0] + epsilon # Step 2
J_plus[i], cache = forward_propagation_n(X, Y, gc_utils.vector_to_dictionary(thetaplus)) # Step 3 ,cache用不到
# 計算J_minus [i]。輸入:“parameters_values,epsilon”。輸出=“J_minus [i]”。
thetaminus = np.copy(parameters_values) # Step 1
thetaminus[i][0] = thetaminus[i][0] - epsilon # Step 2
J_minus[i], cache = forward_propagation_n(X, Y, gc_utils.vector_to_dictionary(thetaminus)) # Step 3 ,cache用不到# 計算gradapprox[i]
gradapprox[i] = (J_plus[i] - J_minus[i]) / (2 * epsilon)# 通過計算差異比較gradapprox和後向傳播梯度。
numerator = np.linalg.norm(grad - gradapprox) # Step 1'
denominator = np.linalg.norm(grad) + np.linalg.norm(gradapprox) # Step 2'
difference = numerator / denominator # Step 3'
if difference < 1e-7:
print("梯度檢查:梯度正常!"+str(difference))
else:
print("梯度檢查:梯度超出閾值!"+str(difference))return difference
gc_utils.py
import numpy as np import matplotlib.pyplot as plt def sigmoid(x): """ Compute the sigmoid of x Arguments: x -- A scalar or numpy array of any size. Return: s -- sigmoid(x) """ s = 1/(1+np.exp(-x)) return s def relu(x): """ Compute the relu of x Arguments: x -- A scalar or numpy array of any size. Return: s -- relu(x) """ s = np.maximum(0,x) return s def dictionary_to_vector(parameters): """ Roll all our parameters dictionary into a single vector satisfying our specific required shape. """ keys = [] count = 0 for key in ["W1", "b1", "W2", "b2", "W3", "b3"]: # flatten parameter new_vector = np.reshape(parameters[key], (-1,1)) keys = keys + [key]*new_vector.shape[0] if count == 0: theta = new_vector else: theta = np.concatenate((theta, new_vector), axis=0) count = count + 1 return theta, keys def vector_to_dictionary(theta): """ Unroll all our parameters dictionary from a single vector satisfying our specific required shape. """ parameters = {} parameters["W1"] = theta[:20].reshape((5,4)) parameters["b1"] = theta[20:25].reshape((5,1)) parameters["W2"] = theta[25:40].reshape((3,5)) parameters["b2"] = theta[40:43].reshape((3,1)) parameters["W3"] = theta[43:46].reshape((1,3)) parameters["b3"] = theta[46:47].reshape((1,1)) return parameters def gradients_to_vector(gradients): """ Roll all our gradients dictionary into a single vector satisfying our specific required shape. """ count = 0 for key in ["dW1", "db1", "dW2", "db2", "dW3", "db3"]: # flatten parameter new_vector = np.reshape(gradients[key], (-1,1)) if count == 0: theta = new_vector else: theta = np.concatenate((theta, new_vector), axis=0) count = count + 1 return thetatestCases.py
import numpy as np def gradient_check_n_test_case(): np.random.seed(1) x = np.random.randn(4, 3) y = np.array([1, 1, 0]) W1 = np.random.randn(5, 4) b1 = np.random.randn(5, 1) W2 = np.random.randn(3, 5) b2 = np.random.randn(3, 1) W3 = np.random.randn(1, 3) b3 = np.random.randn(1, 1) parameters = {"W1": W1, "b1": b1, "W2": W2, "b2": b2, "W3": W3, "b3": b3} return x, y, parametersgradient_checking.py
import testCases from gradient_checking_function import forward_propagation,backward_propagation,gradient_check from gradient_checking_function import forward_propagation_n,backward_propagation_n,gradient_check_n #測試gradient_check print("-----------------測試gradient_check-----------------") x, theta = 2, 4 difference = gradient_check(x, theta) print("difference = " + str(difference)) #test 高維 print("-----------------測試gradient_check_n-----------------") X, Y, parameters = testCases.gradient_check_n_test_case() cost, cache = forward_propagation_n(X, Y, parameters) gradients = backward_propagation_n(X, Y, cache) difference = gradient_check_n(parameters, gradients, X, Y)