1、VGGNet：5段卷積【每段有2~3個卷積層+最大池化層】【每段過濾器個數：64-128-256-512-512】
每段的2~3個卷積層串聯在一塊兒的做用：網絡
2個3×3的卷積層串聯的效果至關於一個5×5的卷積層，即一個像素會跟周圍5×5的像素產生關聯。【28*28的輸入通過一次5*5獲得24*24，s=1,p=0,（28-5）/1 + 1 = 24。而28*28通過2個3*3也能夠獲得24*24.】session
3個3×3的卷積層串聯的效果至關於一個7×7的卷積層，dom
- 好處一：3個3×3的卷積層串聯擁有的餐數量比1個7×7的參數量少。只是後者的：（3×3×3）/ （7 × 7） = 55 %。
- 好處二：3個3×3的卷積層擁有比1個7×7的卷積層更多的線性變換（如，前者可使用三次Relu函數，後者只有一次），使得CNN對特徵的學習能力更強。
VGG探索了卷積神經網絡的深度與其性能之間的關係，反覆堆疊3×3的小型卷積核和2×2的最大池化層，構築了16~19層深度的卷積神經網絡。ide
2、VGG訓練的技巧：
- 先訓練級別A的簡單網絡，再複用A網絡的權重來初始化後面的幾個複雜模型，這樣訓練收斂的速度更快。
- 在預測時，VGG採用Multi-Scale的方法，將圖像scale到一個尺寸Q，並將圖片輸入卷積網絡計算。而後在最後一個卷積層使用滑窗的方式進行分類預測，將不一樣窗口的分類結果平均，再將不一樣尺寸Q的結果平均獲得最後結果。提升數據利用率和預測準確率
- 採用了Multi-scale作數據加強，防止過擬合
3、代碼：
#加載模塊 from datetime import datetime import math import time import tensorflow as tf #定義函數：卷積層、池化層、全鏈接層 #conv_op用來建立卷積層 def conv_op(input_op , name ,kh , kw , n_out, dh ,dw , p): n_in = input_op.get_shape()[-1].value with tf.name_scope(name) as scope: w = tf.get_variable(scope+'w',shape = [kh,kw,n_in,n_out], dtype = tf.float32 , initializer=tf.contrib.layers.xavier_initializer_conv2d()) conv = tf.nn.conv2d(input_op,w,strides = [1,dh,dw,1],padding = 'SAME') b = tf.Variable(tf.constant(0.0,shape = [n_out] , dtype = tf.float32),trainable = True , name = 'b') z = tf.nn.bias_add(conv,b) activation = tf.nn.relu(z,name = scope) p+=[w,b] return activation #用來建立全鏈接層 def fc_op(input_op,name,n_out,p): n_in = input_op.get_shape()[-1].value with tf.name_scope(name) as scope: w = tf.get_variable(scope+'w',shape = [n_in,n_out],dtype = tf.float32, initializer= tf.contrib.layers.xavier_initializer()) b = tf.Variable(tf.constant(0.1,shape = [n_out],dtype = tf.float32),name = 'b') activation = tf.nn.relu_layer(input_op,w,b,name = scope) p += [w,b] return activation #用來建立池化層 def mpool_op(input_op,name,kh,kw,dh,dw): return tf.nn.max_pool(input_op,ksize = [1,kh,kw,1],strides = [1,dh,dw,1],padding = 'SAME',name = name) #創建VGG模型 def inference_op(input_op,keep_prob): p=[] conv1_1=conv_op(input_op,name="conv1_1",kh=3,kw=3,n_out=64,dh=1,dw=1,p=p) conv1_2=conv_op(conv1_1,name="conv1_2",kh=3,kw=3,n_out=64,dh=1,dw=1,p=p) pool1=mpool_op(conv1_2,name="pool1",kh=2,kw=2,dw=2,dh=2) conv2_1=conv_op(pool1,name="conv2_1",kh=3,kw=3,n_out=128,dh=1,dw=1,p=p) conv2_2=conv_op(conv2_1,name="conv2_2",kh=3,kw=3,n_out=128,dh=1,dw=1,p=p) pool2=mpool_op(conv2_2,name="pool2",kh=2,kw=2,dw=2,dh=2) conv3_1=conv_op(pool2,name="conv3_1",kh=3,kw=3,n_out=256,dh=1,dw=1,p=p) conv3_2=conv_op(conv3_1,name="conv3_2",kh=3,kw=3,n_out=256,dh=1,dw=1,p=p) conv3_3=conv_op(conv3_2,name="conv3_3",kh=3,kw=3,n_out=256,dh=1,dw=1,p=p) pool3=mpool_op(conv3_3,name="pool3",kh=2,kw=2,dw=2,dh=2) conv4_1=conv_op(pool3,name="conv4_1",kh=3,kw=3,n_out=512,dh=1,dw=1,p=p) conv4_2=conv_op(conv4_1,name="conv4_2",kh=3,kw=3,n_out=512,dh=1,dw=1,p=p) conv4_3=conv_op(conv4_2,name="conv4_3",kh=3,kw=3,n_out=512,dh=1,dw=1,p=p) pool4=mpool_op(conv4_3,name="pool4",kh=2,kw=2,dw=2,dh=2) conv5_1=conv_op(pool4,name="conv5_1",kh=3,kw=3,n_out=512,dh=1,dw=1,p=p) conv5_2=conv_op(conv5_1,name="conv5_2",kh=3,kw=3,n_out=512,dh=1,dw=1,p=p) conv5_3=conv_op(conv5_2,name="conv5_3",kh=3,kw=3,n_out=512,dh=1,dw=1,p=p) pool5=mpool_op(conv5_3,name="pool5",kh=2,kw=2,dw=2,dh=2) shp=pool5.get_shape() flattened_shape=shp[1].value*shp[2].value*shp[3].value resh1=tf.reshape(pool5,[-1,flattened_shape],name="resh1") fc6=fc_op(resh1,name="fc6",n_out=4096,p=p) fc6_drop=tf.nn.dropout(fc6,keep_prob,name="fc6_drop") fc7=fc_op(fc6_drop,name="fc7",n_out=4096,p=p) fc7_drop=tf.nn.dropout(fc7,keep_prob,name="fc7_drop") fc8=fc_op(fc7_drop,name="fc8",n_out=1000,p=p) softmax=tf.nn.softmax(fc8) predictions=tf.argmax(softmax,1) return predictions,softmax,fc8,p #時間差 def time_tensorflow_run(session,target,feed,info_string): num_steps_burn_in=10 total_duration=0.0 total_duration_squared=0.0 for i in range(num_batches+num_steps_burn_in): start_time=time.time() _=session.run(target,feed_dict=feed) duration=time.time()-start_time if i>=num_steps_burn_in: if not i%10: print('%s:step %d,duration=%.3f' % (datetime.now(),i-num_steps_burn_in,duration)) total_duration+=duration total_duration_squared+=duration*duration mn=total_duration/num_batches vr=total_duration_squared/num_batches-mn*mn sd=math.sqrt(vr) print('%s:%s across %d steps,%.3f +/- %.3f sec / batch' % (datetime.now(),info_string,num_batches,mn,sd)) #預測 def run_benchmark(): with tf.Graph().as_default(): image_size=224 images=tf.Variable(tf.random_normal([batch_size,image_size,image_size,3],dtype=tf.float32,stddev=1e-1)) keep_prob=tf.placeholder(tf.float32) predictions,softmax,fc8,p=inference_op(images,keep_prob) init=tf.global_variables_initializer() sess=tf.Session() sess.run(init) time_tensorflow_run(sess,predictions,{keep_prob:1.0},"Forward") objective=tf.nn.l2_loss(fc8) grad=tf.gradients(objective,p) time_tensorflow_run(sess,grad,{keep_prob:0.5},"Forward-backward") #訓練 batch_size=32 num_batches=100 run_benchmark()