tensorflow基于卷积神经网络实现表情识别分类
一、模型一
from __future__ import division, print_function, absolute_import
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d, avg_pool_2d
from tflearn.layers.normalization import local_response_normalization
from tflearn.layers.merge_ops import merge
from tflearn.layers.estimator import regression
import tflearn
import tensorflow as tf
from PIL import Image
import numpy as np
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.normalization import local_response_normalization
from tflearn.layers.estimator import regression
from sklearn.model_selection import train_test_split
# from sklearn.cross_validation import train_test_split
from tflearn.layers.normalization import batch_normalization
from tflearn.layers.merge_ops import merge
#n = 5
#X = np.load("C:/Users/ivylab/Desktop/FFF/image1.npy")/255
#Y = np.load("C:/Users/ivylab/Desktop/FFF/labels1.npy")
X = np.load(r"D:\FER2013\aaa\ffff\8-8/fer-mouth.npy")/255
Y = np.load(r"D:\FER2013\aaa\ffff\8-8/fer-mouth-label.npy")
X = X[:, :, :, np.newaxis]
# print(labels)
#X, X0, Y, Y0 = train_test_split(image / 255, labels, test_size=0)
#X = X[:, :, :, np.newaxis]
def net():
img_prep = tflearn.ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# img_aug = tflearn.ImageAugmentation()
# img_aug.add_random_flip_leftright()
# img_aug.add_random_blur()
# img_aug.add_random_rotation(5.0)
network = input_data(shape=[None, 48, 48, 1])
# network = conv_2d(network, 64, 3, activation='relu')
# network = max_pool_2d(network, 3, strides=2)
# network = batch_normalization(network)
# conv1_7_7 = conv_2d(network, 64, 7, strides=2, activation='relu', name='conv1_7_7_s2')
# pool1_3_3 = max_pool_2d(conv1_7_7, 3, strides=2)
# pool1_3_3 = local_response_normalization(pool1_3_3)
# conv2_3_3_reduce = conv_2d(pool1_3_3, 64, 1, activation='relu', name='conv2_3_3_reduce')
# conv2_3_3 = conv_2d(conv2_3_3_reduce, 192, 3, activation='relu', name='conv2_3_3')
# conv2_3_3 = local_response_normalization(conv2_3_3)
# pool2_3_3 = max_pool_2d(conv2_3_3, kernel_size=3, strides=2, name='pool2_3_3_s2')
# 3a
# inception_3a_1_1 = conv_2d(network, 64, 1, activation='relu')
## inception_3a_1_1 = batch_normalization(inception_3a_1_1 )
# inception_3a_3_3_reduce = conv_2d(network, 96, 1, activation='relu', name='inception_3a_3_3_reduce')
## inception_3a_3_3_reduce = batch_normalization(inception_3a_3_3_reduce )
# inception_3a_3_3 = conv_2d(inception_3a_3_3_reduce, 128, filter_size=3, activation='relu')
# inception_3a_5_5_reduce = conv_2d(network, 16, filter_size=1, activation='relu', name='inception_3a_5_5_reduce')
# inception_3a_5_5 = conv_2d(inception_3a_5_5_reduce, 32, filter_size=5, activation='relu', name='inception_3a_5_5')
# inception_3a_pool = max_pool_2d(network, kernel_size=3, strides=1)
## inception_3a_3_3_reduce = batch_normalization(inception_3a_pool )
# inception_3a_pool_1_1 = conv_2d(inception_3a_pool, 32, filter_size=1, activation='relu')
# inception_3a_output = merge([inception_3a_1_1, inception_3a_3_3, inception_3a_5_5, inception_3a_pool_1_1],
# mode='concat', axis=3)
# network1 = max_pool_2d(inception_3a_output, kernel_size=3, strides=2, name='pool3_3_3')
# network1 = batch_normalization( network1)
# # 3b
# inception_3b_1_1 = conv_2d(inception_3a_output, 128, filter_size=1, activation='relu', name='inception_3b_1_1')
# inception_3b_3_3_reduce = conv_2d(inception_3a_output, 128, filter_size=1, activation='relu',
# name='inception_3b_3_3_reduce')
# inception_3b_3_3 = conv_2d(inception_3b_3_3_reduce, 192, filter_size=3, activation='relu', name='inception_3b_3_3')
# inception_3b_5_5_reduce = conv_2d(inception_3a_output, 32, filter_size=1, activation='relu',
# name='inception_3b_5_5_reduce')
# inception_3b_5_5 = conv_2d(inception_3b_5_5_reduce, 96, filter_size=5, name='inception_3b_5_5')
# inception_3b_pool = max_pool_2d(inception_3a_output, kernel_size=3, strides=1, name='inception_3b_pool')
# inception_3b_pool_1_1 = conv_2d(inception_3b_pool, 64, filter_size=1, activation='relu',
# name='inception_3b_pool_1_1')
# inception_3b_output = merge([inception_3b_1_1, inception_3b_3_3, inception_3b_5_5, inception_3b_pool_1_1],
# mode='concat', axis=3, name='inception_3b_output')
# network1 = max_pool_2d(inception_3b_output, kernel_size=3, strides=2, name='pool3_3_3')
# network = fully_connected(network1, 2048, activation='tanh')
# network = dropout(network, 0.5)
# network = fully_connected(network, 1024, activation='tanh')
# network = dropout(network, 0.5)
# # network = fully_connected(network, 2, activation='softmax',restore=False)
# network = fully_connected(network, 2, activation='softmax')
network = conv_2d(network, 64, 3,activation='relu' ) #22*22*32
network = max_pool_2d(network, 3, strides=2) #11*11*32
network = batch_normalization(network)
network = conv_2d(network, 96, 3, activation='relu') #11*11*96
network = max_pool_2d(network, 3, strides=2) # 5*5*96
network = batch_normalization(network)
# network = conv_2d(network, 128, 3, activation='relu')
# network = conv_2d(network, 96, 5, activation='relu')
# network = fully_connected(network, 256, activation='tanh' )
# network = dropout(network, 0.5)
network = conv_2d(network, 96, 1, activation='relu') #11*11*96
# network = fully_connected(network, 1024, activation='tanh' )
network = dropout(network, 0.5)
# network = fully_connected(network, 2, activation='softmax')
network = fully_connected(network, 2, activation='softmax',restore=False)
# network = regression(network, optimizer=tflearn.optimizers.Momentum(lr_decay=0.96),
# loss='categorical_crossentropy',
# learning_rate=0.001)
# network = max_pool_2d(network, 3, strides=2) # 5*5*96
# network = batch_normalization(network)
# network = regression(network,optimizer='momentum',loss='categorical_crossentropy',learning_rate=0.001)
# network = regression(network,optimizer=tflearn.optimizers.Momentum(lr_decay=0.96),loss='categorical_crossentropy',learning_rate=0.0001)
network = regression(network, optimizer=tflearn.optimizers.Momentum(lr_decay=0.96, decay_step=2000),
loss='categorical_crossentropy',
learning_rate=0.001)
return network
# Training
max_test_acu = 0
test_all = []
train_all = []
ss = []
for i in range(4):
prediction = []
test_X = X[1000 * i:1000 * i + 1000, :, :, :]
np.save(r'D:\FER2013\aaa\ffff\8-8/' + "test" + str(i) + "-" + "img", test_X)
test_Y = Y[1000 * i:1000 * i + 1000, :]
np.save(r'D:\FER2013\aaa\ffff\8-8/' + "test" + str(i) + "-" + "label", test_Y)
train_X = np.delete(X, range(1000 * i, 1000 * i + 1000), axis=0)
np.save(r'D:\FER2013\aaa\ffff\8-8/' + "train" + str(i) + "-" + "img", train_X)
train_Y = np.delete(Y, range(1000 * i, 1000 * i + 1000), axis=0)
np.save(r'D:\FER2013\aaa\ffff\8-8/' + "train" + str(i) + "-" + "label", train_Y)
test_acu = []
train_acu = []
tf.reset_default_graph()
network = net()
model = tflearn.DNN(network, checkpoint_path='model_alexnet',
max_checkpoints=1, tensorboard_verbose=0)
# model.load("D:/train/fei/yu_Model.tfl")
for j in range(100):
print("********")
print(i)
model.fit(train_X, train_Y, n_epoch=1, shuffle=True,
show_metric=True, batch_size=8, snapshot_step=1000,
snapshot_epoch=False, run_id='alexnet_fer2013')
acu_train = model.evaluate(train_X, train_Y)
acu_test = model.evaluate(test_X, test_Y)
train_acu.append(acu_train[0])
test_acu.append(acu_test[0])
# for index in range(len(test_X)):
# test_X1=test_X[index]
# test_X2=test_X1.reshape(1,48,48,1)
# a=model.predict(test_X2)
# prediction.append(a)
# prediction1=np.array(prediction)
# np.save('D:/toupiao'+str(i)+"-prediction1.npy",prediction1)
## for index in range(len(test_X)):
## test_X=test_X[index:index+1,:,:,:]
# test_X1=test_X[index]
## test_X1=test_X[0]
# test_X2=test_X1.reshape(1,48,48,1)
# a=model.predict(test_X2)
#
#
# prediction.append(a)
if acu_test[0] > max_test_acu:
max_test_acu = acu_test[0]
model.save(r'D:\FER2013\aaa\ffff\8-8/' + str(j) + "-" + str(i) + "new_model.tfl")
for index in range(len(test_X)):
test_X1 = test_X[index]
test_X2 = test_X1.reshape(1, 48, 48, 1)
a = model.predict(test_X2)
prediction.append(a)
prediction1 = np.array(prediction)
np.save(r'D:\FER2013\aaa\ffff\8-8/' + str(i) + "-prediction1.npy", prediction1)
else:
continue
# for index in range(len(test_X)):
# test_X1=test_X[index]
# test_X2=test_X1.reshape(1,48,48,1)
# a=model.predict(test_X2)
# prediction.append(a)
# prediction1=np.array(prediction)
# np.save('D:/tou_piao/'+str(i)+"-prediction1.npy",prediction1)
# if(acu_test>max_test_acu):
# model.save("D:/train/aa/"+str(i)+"-new_model.tfl")
test_all.append(test_acu)
train_all.append(train_acu)
aaa = np.array(test_all).reshape(4, 100)
bbb = np.array(train_all).reshape(4, 100)
np.save(r'D:\FER2013\aaa\ffff\8-8/test_all.npy', aaa)
np.save(r'D:\FER2013\aaa\ffff\8-8/train_all.npy', bbb)
s = 0
avg = 0
for m in range(4):
avg = avg + max(aaa[m])
s = max(aaa[m])
ss.append(s)
ss = np.array(ss)
np.save(r'D:\FER2013\aaa\ffff\8-8/test.npy', ss)
# np.save('x_shuffle.npy',X)
# np.save('y_shuffle.npy',Y)
print("*********avg")
print(avg / 4)
print("**^^^")
print(ss)
# result_all=np.vstack((result1,result2,result3,result4,result5,result6,result7,result8,result9,result10))
print('fcn_Done!')
model.save(r"D:\FER2013\aaa\ffff\8-8/FCN.tfl")
二、模型二
from __future__ import division, print_function, absolute_import
import tflearn
import tensorflow as tf
from PIL import Image
import numpy as np
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.normalization import local_response_normalization
from tflearn.layers.estimator import regression
#from sklearn.model_selection import train_test_split
from sklearn.cross_validation import train_test_split # 大机器
from tflearn.layers.normalization import batch_normalization
#image = np.load("D:/lfw_new_image_48.npy")
#labels = np.load("D:/lfw_new_lable_48.npy")
## print(image)
#print('*****')
## print(labels)
#X, X0, Y, Y0 = train_test_split(image / 255, labels, test_size=0)
#X = X[:, :, :, np.newaxis]
##train_X = X[0:7000, :, :, :]
##train_Y = Y[0:7000, :]
##test_X = X[7000:7750, :, :, :]
##test_Y = Y[7000:7750, :]
#X=np.load("C:/Users/ivylab/Desktop/FFF/image.npy")
##X=X[:,:,:,np.newaxis]
#Y=np.load("C:/Users/ivylab/Desktop/FFF/labels.npy")
X = np.load(r"D:\FER2013\aaa\ffff\8-8/fer-mouth.npy")/255
Y = np.load(r"D:\FER2013\aaa\ffff\8-8/fer-mouth-label.npy")
X = X[:, :, :, np.newaxis]
# Building 'AlexNet'
def net():
img_prep = tflearn.ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
#
# img_aug = tflearn.ImageAugmentation()
# img_aug.add_random_flip_leftright()
## img_aug.add_random_blur()
# img_aug.add_random_rotation(2.0)
network = input_data(shape=[None, 48, 48, 1])
network = conv_2d(network, 64, 3, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = batch_normalization(network)
network = conv_2d(network, 128, 3, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = batch_normalization(network)
network = fully_connected(network, 1024, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 1024, activation='tanh')
network = dropout(network, 0.5)
# network = fully_connected(network, 2, activation='softmax',restore=False)
network = fully_connected(network, 2, activation='softmax')
# network = regression(network,optimizer='momentum',loss='categorical_crossentropy',learning_rate=0.001)
# network = regression(network,optimizer=tflearn.optimizers.Momentum(lr_decay=0.96),loss='categorical_crossentropy',learning_rate=0.0001)
network = regression(network, optimizer=tflearn.optimizers.Momentum(lr_decay=0.96,decay_step=2000),
loss='categorical_crossentropy',
learning_rate=0.001)
return network
# Training
max_test_acu = 0
test_all=[]
train_all=[]
ss=[]
for i in range(4):
prediction=[]
test_X=X[1000*i:1000*i+1000,:,:,:]
np.save('D:/toupiao/'+"test"+str(i)+"-"+"img",test_X)
test_Y=Y[1000*i:1000*i+1000,:]
np.save('D:/toupiao/'+"test"+str(i)+"-"+"label",test_Y)
train_X=np.delete(X,range(1000*i,1000*i+1000),axis=0)
np.save('D:/toupiao/'+"train"+str(i)+"-"+"img",train_X)
train_Y=np.delete(Y,range(1000*i,1000*i+1000),axis=0)
np.save('D:/toupiao/'+"train"+str(i)+"-"+"label",train_Y)
test_acu = []
train_acu = []
tf.reset_default_graph()
network=net()
model = tflearn.DNN(network, checkpoint_path='model_alexnet',
max_checkpoints=1, tensorboard_verbose=0)
# model.load('D:/train/ee/yu_Model.tfl')
for j in range(100):
print("********")
print(i)
model.fit(train_X, train_Y, n_epoch=1, shuffle=True,
show_metric=True, batch_size=8, snapshot_step=1000,
snapshot_epoch=False, run_id='alexnet_fer2013')
acu_train = model.evaluate(train_X, train_Y)
acu_test = model.evaluate(test_X, test_Y)
train_acu.append(acu_train[0])
test_acu.append(acu_test[0])
# for index in range(len(test_X)):
# test_X1=test_X[index]
# test_X2=test_X1.reshape(1,48,48,1)
# a=model.predict(test_X2)
# prediction.append(a)
# prediction1=np.array(prediction)
# np.save('D:/toupiao'+str(i)+"-prediction1.npy",prediction1)
## for index in range(len(test_X)):
## test_X=test_X[index:index+1,:,:,:]
# test_X1=test_X[index]
## test_X1=test_X[0]
# test_X2=test_X1.reshape(1,48,48,1)
# a=model.predict(test_X2)
#
#
# prediction.append(a)
if acu_test[0]>max_test_acu:
max_test_acu = acu_test[0]
# model.save("D:/toupiao2/model/"+str(j)+"-"+str(i)+"new_model.tfl")
for index in range(len(test_X)):
test_X1=test_X[index]
test_X2=test_X1.reshape(1,48,48,1)
a=model.predict(test_X2)
prediction.append(a)
prediction1=np.array(prediction)
np.save('D:/tou_piao/'+str(i)+"-prediction1.npy",prediction1)
else:
continue
# for index in range(len(test_X)):
# test_X1=test_X[index]
# test_X2=test_X1.reshape(1,48,48,1)
# a=model.predict(test_X2)
# prediction.append(a)
# prediction1=np.array(prediction)
# np.save('D:/tou_piao/'+str(i)+"-prediction1.npy",prediction1)
# if(acu_test>max_test_acu):
# model.save("D:/train/aa/"+str(i)+"-new_model.tfl")
test_all.append(test_acu)
train_all.append(train_acu)
aaa=np.array(test_all).reshape(4,100)
bbb=np.array(train_all).reshape(4,100)
np.save('D:/tou_piao/test_all.npy',aaa)
np.save('D:/tou_piao/train_all.npy',bbb)
s=0
avg=0
for m in range(4):
avg=avg+max(aaa[m])
s=max(aaa[m])
ss.append(s)
ss=np.array(ss)
np.save('D:/tou_piao/test.npy',ss)
#np.save('x_shuffle.npy',X)
#np.save('y_shuffle.npy',Y)
print("*********avg")
print(avg/4)
print("**^^^")
print(ss)
#result_all=np.vstack((result1,result2,result3,result4,result5,result6,result7,result8,result9,result10))
print('tenfold_Done!')
#print(np.max(test_acu))
#print("@@@@@@@@@@")
#for index in test_acu:
# print(index)
#print("********")
#for index in train_acu:
# print(index)
#
model.save("D:/train/bb/yu_Model.tfl")
2万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
