Tensorboard可視化：基于LeNet5進行面部表情分類
日期：2021.09.20 來源：湖南檢信智能
檢信智能為群體性人群提供高頻次AI心理情緒監測服務
加盟合作：
191-1881-8899
服務熱線：
0731-82298661
Tensorboard可視化：基于LeNet5進行面部表情分類
面部表情分類
面部表情是面部肌肉的一個或多個動作或狀態的結果。這些運動表達了個體對觀察者的情緒狀態。面部表情是非語言交際的一種形式。它是表達人類之間的社會信息的主要手段，不過也發生在大多數其他哺乳動物和其他一些動物物種中。人類的面部表情至少有21種，除了常見的高興、吃驚、悲傷、憤怒、厭惡和恐懼6種，還有驚喜（高興＋吃驚）、悲憤（悲傷＋憤怒）等15種可被區分的復合表情。
面部表情識別技術主要的應用領域包括人機交互、智能控制、安全、醫療、通信等領域。
網絡架構
LeNet-5出自論文Gradient-Based Learning Applied to Document Recognition，是一種用于手寫體字符識別的非常高效的卷積神經網絡。LeNet5的網絡架構如下：
但是因為我們要做的是面部表情分類，而且CK+數據集樣本大小是48*48，因此需要對LeNet5網絡進行微調。網絡架構如下：
網絡結構如下：
計算圖如下：
代碼實現
預處理
數據集加載，并進行預處理，同時將測試集的前225張樣本拼接成15張*15張的大圖片，用于Tensorboard可視化。
%matplotlib inline
import matplotlib.pyplot as plt
import os
import cv2
import numpy as np
from tensorflow import name_scope as namespace
from tensorflow.contrib.tensorboard.plugins import projector
NUM_PIC_SHOW=225
base_filedir='D:/CV/datasets/facial_exp/CK+'
dict_str2int={'anger':0,'contempt':1,'disgust':2,'fear':3,'happy':4,'sadness':5,'surprise':6}
labels=[]
data=[]
#讀取圖片并將其保存至data
for expdir in os.listdir(base_filedir):
base_expdir=os.path.join(base_filedir,expdir)
for name in os.listdir(base_expdir):
labels.append(dict_str2int[expdir])
path=os.path.join(base_expdir,name)
path=path.replace('\\','/') #將\替換為/
img = cv2.imread(path,0)
data.append(img)
data=np.array(data)
labels=np.array(labels)
#將data打亂
permutation = np.random.permutation(data.shape[0])
data = data[permutation,:,:]
labels = labels[permutation]
#取前225個圖片拼成一張大圖片，用于tensorboard可視化
img_set=data[:NUM_PIC_SHOW]#前225的數據用于顯示
label_set=labels[:NUM_PIC_SHOW]
big_pic=None
index=0
for row in range(15):
row_vector=img_set[index]
index+=1
for col in range(1,15):
img=img_set[index]
row_vector=np.hstack([row_vector,img])
index+=1
if(row==0):
big_pic=row_vector
else:
big_pic=np.vstack([big_pic,row_vector])
plt.imshow(big_pic, cmap='gray')
plt.show()
#寫入大圖片
cv2.imwrite("D:/Jupyter/TensorflowLearning/facial_expression_cnn_projector/data/faces.png",big_pic)
#轉換數據格式和形狀
data=data.reshape(-1,48*48).astype('float32')/255.0
labels=labels.astype('float32')
#0.3的比例測試
scale=0.3
test_data=data[:int(scale*data.shape[0])]
test_labels=labels[:int(scale*data.shape[0])]
train_data=data[int(scale*data.shape[0]):]
train_labels=labels[int(scale*data.shape[0]):]
print(train_data.shape)
print(train_labels.shape)
print(test_data.shape)
print(test_labels.shape)
#將標簽one-hot
train_labels_onehot=np.zeros((train_labels.shape[0],7))
test_labels_onehot=np.zeros((test_labels.shape[0],7))
for i,label in enumerate(train_labels):
train_labels_onehot[i,int(label)]=1
for i,label in enumerate(test_labels):
test_labels_onehot[i,int(label)]=1
print(train_labels_onehot.shape)
print(test_labels_onehot.shape)
2.定義前向網絡
import tensorflow as tf
IMAGE_SIZE=48 #圖片大小
NUM_CHANNELS=1 #圖片通道
CONV1_SIZE=5
CONV1_KERNEL_NUM=32
CONV2_SIZE=5
CONV2_KERNEL_NUM=64
FC_SIZE=512 #隱層大小
OUTPUT_NODE=7 #輸出大小
#參數概要，用于tensorboard實時查看訓練過程
def variable_summaries(var):
with namespace('summaries'):
mean=tf.reduce_mean(var)
tf.summary.scalar('mean',mean) #平均值
with namespace('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
#獲取權重
def get_weight(shape,regularizer,name=None):
w=tf.Variable(tf.truncated_normal(shape,stddev=0.1),name=name)
#variable_summaries(w)
if(regularizer!=None):
tf.add_to_collection('losses',tf.contrib.layers.l2_regularizer(regularizer)(w))
return w
#獲取偏置
def get_bias(shape,name=None):
b=tf.Variable(tf.zeros(shape),name=name)
#variable_summaries(b)
return b
#定義前向網絡
def forward(x,train,regularizer):
with tf.name_scope('layer'):
#把輸入reshape
with namespace('reshape_input'):
x_reshaped=tf.reshape(x,[-1,IMAGE_SIZE,IMAGE_SIZE,NUM_CHANNELS])
with tf.name_scope('conv1'):
#定義兩個卷積層
conv1_w=get_weight([CONV1_SIZE,CONV1_SIZE,NUM_CHANNELS,CONV1_KERNEL_NUM],regularizer=regularizer,name='conv1_w')
conv1_b=get_bias([CONV1_KERNEL_NUM],name='conv1_b')
conv1=tf.nn.conv2d(x_reshaped,conv1_w,strides=[1,1,1,1],padding='SAME')
relu1=tf.nn.relu(tf.nn.bias_add(conv1,conv1_b))
pool1=tf.nn.max_pool(relu1,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
with tf.name_scope('conv2'):
conv2_w=get_weight([CONV2_SIZE,CONV2_SIZE,CONV1_KERNEL_NUM,CONV2_KERNEL_NUM],regularizer=regularizer,name='conv2_w')
conv2_b=get_bias([CONV2_KERNEL_NUM],name='conv2_b')
conv2=tf.nn.conv2d(pool1,conv2_w,strides=[1,1,1,1],padding='SAME')
relu2=tf.nn.relu(tf.nn.bias_add(conv2,conv2_b)) #對卷機后的輸出添加偏置，并通過relu完成非線性激活
pool2=tf.nn.max_pool(relu2,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
with tf.name_scope('flatten'):
#定義reshape層
pool_shape=pool2.get_shape().as_list() #獲得張量的維度并轉換為列表
nodes=pool_shape[1]*pool_shape[2]*pool_shape[3] #[0]為batch值，[1][2][3]分別為長寬和深度
#print(type(pool2))
reshaped=tf.reshape(pool2,[-1,nodes])
with tf.name_scope('fc1'):
#定義兩層全連接層
fc1_w=get_weight([nodes,FC_SIZE],regularizer,name='fc1_w')
fc1_b=get_bias([FC_SIZE],name='fc1_b')
fc1=tf.nn.relu(tf.matmul(reshaped,fc1_w)+fc1_b)
if(train):
fc1=tf.nn.dropout(fc1,0.5)
with tf.name_scope('fc2'):
fc2_w=get_weight([FC_SIZE,OUTPUT_NODE],regularizer,name='fc2_w')
fc2_b=get_bias([OUTPUT_NODE],name='fc2_b')
y=tf.matmul(fc1,fc2_w)+fc2_b
return y
3.定義反向傳播 ，可視化設置，并進行訓練，
BATCH_SIZE=100 #每次樣本數
LEARNING_RATE_BASE=0.005 #基本學習率
LEARNING_RATE_DECAY=0.99 #學習率衰減率
REGULARIZER=0.0001 #正則化系數
STEPS=2500 #訓練次數
MOVING_AVERAGE_DECAY=0.99 #滑動平均衰減系數
SAVE_PATH='.\\facial_expression_cnn_projector\\' #參數保存路徑
data_len=train_data.shape[0]
#將拼接為big_pic的測試樣本保存至標量，用于訓練過程可視化
pic_stack=tf.stack(test_data[:NUM_PIC_SHOW]) #stack拼接圖片張量
embedding=tf.Variable(pic_stack,trainable=False,name='embedding')
if(tf.gfile.Exists(os.path.join(SAVE_PATH,'projector'))==False):
tf.gfile.MkDir(os.path.join(SAVE_PATH,'projector'))
#創建metadata文件，存放可視化圖片的label
if(tf.gfile.Exists(os.path.join(SAVE_PATH,'projector','metadata.tsv'))==True):
tf.gfile.DeleteRecursively(os.path.join(SAVE_PATH,'projector'))
tf.gfile.MkDir(os.path.join(SAVE_PATH,'projector'))
#將可視化圖片的標簽寫入
with open(os.path.join(SAVE_PATH,'projector','metadata.tsv'),'w') as f:
for i in range(NUM_PIC_SHOW):
f.write(str(label_set[i])+'\n')
with tf.Session() as sess:
with tf.name_scope('input'):
#x=tf.placeholder(tf.float32,[BATCH_SIZE,IMAGE_SIZE,IMAGE_SIZE,NUM_CHANNELS],name='x_input')
x=tf.placeholder(tf.float32,[None,IMAGE_SIZE*IMAGE_SIZE*NUM_CHANNELS],name='x_input')
y_=tf.placeholder(tf.float32,[None,OUTPUT_NODE],name='y_input')
#reshape可視化圖片
with namespace('input_reshape'):
image_shaped_input=tf.reshape(x,[-1,IMAGE_SIZE,IMAGE_SIZE,1]) #把輸入reshape
tf.summary.image('input',image_shaped_input,7) #添加到tensorboard中顯示
y=forward(x,True,REGULARIZER)
global_step=tf.Variable(0,trainable=False)
with namespace('loss'):
#softmax并計算交叉熵
ce=tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y,labels=tf.argmax(y_,1))
cem=tf.reduce_mean(ce) #求每個樣本的交叉熵
loss=cem+tf.add_n(tf.get_collection('losses'))
tf.summary.scalar('loss',loss) #loss只有一個值，就直接輸出
learning_rate=tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,
data_len/BATCH_SIZE,
LEARNING_RATE_DECAY,
staircase=True
)
with namespace('train'):
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 namespace('accuracy'):
correct_prediction=tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
tf.summary.scalar('accuracy',accuracy)
with tf.control_dependencies([train_step,ema_op]):
train_op=tf.no_op(name='train')
init_op=tf.global_variables_initializer()
sess.run(init_op)
#合并所有的summary
merged=tf.summary.merge_all()
#寫入圖結構
writer=tf.summary.FileWriter(os.path.join(SAVE_PATH,'projector'),sess.graph)
saver=tf.train.Saver() #保存網絡的模型
#配置可視化
config=projector.ProjectorConfig() #tensorboard配置對象
embed=config.embeddings.add() #增加一項
embed.tensor_name=embedding.name #指定可視化的變量
embed.metadata_path='D:/Jupyter/TensorflowLearning/facial_expression_cnn_projector/projector/metadata.tsv' #路徑
embed.sprite.image_path='D:/Jupyter/TensorflowLearning/facial_expression_cnn_projector/data/faces.png'
embed.sprite.single_image_dim.extend([IMAGE_SIZE,IMAGE_SIZE])#可視化圖片大小
projector.visualize_embeddings(writer,config)
#斷點續訓
#ckpt=tf.train.get_checkpoint_state(MODEL_SAVE_PATH)
#if(ckpt and ckpt.model_checkpoint_path):
# saver.restore(sess,ckpt.model_checkpoint_path)
for i in range(STEPS):
run_option=tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_metadata=tf.RunMetadata()
start=(i*BATCH_SIZE)%(data_len-BATCH_SIZE)
end=start+BATCH_SIZE
summary,_,loss_value,step=sess.run([merged,train_op,loss,global_step],
feed_dict={x:train_data[start:end],y_:train_labels_onehot[start:end]},
options=run_option,
run_metadata=run_metadata)
writer.add_run_metadata(run_metadata,'step%03d'%i)
writer.add_summary(summary,i)#寫summary和i到文件
if(i%100==0):
acc=sess.run(accuracy,feed_dict={x:test_data,y_:test_labels_onehot})
print('%d %g'%(step,loss_value))
print('acc:%f'%(acc))
saver.save(sess,os.path.join(SAVE_PATH,'projector','model'),global_step=global_step)
writer.close()
可視化訓練過程
執行上面的代碼，打開tensorboard，可以看到訓練精度和交叉熵損失如下：
由于只有六百多的訓練樣本，故得到曲線抖動很大，訓練精度大概在百分之八九十多浮動，測試精度在百分之七八十浮動，可見精度不高。下面使用Tensorboard將訓練過程可視化(圖片是用Power Point錄頻 然后用迅雷應用截取gif得到的)：
————————————————
版權聲明：本文為CSDN博主「陳建驅」的原創文章，遵循 CC 4.0 BY-SA 版權協議，轉載請附上原文出處鏈接及本聲明。
檢信智能公眾號