tensorflow學(xué)習(xí)使用路線
一、學(xué)習(xí)路線
個人感覺對于任何一個深度學(xué)習(xí)庫,如mxnet、tensorflow、theano、caffe等,基本上我都采用同樣的一個學(xué)習(xí)流程,大體流程如下:
(1)訓(xùn)練階段:數(shù)據(jù)打包-》網(wǎng)絡(luò)構(gòu)建、訓(xùn)練-》模型保存-》可視化查看損失函數(shù)、驗(yàn)證精度
(2)測試階段:模型加載-》測試圖片讀取-》預(yù)測顯示結(jié)果
(3)移植階段:量化、壓縮加速-》微調(diào)-》C++移植打包-》上線
這邊我就以tensorflow為例子,講解整個流程的大體架構(gòu),完成一個深度學(xué)習(xí)項(xiàng)目所需要熟悉的過程代碼。
二、訓(xùn)練、測試階段
1、tensorflow打包數(shù)據(jù)
這一步對于tensorflow來說,也可以直接自己在線讀?。?jpg圖片、標(biāo)簽文件等,然后通過phaceholder變量,把數(shù)據(jù)送入網(wǎng)絡(luò)中,進(jìn)行計算。
不過這種效率比較低,對于大規(guī)模訓(xùn)練數(shù)據(jù)來說,我們需要一個比較高效的方式,tensorflow建議我們采用tfrecoder進(jìn)行高效數(shù)據(jù)讀取。學(xué)習(xí)tensorflow一定要學(xué)會tfrecoder文件寫入、讀取,具體示例代碼如下:
[python]view plaincopy#coding=utf-8 #tensorflow高效數(shù)據(jù)讀取訓(xùn)練 importtensorflowastf importcv2 #把train.txt文件格式,每一行:圖片路徑名類別標(biāo)簽 #獎數(shù)據(jù)打包,轉(zhuǎn)換成tfrecords格式,以便后續(xù)高效讀取 defencode_to_tfrecords(lable_file,data_root,new_name='data.tfrecords',resize=None): writer=tf.python_io.TFRecordWriter(data_root+'/'+new_name) num_example=0 withopen(lable_file,'r')asf: forlinf.readlines(): l=l.split() image=cv2.imread(data_root+"/"+l[0]) ifresizeisnotNone: image=cv2.resize(image,resize)#為了 height,width,nchannel=image.shape label=int(l[1]) example=tf.train.Example(features=tf.train.Features(feature={ 'height':tf.train.Feature(int64_list=tf.train.Int64List(value=[height])), 'width':tf.train.Feature(int64_list=tf.train.Int64List(value=[width])), 'nchannel':tf.train.Feature(int64_list=tf.train.Int64List(value=[nchannel])), 'image':tf.train.Feature(bytes_list=tf.train.BytesList(value=[image.tobytes()])), 'label':tf.train.Feature(int64_list=tf.train.Int64List(value=[label])) })) serialized=example.SerializeToString() writer.write(serialized) num_example+=1 printlable_file,"樣本數(shù)據(jù)量:",num_example writer.close() #讀取tfrecords文件 defdecode_from_tfrecords(filename,num_epoch=None): filename_queue=tf.train.string_input_producer([filename],num_epochs=num_epoch)#因?yàn)橛械挠?xùn)練數(shù)據(jù)過于龐大,被分成了很多個文件,所以第一個參數(shù)就是文件列表名參數(shù) reader=tf.TFRecordReader() _,serialized=reader.read(filename_queue) example=tf.parse_single_example(serialized,features={ 'height':tf.FixedLenFeature([],tf.int64), 'width':tf.FixedLenFeature([],tf.int64), 'nchannel':tf.FixedLenFeature([],tf.int64), 'image':tf.FixedLenFeature([],tf.string), 'label':tf.FixedLenFeature([],tf.int64) }) label=tf.cast(example['label'],tf.int32) image=tf.decode_raw(example['image'],tf.uint8) image=tf.reshape(image,tf.pack([ tf.cast(example['height'],tf.int32), tf.cast(example['width'],tf.int32), tf.cast(example['nchannel'],tf.int32)])) #label=example['label'] returnimage,label #根據(jù)隊(duì)列流數(shù)據(jù)格式,解壓出一張圖片后,輸入一張圖片,對其做預(yù)處理、及樣本隨機(jī)擴(kuò)充 defget_batch(image,label,batch_size,crop_size): #數(shù)據(jù)擴(kuò)充變換 distorted_image=tf.random_crop(image,[crop_size,crop_size,3])#隨機(jī)裁剪 distorted_image=tf.image.random_flip_up_down(distorted_image)#上下隨機(jī)翻轉(zhuǎn) #distorted_image=tf.image.random_brightness(distorted_image,max_delta=63)#亮度變化 #distorted_image=tf.image.random_contrast(distorted_image,lower=0.2,upper=1.8)#對比度變化 #生成batch #shuffle_batch的參數(shù):capacity用于定義shuttle的范圍,如果是對整個訓(xùn)練數(shù)據(jù)集,獲取batch,那么capacity就應(yīng)該夠大 #保證數(shù)據(jù)打的足夠亂 images,label_batch=tf.train.shuffle_batch([distorted_image,label],batch_size=batch_size, num_threads=16,capacity=50000,min_after_dequeue=10000) #images,label_batch=tf.train.batch([distorted_image,label],batch_size=batch_size) #調(diào)試顯示 #tf.image_summary('images',images) returnimages,tf.reshape(label_batch,[batch_size]) #這個是用于測試階段,使用的get_batch函數(shù) defget_test_batch(image,label,batch_size,crop_size): #數(shù)據(jù)擴(kuò)充變換 distorted_image=tf.image.central_crop(image,39./45.) distorted_image=tf.random_crop(distorted_image,[crop_size,crop_size,3])#隨機(jī)裁剪 images,label_batch=tf.train.batch([distorted_image,label],batch_size=batch_size) returnimages,tf.reshape(label_batch,[batch_size]) #測試上面的壓縮、解壓代碼 deftest(): encode_to_tfrecords("data/train.txt","data",(100,100)) image,label=decode_from_tfrecords('data/data.tfrecords') batch_image,batch_label=get_batch(image,label,3)#batch生成測試 init=tf.initialize_all_variables() withtf.Session()assession: session.run(init) coord=tf.train.Coordinator() threads=tf.train.start_queue_runners(coord=coord) forlinrange(100000):#每run一次,就會指向下一個樣本,一直循環(huán) #image_np,label_np=session.run([image,label])#每調(diào)用run一次,那么 '''''cv2.imshow("temp",image_np) cv2.waitKey()''' #printlabel_np #printimage_np.shape batch_image_np,batch_label_np=session.run([batch_image,batch_label]) printbatch_image_np.shape printbatch_label_np.shape coord.request_stop()#queue需要關(guān)閉,否則報錯 coord.join(threads) #test()
2、網(wǎng)絡(luò)架構(gòu)與訓(xùn)練
經(jīng)過上面的數(shù)據(jù)格式處理,接著我們只要寫一寫網(wǎng)絡(luò)結(jié)構(gòu)、網(wǎng)絡(luò)優(yōu)化方法,把數(shù)據(jù)搞進(jìn)網(wǎng)絡(luò)中就可以了,具體示例代碼如下:
[python]view
plaincopy#coding=utf-8
importtensorflowastf
fromdata_encoder_decoederimportencode_to_tfrecords,decode_from_tfrecords,get_batch,get_test_batch
importcv2
importos
classnetwork(object):
def__init__(self):
withtf.variable_scope("weights"):
self.weights={
#39*39*3->36*36*20->18*18*20
'conv1':tf.get_variable('conv1',[4,4,3,20],initializer=tf.contrib.layers.xavier_initializer_conv2d()),
#18*18*20->16*16*40->8*8*40
'conv2':tf.get_variable('conv2',[3,3,20,40],initializer=tf.contrib.layers.xavier_initializer_conv2d()),
#8*8*40->6*6*60->3*3*60
'conv3':tf.get_variable('conv3',[3,3,40,60],initializer=tf.contrib.layers.xavier_initializer_conv2d()),
#3*3*60->120
'fc1':tf.get_variable('fc1',[3*3*60,120],initializer=tf.contrib.layers.xavier_initializer()),
#120->6
'fc2':tf.get_variable('fc2',[120,6],initializer=tf.contrib.layers.xavier_initializer()),
}
withtf.variable_scope("biases"):
self.biases={
'conv1':tf.get_variable('conv1',[20,],initializer=tf.constant_initializer(value=0.0,dtype=tf.float32)),
'conv2':tf.get_variable('conv2',[40,],initializer=tf.constant_initializer(value=0.0,dtype=tf.float32)),
'conv3':tf.get_variable('conv3',[60,],initializer=tf.constant_initializer(value=0.0,dtype=tf.float32)),
'fc1':tf.get_variable('fc1',[120,],initializer=tf.constant_initializer(value=0.0,dtype=tf.float32)),
'fc2':tf.get_variable('fc2',[6,],initializer=tf.constant_initializer(value=0.0,dtype=tf.float32))
}
definference(self,images):
#向量轉(zhuǎn)為矩陣
images=tf.reshape(images,shape=[-1,39,39,3])#[batch,in_height,in_width,in_channels]
images=(tf.cast(images,tf.float32)/255.-0.5)*2#歸一化處理
#第一層
conv1=tf.nn.bias_add(tf.nn.conv2d(images,self.weights['conv1'],strides=[1,1,1,1],padding='VALID'),
self.biases['conv1'])
relu1=tf.nn.relu(conv1)
pool1=tf.nn.max_pool(relu1,ksize=[1,2,2,1],strides=[1,2,2,1],padding='VALID')
#第二層
conv2=tf.nn.bias_add(tf.nn.conv2d(pool1,self.weights['conv2'],strides=[1,1,1,1],padding='VALID'),
self.biases['conv2'])
relu2=tf.nn.relu(conv2)
pool2=tf.nn.max_pool(relu2,ksize=[1,2,2,1],strides=[1,2,2,1],padding='VALID')
#第三層
conv3=tf.nn.bias_add(tf.nn.conv2d(pool2,self.weights['conv3'],strides=[1,1,1,1],padding='VALID'),
self.biases['conv3'])
relu3=tf.nn.relu(conv3)
pool3=tf.nn.max_pool(relu3,ksize=[1,2,2,1],strides=[1,2,2,1],padding='VALID')
#全連接層1,先把特征圖轉(zhuǎn)為向量
flatten=tf.reshape(pool3,[-1,self.weights['fc1'].get_shape().as_list()[0]])
drop1=tf.nn.dropout(flatten,0.5)
fc1=tf.matmul(drop1,self.weights['fc1'])+self.biases['fc1']
fc_relu1=tf.nn.relu(fc1)
fc2=tf.matmul(fc_relu1,self.weights['fc2'])+self.biases['fc2']
returnfc2
definference_test(self,images):
#向量轉(zhuǎn)為矩陣
images=tf.reshape(images,shape=[-1,39,39,3])#[batch,in_height,in_width,in_channels]
images=(tf.cast(images,tf.float32)/255.-0.5)*2#歸一化處理
#第一層
conv1=tf.nn.bias_add(tf.nn.conv2d(images,self.weights['conv1'],strides=[1,1,1,1],padding='VALID'),
self.biases['conv1'])
relu1=tf.nn.relu(conv1)
pool1=tf.nn.max_pool(relu1,ksize=[1,2,2,1],strides=[1,2,2,1],padding='VALID')
#第二層
conv2=tf.nn.bias_add(tf.nn.conv2d(pool1,self.weights['conv2'],strides=[1,1,1,1],padding='VALID'),
self.biases['conv2'])
relu2=tf.nn.relu(conv2)
pool2=tf.nn.max_pool(relu2,ksize=[1,2,2,1],strides=[1,2,2,1],padding='VALID')
#第三層
conv3=tf.nn.bias_add(tf.nn.conv2d(pool2,self.weights['conv3'],strides=[1,1,1,1],padding='VALID'),
self.biases['conv3'])
relu3=tf.nn.relu(conv3)
pool3=tf.nn.max_pool(relu3,ksize=[1,2,2,1],strides=[1,2,2,1],padding='VALID')
#全連接層1,先把特征圖轉(zhuǎn)為向量
flatten=tf.reshape(pool3,[-1,self.weights['fc1'].get_shape().as_list()[0]])
fc1=tf.matmul(flatten,self.weights['fc1'])+self.biases['fc1']
fc_relu1=tf.nn.relu(fc1)
fc2=tf.matmul(fc_relu1,self.weights['fc2'])+self.biases['fc2']
returnfc2
#計算softmax交叉熵?fù)p失函數(shù)
defsorfmax_loss(self,predicts,labels):
predicts=tf.nn.softmax(predicts)
labels=tf.one_hot(labels,self.weights['fc2'].get_shape().as_list()[1])
loss=-tf.reduce_mean(labels*tf.log(predicts))#tf.nn.softmax_cross_entropy_with_logits(predicts,labels)
self.cost=loss
returnself.cost
#梯度下降
defoptimer(self,loss,lr=0.001):
train_optimizer=tf.train.GradientDescentOptimizer(lr).minimize(loss)
returntrain_optimizer
deftrain():
encode_to_tfrecords("data/train.txt","data",'train.tfrecords',(45,45))
image,label=decode_from_tfrecords('data/train.tfrecords')
batch_image,batch_label=get_batch(image,label,batch_size=50,crop_size=39)#batch生成測試
#網(wǎng)絡(luò)鏈接,訓(xùn)練所用
net=network()
inf=net.inference(batch_image)
loss=net.sorfmax_loss(inf,batch_label)
opti=net.optimer(loss)
#驗(yàn)證集所用
encode_to_tfrecords("data/val.txt","data",'val.tfrecords',(45,45))
test_image,test_label=decode_from_tfrecords('data/val.tfrecords',num_epoch=None)
test_images,test_labels=get_test_batch(test_image,test_label,batch_size=120,crop_size=39)#batch生成測試
test_inf=net.inference_test(test_images)
correct_prediction=tf.equal(tf.cast(tf.argmax(test_inf,1),tf.int32),test_labels)
accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
init=tf.initialize_all_variables()
withtf.Session()assession:
session.run(init)
coord=tf.train.Coordinator()
threads=tf.train.start_queue_runners(coord=coord)
max_iter=100000
iter=0
ifos.path.exists(os.path.join("model",'model.ckpt'))isTrue:
tf.train.Saver(max_to_keep=None).restore(session,os.path.join("model",'model.ckpt'))
whileiter<max_iter:
loss_np,_,label_np,image_np,inf_np=session.run([loss,opti,batch_label,batch_image,inf])
#printimage_np.shape
#cv2.imshow(str(label_np[0]),image_np[0])
#printlabel_np[0]
#cv2.waitKey()
#printlabel_np
ifiter%50==0:
print'trainloss:',loss_np
ifiter%500==0:
accuracy_np=session.run([accuracy])
print'***************testaccruacy:',accuracy_np,'*******************'
tf.train.Saver(max_to_keep=None).save(session,os.path.join('model','model.ckpt'))
iter+=1
coord.request_stop()#queue需要關(guān)閉,否則報錯
coord.join(threads)
train()
3、可視化顯示
(1)首先再源碼中加入需要跟蹤的變量:
[python]view plaincopy