深度學習框架tensorflow學習與應用10(MNSIT卷積神經網路實現)
阿新 • • 發佈:2018-12-29
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets('F:/PY/MNIST_data/', one_hot=True) batch_size = 100 n_batch = mnist.train.num_examples // batch_size #引數概要 def variable_summaries(var): with tf.name_scope('summaries'): mean = tf.reduce_mean(var) tf.summary.scalar('mean', mean)#平均值 with tf.name_scope('stddev'): stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean))) tf.summary.scalar('stddev', stddev)#標準差 tf.summary.scalar('max', tf.reduce_max(var))#最大值 tf.summary.scalar('min', tf.reduce_min(var))#最小值 tf.summary.histogram('histogram', var)#直方圖 def weight_variable(shape, name): initial = tf.truncated_normal(shape, stddev = 0.1) return tf.Variable(initial, name=name) def bias_variable(shape, name): initial = tf.constant(0.1, shape=shape) return tf.Variable(initial, name=name) #卷積層 def conv2d(x,W): return tf.nn.conv2d(x, W , strides =[1,1,1,1], padding='SAME') def max_pool_2x2(x): return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1],padding='SAME') #名稱空間 with tf.name_scope('input'): x = tf.placeholder(tf.float32, [None, 784], name= 'x-input') y = tf.placeholder(tf.float32, [None, 10],name ='y-input') with tf.name_scope('x_image'): x_image = tf.reshape(x, [-1, 28, 28, 1], name='x_iamge') with tf.name_scope('Conv1'): #第一層 with tf.name_scope('W_conv1'): W_conv1 = weight_variable([5, 5, 1, 32],name='W_conv1') with tf.name_scope('b_conv1'): b_conv1 = bias_variable([32], name='b_conv1') #每一個卷積核一個偏置值 # 把x_image和權值向量進行卷積,再加上偏置值,然後應用於relu啟用函式 with tf.name_scope('conv2d_1'): conv2d_1 = conv2d(x_image, W_conv1) + b_conv1 with tf.name_scope('relu'): h_conv1 = tf.nn.relu(conv2d_1) with tf.name_scope('h_pool1'): h_pool1 = max_pool_2x2((h_conv1)) #進行max-pooling kernel_transposed = tf.transpose (W_conv1, [3, 0, 1, 2]) with tf.name_scope('Conv2'): #第二層 # 初始化第二個卷積層的權值和偏置 with tf.name_scope('W_conv2'): W_conv2 = weight_variable([5, 5, 32, 64], name= 'W_conv2') with tf.name_scope('b_conv2'): b_conv2 = bias_variable([64], name='b_conv2') # 把h_pool1和權值向量進行卷積,再加上偏置值,然後應用於relu啟用函式 with tf.name_scope('conv2d_2'): conv2d_2 = conv2d(h_pool1,W_conv2)+ b_conv2 with tf.name_scope('relu'): h_conv2 = tf.nn.relu(conv2d_2) with tf.name_scope('h_pool2'): h_pool2 = max_pool_2x2(h_conv2) #進行max-pooling #28*28的圖片第一次卷積後還是28*28,第一次池化後變為14*14 #第二次卷積後為14*14,第二次池化後變為了7*7 #進過上面操作後得到64張7*7的平面 with tf.name_scope('fc1'): # 初始化第一個全連線層的權值 with tf.name_scope('W_fc1'): W_fc1 = weight_variable([7*7*64,1024],name='W_fc1') with tf.name_scope('b_fc1'): b_fc1 = bias_variable([1024], name='b_fc1') #1024個節點 with tf.name_scope('h_pool2_flat'): #把池化層2的輸出扁平化為1維 h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64], name='h_pool2_flat') # 求第一個全連線層的輸出 with tf.name_scope('wx_plus_b1'): wx_plus_b1 = tf.matmul(h_pool2_flat, W_fc1) +b_fc1 with tf.name_scope('relu'): h_fc1 = tf.nn.relu(wx_plus_b1) # keep_prob用來表示神經元的輸出概率 with tf.name_scope('keep_prob'): keep_prob = tf.placeholder(tf.float32, name='keep_prob') with tf.name_scope('h_fc1_drop'): h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob, name='h_fc1_drop') with tf.name_scope('fc2'): # 初始化第二個全連線層 with tf.name_scope('W_fc2'): w_fc2 = weight_variable([1024, 10], name='W_fc2') with tf.name_scope('b_fc2'): b_fc2 = bias_variable([10], name='b_fc2') with tf.name_scope('wx_plus_b2'): wx_plus_b2 = tf.matmul(h_fc1_drop, w_fc2) + b_fc2 with tf.name_scope('softmax'): # 計算輸出 prediction = tf.nn.softmax(wx_plus_b2) #交叉熵代價函式 with tf.name_scope('cross_entropy'): cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels= y,logits =prediction), name ='cross_entopy') tf.summary.scalar('cross_entropy', cross_entropy) #使用AdamOptimizer進行優化 with tf.name_scope('train'): train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy) #求準確率 with tf.name_scope('accuracy'): with tf.name_scope('correct_prediction'): #結果存放在一個布林列表中 correct_prediction = tf.equal(tf.argmax(prediction,1),tf.argmax(y,1))#argmax返回一維張量中最大的值所在的位置 with tf.name_scope('accuracy'): # 求準確率 accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) tf.summary.scalar('accuracy',accuracy) # 合併所有的summary merged = tf.summary.merge_all() with tf.Session() as sess: sess.run(tf.global_variables_initializer()) train_writer = tf.summary.FileWriter('logs/train', sess.graph) test_writer = tf.summary.FileWriter('logs/test',sess.graph) # img0 = tf.summary.image('conv1/filters', kernel_transposed, max_outputs=6) # layer1_image1 = h_conv1[0:1, :, :, 0:14] # layer1_image1 = tf.transpose(layer1_image1, perm=[3, 1, 2, 0]) # img1 = tf.summary.image("filtered_images_layer1", layer1_image1, max_outputs=16) # train_writer.add_summary(sess.run(img0)) # train_writer.add_summary(sess.run(img1)) for i in range(5001): # 訓練模型 batch_xs1, batch_ys1 = mnist.train.next_batch(batch_size) sess.run(train_step, feed_dict={x:batch_xs1, y: batch_ys1, keep_prob: 0.7}) # 記錄訓練集計算的引數 summary = sess.run(merged, feed_dict ={x:batch_xs1, y:batch_ys1, keep_prob:1.0}) train_writer.add_summary(summary,i) batch_xs, batch_ys = mnist.test.next_batch(batch_size) summary1 = sess.run(merged, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.0}) test_writer.add_summary(summary1, i) if i%100 ==0: test_acc = sess.run(accuracy, feed_dict={x:mnist.test.images, y:mnist.test.labels, keep_prob:1.0}) train_acc = sess.run(accuracy, feed_dict={x:mnist.train.images[:10000],y:mnist.train.labels[:10000],keep_prob:0.7}) print("Iter"+str(i)+".Testing Accuracy="+str(test_acc)+",Traning Accuracy="+str(train_acc))
Iter4500.Testing Accuracy=0.9871,Traning Accuracy=0.9895
Iter4600.Testing Accuracy=0.9867,Traning Accuracy=0.9885
Iter4700.Testing Accuracy=0.986,Traning Accuracy=0.9881
Iter4800.Testing Accuracy=0.9873,Traning Accuracy=0.9881
Iter4900.Testing Accuracy=0.9875,Traning Accuracy=0.9894
Iter5000.Testing Accuracy=0.9873,Traning Accuracy=0.9889