中國大學MOOC-人工智慧實踐:Tensorflow筆記-課程筆記 Chapter5
阿新 • • 發佈:2019-01-01
學習課程時的個人筆記記錄。具體課程情況可以點選連結檢視。(這裡推一波中國大學MOOC,很好的學習平臺,質量高,種類全,想要學習的話很有用的)**
本篇是第五章的學習筆記,第四章的可以點選我閱讀.
前三章的可以點選我閱讀.
Chapter 5 全連線網路基礎
5.1 MNIST 資料集
MNIST資料集:
6W張28*28的0~9手寫數字圖片和標籤,用於訓練
1W張28*28的0~9手寫數字圖片和標籤,用於測試
每張圖片的784個畫素點(28*28)組成長度為784的一維陣列,作為輸入特徵
圖片的標籤以一維陣列的形式給出,每個元素表示對應分類出現的概率
TF 提供 input_data 模組自動讀取資料集
from tensorflow.examples.tutorials.minist import input_data
minist = input_data.read_data_set('./data/', one_hot=True)
返回各子集樣本數
mnist.train.num_examples #返回訓練集樣本數
mnist.validation.num_examples #返回驗證集樣本數
mnist.test.num_examples #返回測試集樣本數
返回標籤和資料
mnist.train.labels[0] #返回標籤
mnist.train.images[0 ] #返回資料
取一小撮資料,準備喂入神經網路
BATCH_SIZE = 200 #定義batch size
xs, ys = mnist.train.next_batch(BATCH_SIZE)
一些常用的函式
tf.get_collection("") #從集合中取全部變數,生成一個列表
tf.add_n([]) #列表內對應元素相加
tf.cast(x, dtype) #把x轉換為dtype型別
tf.argmax(x, axis) #返回最大值所在索引號 如: tf.argmax([1,0,0], 1) 返回0
import os
os.path.join("home", "name") #f返回home/name
字串.split() #按照指定的拆分符對字串切片,返回分割後的列表
#如:'./model/mnist_model-1001'.split('-')[-1] 返回1001
with tf.Graph().as_default() as g: #其內定義的節點在計算圖g中
儲存模型
saver = tf.train.Saver() #例項化saver物件
with tf.Session() as sess: #在with結構for迴圈中一定輪數時儲存模型到當前會話
for i in ranges(STEPS): #拼接成./MODEL_SAVE_PATH/MODEL_NAME-global_step
if i % 輪數 == 0:
saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step = global_step)
載入模型
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(儲存路徑)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess,ckpt.model_checkpoint_path)
例項化課還原滑動平均值的saver
ema = tf.train.ExponentialMovingAverage(滑動平均基數)
ema_restore = ema.variables_to_restore()
saver = tf.train.Saver(ema_restore)
準確率計算方法
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
5.2 模組化搭建神經網路八股
forward.py
def forward(x, regularizer):
w =
b =
y =
return y
def get_weight(shape, regularizer):
pass
def get_bias(shape):
pass
backward.py
def backward(mnist):
x =
y_ =
y = #復現前向傳播,計算出y
global_step =
loss =
<正則化,指數衰減學習率,滑動平均>
train_step =
例項化Saver
with tf.Session() as sess:
初始化
for i in range(STEPS):
sess.run(train_step,feed_dict={x:, y_:})
if i%輪數 ==0:
print
saver.save()
損失函式loss含正則化regularization
backward.py中加入
ce = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y,labels=tf.argmax(y_,1))
cem = tf.reduce_mean(ce)
loss = cem+tf.add_n(tf.get_collection('losses'))
forward.py中加入
if regularizer != None:tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(regularizer)(w))
學習率learning_rate
backward.py中加入
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,
LEARNING_RATE_STEP,
LEARNING_RATE_DECAY,
staircase = True)
滑動平均ema
ema = tf.train.ExponentialMovingAverage(衰減率MOVING_AVERAGE_DECAY,當前輪數global_step)
ema_op = ema.apply(tf.trainable_variables())
with tf.control_dependencies([train_step,ema_op]):
train_op = tf.no_op(name='train')
test.py
def test(mnist):
with tf.Graph()as_default()as g:
x =
y_ =
y =
例項化可還原滑動平均值的saver
計算正確率
while True:
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(儲存路徑) #載入ckpt模型
if ckpt and ckpt.model_checkpoint_path: #如果已經有ckpt模型則恢復
saver.restore(sess,ckpt.model_checkpoint_path) #恢復會話
global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1] #恢復輪數
accuracy_score = sess.run(accuracy, feed_dict={x:mnist.test.images, y_:mnist.test.labels}) #計算準確率
print("After %s training steps, test accuracy = %g" % (global_step, accuracy_score))
else: #如果沒有模型
print("No checkpoint file found!") #給出提示
return
def main():
mnist = input_data.read_data_sets("./data/", one_hot=True)
test(mnist)
if __name__=='__main__':
main()
5.3 手寫數字識別準確率輸出
前向傳播 mnist_forward.py
#coding:utf-8
import tensorflow as tf
INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500
def get_weight(shape, regularizer):
w = tf.Variable(tf.truncated_normal(shape,stddev=0.1))
if regularizer != None: tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(regularizer)(w))
return w
def get_bias(shape):
b = tf.Variable(tf.zeros(shape))
return b
def forward(x, regularizer):
w1 = get_weight([INPUT_NODE, LAYER1_NODE], regularizer)
b1 = get_bias([LAYER1_NODE])
y1 = tf.nn.relu(tf.matmul(x, w1) + b1)
w2 = get_weight([LAYER1_NODE, OUTPUT_NODE], regularizer)
b2 = get_bias([OUTPUT_NODE])
y = tf.matmul(y1, w2) + b2
return y
反向傳播 mnist_backward.py
#coding:utf-8
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_forward
import os
BATCH_SIZE = 200
LEARNING_RATE_BASE = 0.1
LEARNING_RATE_DECAY = 0.99
REGULARIZER = 0.0001
STEPS = 50000
MOVING_AVERAGE_DECAY = 0.99
MODEL_SAVE_PATH = 'G:/model/' #這裡是我選擇放置訓練好的model的路徑,根據自己的需要進行修改
MODEL_NAME = 'mnist_model'
DATA_PATH = 'G:/datasets/mnist' #這裡是我放置dataset的路徑,根據自己的需要進行修改
def backward(mnist):
x = tf.placeholder(tf.float32, [None, mnist_forward.INPUT_NODE])
y_ = tf.placeholder(tf.float32, [None, mnist_forward.OUTPUT_NODE])
y = mnist_forward.forward(x, REGULARIZER)
global_step = tf.Variable(0, trainable=False)
ce = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y,labels=tf.argmax(y_, 1))
cem = tf.reduce_mean(ce)
loss = cem + tf.add_n(tf.get_collection('losses'))
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE,global_step,mnist.train.num_examples / BATCH_SIZE,LEARNING_RATE_DECAY,staircase = True)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
ema = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
ema_op = ema.apply(tf.trainable_variables())
with tf.control_dependencies([train_step, ema_op]):
train_op = tf.no_op(name = 'train')
saver = tf.train.Saver()
with tf.Session() as sess:
init_op = tf.global_variables_initializer()
sess.run(init_op)
for i in range(STEPS):
xs, ys = mnist.train.next_batch(BATCH_SIZE)
_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: xs, y_: ys})
if i % 1000 == 0:
print("After %d training steps, loss on training batch is %g." % (step, loss_value))
saver.save(sess, os.path.join(MODEL_SAVE_PATH,MODEL_NAME),global_step=global_step)
def main():
mnist = input_data.read_data_sets(DATA_PATH, one_hot = True)
backward(mnist)
if __name__ == '__main__':
main()
測試輸出準確率 mnist_test.py
#coding:utf-8
import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_backward
import mnist_forward
TEST_INTERVAL_SECS = 5
DATA_PATH = 'G:/datasets/mnist' #這裡是我放置dataset的路徑,根據自己的需要進行修改
def test(mnist):
with tf.Graph().as_default() as g:
x = tf.placeholder(tf.float32, [None, mnist_forward.INPUT_NODE])
y_ = tf.placeholder(tf.float32, [None, mnist_forward.OUTPUT_NODE])
y = mnist_forward.forward(x, None)
ema = tf.train.ExponentialMovingAverage(mnist_backward.MOVING_AVERAGE_DECAY)
ema_restore = ema.variables_to_restore()
saver = tf.train.Saver(ema_restore)
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
while True:
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(mnist_backward.MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
accuracy_score = sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels})
print("After %s training steps, test accuracy = %g" % (global_step, accuracy_score))
else:
print("No checkpoint file found!")
return
time.sleep(TEST_INTERVAL_SECS)
def main():
mnist = input_data.read_data_sets(DATA_PATH, one_hot=True)
test(mnist)
if __name__ == '__main__':
main()
執行結果::
跑這麼個小玩意 ,電腦卡成狗/微笑