Deep Neural Network (Tensorflow)
Deep Neural Network (Tensorflow)
仅用于自己学习使用
依赖的库
import numpy as np
import h5py
from matplotlib import pyplot as plt
import tensorflow as tf
from tensorflow.python.framework import ops
import tf_utils
import time
import matplotlib.pyplot as plt # plt 用于显示图片
import matplotlib.image as mpimg # mpimg 用于读取图片
import numpy as np
创建placeholders
def create_placeholders(n_x,n_y):
X = tf.placeholder(tf.float32, [n_x, None], name="X")
Y = tf.placeholder(tf.float32, [n_y, None], name="Y")
return X, Y
初始化参数
def initialize_parameters_deep(layers_dims):
tf.set_random_seed(1) #指定随机种子
# np.random.seed(3)
parameters = {}
L = len(layers_dims)
for l in range(1,L):
parameters["W" + str(l)] = tf.get_variable("W" + str(l),[layers_dims[l], layers_dims[l - 1]],initializer=tf.contrib.layers.xavier_initializer(seed=1))
parameters["b" + str(l)] = tf.get_variable("b" + str(l),[layers_dims[l], 1],initializer=tf.zeros_initializer())
return parameters
前向传播
def linear_activation_forward(A_prev,W,b,activation):
Z = tf.matmul(W,A_prev)+b # np.dot(W,A_prev) + b
if activation == "sigmoid":
A= tf.nn.sigmoid(Z)
elif activation == "relu":
A = tf.nn.relu(Z)
# assert(A.shape == (W.shape[0],A_prev.shape[1]))
cache = (A_prev, W, b,Z) # (A_prev, W, b,Z)
return A,cache
def L_model_forward(X,parameters):
caches = [] #[(X, W1, b1,Z1),(A1, W2, b2,Z2).....]
A = X
L = len(parameters) // 2
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)
ZL = tf.matmul(parameters['W' + str(L)],A)+parameters['b' + str(L)]
AL, cache = linear_activation_forward(A, parameters['W' + str(L)], parameters['b' + str(L)], "sigmoid")
caches.append(cache)
return ZL
成本函数
def compute_cost(ZL,Y):
logits = tf.transpose(ZL) #转置
labels = tf.transpose(Y) #转置
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits,labels=labels))
return cost
多层神经网络
def L_layer_model(X_train, Y_train,X_test,Y_test, layers_dims, learning_rate=0.0001, num_iterations=1500, minibatch_size=32,print_cost=True,is_Plot=True):
ops.reset_default_graph() #能够重新运行模型而不覆盖tf变量
tf.set_random_seed(1)
seed = 3
(n_x , m) = X_train.shape #获取输入节点数量和样本数
n_y = Y_train.shape[0] #获取输出节点数量
costs = [] #成本集
#给X和Y创建placeholder
X,Y = create_placeholders(n_x,n_y)
#初始化参数
parameters =initialize_parameters_deep(layers_dims)
ZL = L_model_forward(X,parameters)
cost = compute_cost(ZL,Y)
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for epoch in range(num_iterations):
epoch_cost =0
num_minibatches = int (m / minibatch_size )
seed = seed +1
minibatches = tf_utils.random_mini_batches(X_train,Y_train,minibatch_size,seed)
for minibatch in minibatches:
(minibatch_X,minibatch_Y) = minibatch
_ , minibatch_cost = sess.run([optimizer,cost],feed_dict={X:minibatch_X,Y:minibatch_Y})
epoch_cost = epoch_cost + minibatch_cost / num_minibatches
if epoch % 5 == 0:
costs.append(epoch_cost)
#是否打印：
if print_cost and epoch % 100 == 0:
print("epoch = " + str(epoch) + " epoch_cost = " + str(epoch_cost))
#是否绘制图谱
if is_Plot:
plt.plot(np.squeeze(costs))
plt.ylabel('cost')
plt.xlabel('iterations (per tens)')
plt.title("Learning rate =" + str(learning_rate))
plt.show()
#保存学习后的参数
parameters = sess.run(parameters)
print("参数已经保存到session。")
#计算当前的预测结果
correct_prediction = tf.equal(tf.argmax(ZL),tf.argmax(Y))
#计算准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,"float"))
print("训练集的准确率：", accuracy.eval({X: X_train, Y: Y_train}))
print("测试集的准确率:", accuracy.eval({X: X_test, Y: Y_test}))
return parameters
完整代码
import numpy as np
import h5py
from matplotlib import pyplot as plt
import tensorflow as tf
from tensorflow.python.framework import ops
import tf_utils
import time
import matplotlib.pyplot as plt # plt 用于显示图片
import matplotlib.image as mpimg # mpimg 用于读取图片
import numpy as np
np.random.seed(1)
def create_placeholders(n_x,n_y):
X = tf.placeholder(tf.float32, [n_x, None], name="X")
Y = tf.placeholder(tf.float32, [n_y, None], name="Y")
return X, Y
def initialize_parameters_deep(layers_dims):
tf.set_random_seed(1) #指定随机种子
# np.random.seed(3)
parameters = {}
L = len(layers_dims)
for l in range(1,L):
parameters["W" + str(l)] = tf.get_variable("W" + str(l),[layers_dims[l], layers_dims[l - 1]],initializer=tf.contrib.layers.xavier_initializer(seed=1))
parameters["b" + str(l)] = tf.get_variable("b" + str(l),[layers_dims[l], 1],initializer=tf.zeros_initializer())
return parameters
def linear_activation_forward(A_prev,W,b,activation):
Z = tf.matmul(W,A_prev)+b # np.dot(W,A_prev) + b
if activation == "sigmoid":
A= tf.nn.sigmoid(Z)
elif activation == "relu":
A = tf.nn.relu(Z)
# assert(A.shape == (W.shape[0],A_prev.shape[1]))
cache = (A_prev, W, b,Z) # (A_prev, W, b,Z)
return A,cache
def L_model_forward(X,parameters):
caches = [] #[(X, W1, b1,Z1),(A1, W2, b2,Z2).....]
A = X
L = len(parameters) // 2
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)
ZL = tf.matmul(parameters['W' + str(L)],A)+parameters['b' + str(L)]
AL, cache = linear_activation_forward(A, parameters['W' + str(L)], parameters['b' + str(L)], "sigmoid")
caches.append(cache)
return ZL
def compute_cost(ZL,Y):
logits = tf.transpose(ZL) #转置
labels = tf.transpose(Y) #转置
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits,labels=labels))
return cost
def L_layer_model(X_train, Y_train,X_test,Y_test, layers_dims, learning_rate=0.0001, num_iterations=1500, minibatch_size=32,print_cost=True,is_Plot=True):
ops.reset_default_graph() #能够重新运行模型而不覆盖tf变量
tf.set_random_seed(1)
seed = 3
(n_x , m) = X_train.shape #获取输入节点数量和样本数
n_y = Y_train.shape[0] #获取输出节点数量
costs = [] #成本集
#给X和Y创建placeholder
X,Y = create_placeholders(n_x,n_y)
#初始化参数
parameters =initialize_parameters_deep(layers_dims)
ZL = L_model_forward(X,parameters)
cost = compute_cost(ZL,Y)
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for epoch in range(num_iterations):
epoch_cost =0
num_minibatches = int (m / minibatch_size )
seed = seed +1
minibatches = tf_utils.random_mini_batches(X_train,Y_train,minibatch_size,seed)
for minibatch in minibatches:
(minibatch_X,minibatch_Y) = minibatch
_ , minibatch_cost = sess.run([optimizer,cost],feed_dict={X:minibatch_X,Y:minibatch_Y})
epoch_cost = epoch_cost + minibatch_cost / num_minibatches
if epoch % 5 == 0:
costs.append(epoch_cost)
#是否打印：
if print_cost and epoch % 100 == 0:
print("epoch = " + str(epoch) + " epoch_cost = " + str(epoch_cost))
#是否绘制图谱
if is_Plot:
plt.plot(np.squeeze(costs))
plt.ylabel('cost')
plt.xlabel('iterations (per tens)')
plt.title("Learning rate =" + str(learning_rate))
plt.show()
#保存学习后的参数
parameters = sess.run(parameters)
print("参数已经保存到session。")
#计算当前的预测结果
correct_prediction = tf.equal(tf.argmax(ZL),tf.argmax(Y))
#计算准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,"float"))
print("训练集的准确率：", accuracy.eval({X: X_train, Y: Y_train}))
print("测试集的准确率:", accuracy.eval({X: X_test, Y: Y_test}))
return parameters
X_train_orig , Y_train_orig , X_test_orig , Y_test_orig , classes = tf_utils.load_dataset()
X_train_flatten = X_train_orig.reshape(X_train_orig.shape[0],-1).T #每一列就是一个样本
X_test_flatten = X_test_orig.reshape(X_test_orig.shape[0],-1).T
#归一化数据
X_train = X_train_flatten / 255
X_test = X_test_flatten / 255
#转换为独热矩阵
Y_train = np.eye(6)[Y_train_orig.reshape(-1)].T
Y_test = np.eye(6)[Y_test_orig.reshape(-1)].T
start_time = time.clock()
layers_dims = [12288, 25, 12, 6] # 5-layer model
parameters = L_layer_model(X_train, Y_train, X_test,Y_test,layers_dims, learning_rate=0.0001,num_iterations = 1500,minibatch_size=32, print_cost = True,is_Plot=True)
end_time = time.clock()
print("CPU的执行时间 = " + str(end_time - start_time) + " 秒" )
参考：https://blog.csdn.net/u013733326/article/details/79971488