链接:https://pan.baidu.com/s/1uRw1aQQww-ZD1UNbN1Y9fA
提取码:cwlh
源代码:
import numpy as np
import h5py
import matplotlib.pyplot as plt
import testCases
from dnn_utils import sigmoid, sigmoid_backward, relu, relu_backward # 参见资料包
import lr_utils
np.random.seed(1)
# 初始化两层参数
def initialize_parameters(n_x, n_h, n_y):
W1 = np.random.randn(n_h, n_x) * 0.01
b1 = np.zeros((n_h, 1))
W2 = np.random.randn(n_y, n_h) * 0.01
b2 = np.zeros((n_y, 1))
assert (W1.shape == (n_h, n_x))
assert (b1.shape == (n_h, 1))
assert (W2.shape == (n_y, n_h))
assert (b2.shape == (n_y, 1))
parameters = {
'W1': W1,
'W2': W2,
'b1': b1,
'b2': b2
}
return parameters
# 初始化多层网络参数
def initialize_parameters_deep(layers_dim):
np.random.seed(3)
L = len(layers_dim)
parameters = {}
for l in range(1, L):
parameters['W' + str(l)] = np.random.randn(layers_dim[l], layers_dim[l - 1]) / np.sqrt(layers_dim[l - 1])
parameters['b' + str(l)] = np.zeros((layers_dim[l], 1))
assert (parameters['W' + str(l)].shape == (layers_dim[l], layers_dim[l - 1]))
assert (parameters['b' + str(l)].shape == (layers_dim[l], 1))
return parameters
# 前向传播线性部分
def linear_forward(A, W, b):
Z = np.dot(W, A) + b
assert (Z.shape == (W.shape[0], A.shape[1]))
cache = (A, W, b)
return (Z, cache)
# 前向激活部分
def linear_activation_forward(A_prev, W, b, activation):
"""
:param A_prev: 上一层的激活值
"""
if activation == 'sigmoid':
Z, linear_cache = linear_forward(A_prev, W, b)
A, activation_cache = sigmoid(Z)
elif activation == 'relu':
Z, linear_cache = linear_forward(A_prev, W, b)
A, activation_cache = relu(Z)
assert (A.shape == (W.shape[0], A_prev.shape[1]))
cache = (linear_cache, activation_cache)
return A, cache
# 多层网络的前向
def L_model_forward(X, parameters):
caches = []
L = len(parameters) // 2
A = X
for l in range(1, L):
A_prev = A
A, cache = linear_activation_forward(A_prev, parameters['W' + str(l)], parameters['b' + str(l)], 'relu')
caches.append(cache)
AL, cache = linear_activation_forward(A, parameters['W' + str(L)], parameters['b' + str(L)], 'sigmoid')
caches.append(cache)
assert (AL.shape == (1, X.shape[1]))
return AL, caches
# 计算成本
def compute_cost(AL, Y):
m = Y.shape[1]
cost = -np.sum(np.multiply(Y, np.log(AL)) + np.multiply(1 - Y, np.log(1 - AL))) / m
cost = np.squeeze(cost)
assert (cost.shape == ())
return cost
# 后向传播,第L层的线性部分
def linear_backward(dZ, cache):
A_prev, W, b = cache
m = A_prev.shape[1]
dW = np.dot(dZ, A_prev.T) / m
db = np.sum(dZ, axis=1, keepdims=True) / m
dA_prev = np.dot(W.T, dZ)
assert (dW.shape == (W.shape))
assert (db.shape == (b.shape))
assert (dA_prev.shape == (A_prev.shape))
return dA_prev, dW, db
# 后向激活
def linear_activation_backward(dA, cache, activation):
linear_cache, activation_cache = cache
if activation == "relu":
dZ = relu_backward(dA, activation_cache)
dA_prev, dW, db = linear_backward(dZ, linear_cache)
elif activation == 'sigmoid':
dZ = sigmoid_backward(dA, activation_cache)
dA_prev, dW, db = linear_backward(dZ, linear_cache)
return dA_prev, dW, db
# 多层网络后向传播
def L_model_backward(AL, Y, caches):
grads={}
L=len(caches)
Y=Y.reshape(AL.shape)
dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL))
current_cache=caches[L-1]
grads['dA'+str(L)],grads['dW'+str(L)],grads['db'+str(L)]=linear_activation_backward(dAL, current_cache, 'sigmoid')
for l in reversed(range(L-1)):
current_cache=caches[l]
dA_prev_temp,dW_temp,db_temp=linear_activation_backward(grads['dA'+str(l+2)],current_cache,'relu')
grads['dA'+str(l+1)]=dA_prev_temp
grads['dW'+str(l+1)]=dW_temp
grads['db'+str(l+1)]=db_temp
return grads
#更新参数
def update_parameters(parameters, grads,learning_rate):
L=len(parameters)//2
for l in range(L):
parameters['W'+str(l+1)]=parameters['W'+str(l+1)]-learning_rate*grads['dW'+str(l+1)]
parameters['b' + str(l+1)] = parameters['b' + str(l+1)] - learning_rate * grads['db' + str(l+1)]
return parameters
#搭建两层神经网络
def two_layer_model(X,Y,layers_dims,learning_rate=0.0075,num_iterations=3000,print_cost=False,isPlot=True):
"""
:param isPlot: 是否绘制误差图像
"""
np.random.seed(1)
grads={}
costs=[]
(n_x,n_h,n_y)=layers_dims
#初始化参数
parameters=initialize_parameters(n_x, n_h, n_y)
W1=parameters['W1']
b1=parameters['b1']
W2=parameters['W2']
b2=parameters['b2']
for i in range(0,num_iterations):
A1,cache1=linear_activation_forward(X, W1, b1, 'relu')
A2,cache2=linear_activation_forward(A1, W2, b2, 'sigmoid')#前向传播
#计算成本
cost=compute_cost(A2, Y)
#后向传播
dA2 = - (np.divide(Y, A2) - np.divide(1 - Y, 1 - A2))
dA1, dW2, db2 = linear_activation_backward(dA2, cache2, "sigmoid")
dA0, dW1, db1 = linear_activation_backward(dA1, cache1, "relu")
grads["dW1"] = dW1
grads["db1"] = db1
grads["dW2"] = dW2
grads["db2"] = db2
#更新参数
parameters = update_parameters(parameters, grads, learning_rate)
W1=parameters['W1']
b1=parameters['b1']
W2=parameters['W2']
b2=parameters['b2']
#打印
if i%100==0:
costs.append(cost)
if print_cost:
print('第',i,'次迭代,成本为:',np.squeeze(cost))
if isPlot:
plt.plot(np.squeeze(costs))
plt.ylabel('cost')
plt.xlabel('iterations (per tens)')
plt.title("Learning rate =" + str(learning_rate))
plt.show()
return parameters
#预测
def predict(X, y, parameters):
m = X.shape[1]
p = np.zeros((1,m))
probas, caches = L_model_forward(X, parameters)
for i in range(0, probas.shape[1]):
if probas[0,i] > 0.5:
p[0,i] = 1
else:
p[0,i] = 0
print("准确度为: " + str(float(np.sum((p == y))/m)))
return p
# train_set_x_orig , train_set_y , test_set_x_orig , test_set_y , classes = lr_utils.load_dataset()
# train_x_flatten = train_set_x_orig.reshape(train_set_x_orig.shape[0], -1).T
# test_x_flatten = test_set_x_orig.reshape(test_set_x_orig.shape[0], -1).T
# train_x = train_x_flatten / 255
# train_y = train_set_y
# test_x = test_x_flatten / 255
# test_y = test_set_y
# n_x = 12288
# n_h = 7
# n_y = 1
# layers_dims = (n_x,n_h,n_y)
# parameters = two_layer_model(train_x, train_set_y, layers_dims = (n_x, n_h, n_y), num_iterations = 2500, print_cost=True,isPlot=True)
# predictions_train = predict(train_x, train_y, parameters) #训练集
# predictions_test = predict(test_x, test_y, parameters) #测试集
def L_layer_model(X, Y, layers_dims, learning_rate=0.0075, num_iterations=3000, print_cost=False,isPlot=True):
np.random.seed(1)
costs = []
parameters = initialize_parameters_deep(layers_dims)
for i in range(0,num_iterations):
AL , caches = L_model_forward(X,parameters)
cost = compute_cost(AL,Y)
grads = L_model_backward(AL,Y,caches)
parameters = update_parameters(parameters,grads,learning_rate)
#打印成本值,如果print_cost=False则忽略
if i % 100 == 0:
#记录成本
costs.append(cost)
#是否打印成本值
if print_cost:
print("第", i ,"次迭代,成本值为:" ,np.squeeze(cost))
#迭代完成,根据条件绘制图
if isPlot:
plt.plot(np.squeeze(costs))
plt.ylabel('cost')
plt.xlabel('iterations (per tens)')
plt.title("Learning rate =" + str(learning_rate))
plt.show()
return parameters
train_set_x_orig , train_set_y , test_set_x_orig , test_set_y , classes = lr_utils.load_dataset()
train_x_flatten = train_set_x_orig.reshape(train_set_x_orig.shape[0], -1).T
test_x_flatten = test_set_x_orig.reshape(test_set_x_orig.shape[0], -1).T
train_x = train_x_flatten / 255
train_y = train_set_y
test_x = test_x_flatten / 255
test_y = test_set_y
layers_dims = [12288, 20, 7, 5, 1] # 5-layer model
parameters = L_layer_model(train_x, train_y, layers_dims, num_iterations = 2500, print_cost = True,isPlot=True)
pred_train = predict(train_x, train_y, parameters) #训练集
pred_test = predict(test_x, test_y, parameters) #测试集
参考:https://blog.csdn.net/u013733326/article/details/79827273