本次作业目的
学习TensorFlow
下载地址
链接:https://pan.baidu.com/s/1imMIYrTCVoiF_H_sT_x5Vg
提取码:5tja
代码
#本次作业的目的
# 初始化变量
# 建立一个会话
# 训练的算法
# 实现一个神经网络
import numpy as np
import h5py
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.python.framework import ops
import tf_utils
import time
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
np.random.seed(1)
#线性函数
def linear_function():
np.random.seed(1)
X=np.random.randn(3,1)
W=np.random.randn(4,3)
b=np.random.randn(4,1)
Y=tf.add(tf.matmul(W,X),b)
sess=tf.Session()
result=sess.run(Y)
sess.close()
return result
#计算sigmiod
def sigmiod(z):
x=tf.placeholder(tf.float32,name='x')
sigmiod=tf.sigmoid(x)
sess=tf.Session()
result=sess.run(sigmiod,feed_dict={x:z})
sess.close()
return result
#独热矩阵
def one_hot_matrix(lables,C):
"""
:param lables: 标签向量
:param C:分类数
:return:独热矩阵
"""
C=tf.constant(C,name='C')
one_hot_matrix=tf.one_hot(indices=lables,depth=C,axis=0)
sess=tf.Session()
one_hot=sess.run(one_hot_matrix)
sess.close()
return one_hot
#初始化为1
def ones(shape):
ones=tf.ones(shape)
sess=tf.Session()
ones=sess.run(ones)
sess.close()
return ones
#构建网络
X_train_orig , Y_train_orig , X_test_orig , Y_test_orig , classes = tf_utils.load_dataset()#加载数据集
#一列为一个样本
X_train_flatten=X_train_orig.reshape(X_train_orig.shape[0],-1).T
X_test_flatten=X_test_orig.reshape(X_test_orig.shape[0],-1).T
#归一化
X_train=X_train_flatten/255
X_test=X_test_flatten/255
#获得独热矩阵
Y_train=tf_utils.convert_to_one_hot(Y_train_orig,6)
Y_test=tf_utils.convert_to_one_hot(Y_test_orig,6)
#创建placeholders
def create_placeholders(n_x,n_y):
"""
参数:
n_x - 一个实数,图片向量的大小(64*64*3 = 12288)
n_y - 一个实数,分类数(从0到5,所以n_y = 6)
返回:
X - 一个数据输入的占位符,维度为[n_x, None],dtype = "float"
Y - 一个对应输入的标签的占位符,维度为[n_Y,None],dtype = "float"
"""
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():
np.random.seed(1)
W1=tf.get_variable('W1',[25,12288],initializer=tf.contrib.layers.xavier_initializer(seed=1))
b1=tf.get_variable('b1',[25,1],initializer=tf.zeros_initializer())
W2=tf.get_variable('W2',[12, 25],initializer=tf.contrib.layers.xavier_initializer(seed=1))
b2 = tf.get_variable('b2', [12, 1], initializer=tf.zeros_initializer())
W3 = tf.get_variable('W3', [6, 12], initializer=tf.contrib.layers.xavier_initializer(seed=1))
b3 = tf.get_variable('b3', [6, 1], initializer=tf.zeros_initializer())
parameters={
'W1':W1,
'W2':W2,
'W3':W3,
'b1':b1,
'b2':b2,
'b3':b3
}
return parameters
#前向传播
def forward_propagation(X,parameters):
W1=parameters['W1']
b1=parameters['b1']
W2=parameters['W2']
b2=parameters['b2']
W3=parameters['W3']
b3=parameters['b3']
Z1=tf.add(tf.matmul(W1,X),b1)
A1=tf.nn.relu(Z1)
Z2=tf.add(tf.matmul(W2,A1),b2)
A2=tf.nn.relu(Z2)
Z3=tf.add(tf.matmul(W3,A2),b3)
return Z3
#计算成本
def compute_cost(Z3,Y):
logits=tf.transpose(Z3)
labels=tf.transpose(Y)
cost=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits,labels=labels))
return cost
#模型构建
def model(X_train,Y_train,X_test,Y_test,learning_rate=0.0001,num_epochs=1500
,minibatch_size=32,print_cost=True,is_plot=True):
ops.reset_default_graph()
tf.set_random_seed(1)
seed=3
(n_x,m)=X_train.shape
n_y=Y_train.shape[0]
costs=[]
X,Y=create_placeholders(n_x,n_y)#给X,Y创建placeholders
parameters=initialize_parameters()#初始化
Z3=forward_propagation(X,parameters)#前向传播
cost=compute_cost(Z3,Y)#计算成本
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)#反向传播,使用Adam优化
init=tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for epoch in range(num_epochs):
epoch_cost=0#每代的成本
num_minibatches=int(m/minibatch_size)#minibatch的数量
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)
if print_cost and epoch%100==0:
print("epoch = " + str(epoch) + " epoch_cost = " + str(epoch_cost))
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(Z3), 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
#开始时间
start_time = time.clock()
#开始训练
parameters = model(X_train, Y_train, X_test, Y_test)
#结束时间
end_time = time.clock()
#计算时差
print("CPU的执行时间 = " + str(end_time - start_time) + " 秒" )
参考地址:https://blog.csdn.net/u013733326/article/details/79971488