天天看點
傳回

Tensorflow深度學習筆記（四）--CNN手寫數字識别可視化讀取資料取批量大小為100載入圖檔定義輸入占位符顯示圖檔初始化weight初始化bias定義卷積層定義max池化層初始化第一卷積層參數定義drop_rate

資料集：MNIST

模型：CNN；卷積層數：2；全連接配接層數：3，全連接配接層Dropout Rate:0.8；激活函數：Relu

損失函數：交叉熵

Optimizer：AdamOptimizer

可視化工具：tensorboad

先看結果：

訓練21epoch，測試集accuracy如下：

Iter 0, Testing Accuracy= 0.9455

Iter 1, Testing Accuracy= 0.9692

Iter 2, Testing Accuracy= 0.9775

Iter 3, Testing Accuracy= 0.9818

Iter 4, Testing Accuracy= 0.9825

Iter 5, Testing Accuracy= 0.9843

Iter 6, Testing Accuracy= 0.9856

Iter 7, Testing Accuracy= 0.9875

Iter 8, Testing Accuracy= 0.9871

Iter 9, Testing Accuracy= 0.989

Iter 10, Testing Accuracy= 0.9902

Iter 11, Testing Accuracy= 0.9895

Iter 12, Testing Accuracy= 0.99

Iter 13, Testing Accuracy= 0.9915

Iter 14, Testing Accuracy= 0.9904

Iter 15, Testing Accuracy= 0.9913

Iter 16, Testing Accuracy= 0.9917

Iter 17, Testing Accuracy= 0.9918

Iter 18, Testing Accuracy= 0.9916

Iter 19, Testing Accuracy= 0.9908

Iter 20, Testing Accuracy= 0.9918

sorboard結果展示

Tensorflow深度學習筆記（四）--CNN手寫數字識别可視化讀取資料取批量大小為100載入圖檔定義輸入占位符顯示圖檔初始化weight初始化bias定義卷積層定義max池化層初始化第一卷積層參數定義drop_rate
Tensorflow深度學習筆記（四）--CNN手寫數字識别可視化讀取資料取批量大小為100載入圖檔定義輸入占位符顯示圖檔初始化weight初始化bias定義卷積層定義max池化層初始化第一卷積層參數定義drop_rate

卷積層1 Weight變化

Tensorflow深度學習筆記（四）--CNN手寫數字識别可視化讀取資料取批量大小為100載入圖檔定義輸入占位符顯示圖檔初始化weight初始化bias定義卷積層定義max池化層初始化第一卷積層參數定義drop_rate

卷積層1 Bias變化

Tensorflow深度學習筆記（四）--CNN手寫數字識别可視化讀取資料取批量大小為100載入圖檔定義輸入占位符顯示圖檔初始化weight初始化bias定義卷積層定義max池化層初始化第一卷積層參數定義drop_rate

全連接配接層1 Weight變化

Tensorflow深度學習筆記（四）--CNN手寫數字識别可視化讀取資料取批量大小為100載入圖檔定義輸入占位符顯示圖檔初始化weight初始化bias定義卷積層定義max池化層初始化第一卷積層參數定義drop_rate

全連接配接層1 Bias變化

Tensorflow深度學習筆記（四）--CNN手寫數字識别可視化讀取資料取批量大小為100載入圖檔定義輸入占位符顯示圖檔初始化weight初始化bias定義卷積層定義max池化層初始化第一卷積層參數定義drop_rate

Graph

Tensorflow深度學習筆記（四）--CNN手寫數字識别可視化讀取資料取批量大小為100載入圖檔定義輸入占位符顯示圖檔初始化weight初始化bias定義卷積層定義max池化層初始化第一卷積層參數定義drop_rate

embedding

Tensorflow深度學習筆記（四）--CNN手寫數字識别可視化讀取資料取批量大小為100載入圖檔定義輸入占位符顯示圖檔初始化weight初始化bias定義卷積層定義max池化層初始化第一卷積層參數定義drop_rate

附代碼：

import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data

from tensorflow.contrib.tensorboard.plugins import projector

讀取資料

mnist = input_data.read_data_sets(‘MNIST_data/’,one_hot=True)

取批量大小為100

batch_size = 100

n_batch = mnist.train.num_examples//batch_size

image_num = 10000

DIR = “F:/dl/”

載入圖檔

embedding = tf.Variable(tf.stack(mnist.test.images[:image_num]), trainable=False, name=’embedding’)

def variable_summary(var):

with tf.name_scope(‘summary’):

mean = tf.reduce_mean(var)

tf.summary.scalar(‘mean’,mean)

stddev = tf.sqrt(tf.reduce_mean(tf.square(var-mean)))

tf.summary.scalar(‘stddev’,stddev)

tf.summary.scalar(‘max’,tf.reduce_max(var))

tf.summary.scalar(‘min’,tf.reduce_min(var))

with tf.name_scope(‘input’):

定義輸入占位符 

x = tf.placeholder(tf.float32,shape=[None,784],name='x-input')
y = tf.placeholder(tf.float32,shape=[None,10],name='y-input')
x_image = tf.reshape(x,shape=[-1,28,28,1],name='x_image')

顯示圖檔

with tf.name_scope(‘input_reshape’):

image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])

tf.summary.image(‘input’, image_shaped_input, 10)

初始化weight

def weight_variable(shape,name):

initial = tf.truncated_normal(shape,stddev=0.1)

return tf.Variable(initial,name=name)

初始化bias

def bias_variable(shape,name):

initial = tf.constant(0.1,shape=shape)

return tf.Variable(initial,name=name)

定義卷積層

def conv2d(x,W):

return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding=’SAME’)

定義max池化層

def max_pool_2x2(x):

return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding=’SAME’)

初始化第一卷積層參數

with tf.name_scope(‘conv1’):

W_conv1 = weight_variable([5,5,1,32],name=’W_conv1’)

B_conv1 = bias_variable([32],name=’B_conv1’)

variable_summary(W_conv1)

variable_summary(B_conv1)

#卷積網絡第一層

conv2d_1 = conv2d(x_image,W_conv1) + B_conv1

h_conv_1 = tf.nn.relu(conv2d_1,name=’h_conv2d_1’)

h_pool_1 = max_pool_2x2(h_conv_1)

with tf.name_scope(‘conv2’):

#初始化第二卷積層參數

W_conv2 = weight_variable([5,5,32,64],name=’W_conv2’)

B_conv2 = bias_variable([64],name=’B_conv2’)

variable_summary(W_conv2)

variable_summary(B_conv2)

#卷積網絡第二層
conv2d_2 = conv2d(h_pool_1,W_conv2) + B_conv2
h_conv_2 = tf.nn.relu(conv2d_2,name='h_conv_2')
h_pool_2 = max_pool_2x2(h_conv_2)

#池化層輸出結果轉化為一維向量
h_pool2_vec = tf.reshape(h_pool_2,[-1,7*7*64])

定義drop_rate

keep_prob = tf.placeholder(tf.float32,name=’keep_prob’)

with tf.name_scope(‘fc1’):

#初始化全連接配接1層參數

W_fc_1 = weight_variable([7*7*64,1024],name=’W_fc_1’)

B_fc_1 =bias_variable([1024],name=’b_fc_1’)

variable_summary(W_fc_1)

variable_summary(B_fc_1)

#第一全連接配接層
h_fc_1 = tf.nn.relu(tf.matmul(h_pool2_vec,W_fc_1) + B_fc_1)
h_fc1_drop = tf.nn.dropout(h_fc_1,keep_prob=keep_prob)

with tf.name_scope(‘fc2’):

#初始化第2全連接配接層參數

W_fc_2 = weight_variable([1024,200],name=’W_fc_2’)

B_fc_2 = bias_variable([200],name=’B_fc_2’)

variable_summary(W_fc_2)

variable_summary(B_fc_2)

#第2全連接配接層
h_fc_2 = tf.nn.relu(tf.matmul(h_fc1_drop,W_fc_2) + B_fc_2)

h_fc2_drop = tf.nn.dropout(h_fc_2,keep_prob=keep_prob)

with tf.name_scope(‘fc3’):

#初始化第3全連接配接層參數

W_fc_3 = weight_variable([200,10],name=’W_fc_3’)

B_fc_3 = bias_variable([10],name=’B_fc_3’)

variable_summary(W_fc_3)

variable_summary(B_fc_3)

#第3全連接配接層
prediction = tf.nn.softmax(tf.matmul(h_fc2_drop,W_fc_3) + B_fc_3)

with tf.name_scope(‘loss’):

#交叉熵損失函數

cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))

tf.summary.scalar(‘loss’,cross_entropy)

lr = tf.Variable(0.0001,dtype=tf.float32)

train_step = tf.train.AdamOptimizer(lr).minimize(cross_entropy)

with tf.name_scope(‘accuracy’):

predict_result = tf.equal(tf.argmax(prediction,1),tf.argmax(y,1))

accuracy = tf.reduce_mean(tf.cast(predict_result,tf.float32))

tf.summary.scalar(‘accuracy’,accuracy)

merged = tf.summary.merge_all()

with tf.Session() as sess:

sess.run(tf.global_variables_initializer())

writer = tf.summary.FileWriter(‘logs/test’,sess.graph)

#産生metadata檔案
if tf.gfile.Exists(DIR + 'projector/projector1/metadata.tsv'):
    tf.gfile.DeleteRecursively(DIR + 'projector/projector1/metadata.tsv')
with open(DIR + 'projector/projector1/metadata.tsv', 'w') as f:
    labels = sess.run(tf.argmax(mnist.test.labels[:],1))
    for i in range(image_num):
        f.write(str(labels[i]) + '\n')


projector_writer = tf.summary.FileWriter(DIR + 'projector/projector1',sess.graph)
saver = tf.train.Saver()
config = projector.ProjectorConfig()
embed = config.embeddings.add()
embed.tensor_name = embedding.name
embed.metadata_path = DIR + 'projector/projector1/metadata.tsv'
embed.sprite.image_path = DIR + 'projector/data/mnist_10k_sprite.png'
embed.sprite.single_image_dim.extend([28,28])
projector.visualize_embeddings(projector_writer,config)


for epoch in range(21):

    run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
    run_metadata = tf.RunMetadata()
    for batch in range(n_batch):
        batch_x,batch_y = mnist.train.next_batch(batch_size)
        summary,_ = sess.run([merged,train_step],feed_dict={x:batch_x,y:batch_y,keep_prob:0.8},options=run_options,run_metadata=run_metadata)
    projector_writer.add_run_metadata(run_metadata, 'step%03d' % epoch)
    projector_writer.add_summary(summary, epoch)
    test_acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0})
    print ("Iter " + str(epoch) + ", Testing Accuracy= " + str(test_acc))


saver.save(sess, DIR + 'projector/projector1/a_model.ckpt')
projector_writer.close()`

附：本人第一篇部落格，還不太用……後面會補上之前寫的BP神經網絡，以及後面會學習的RNN，GAN，RL。時間允許的話也會更一些ML内容，歡迎小夥伴一起交流。

dl 深度學習 tensorflow cnn tensorboard
上一篇: 神經網絡基礎Convolutional neural networks基于 BP 神經網絡的識别手寫體數字 - 神經網絡基礎
下一篇: ML Notes: Week 4 - Neural Networks: Representation

繼續閱讀