def bidirectional_active_expert():
TrainData, TrainLabels, OracleData, OracleLabels,\
TestData, TestLabels, _, _, lenn_s, lenn_t, _ = load_process()
batch = tf.placeholder(tf.float32,[None,unit.H,unit.W,unit.Channel])
label = tf.placeholder(tf.uint8,[None])
keep_prop = tf.placeholder(tf.float32)
feature = SharePart(batch,keep_prop)
result = MissionPart(feature)
loss = SoftmaxWithLoss(result,label)
acc = Test(result,label)
opt = train_net(loss)
softmax = tf.nn.softmax(result)
entropy = tf.reduce_sum(-softmax * tf.log(softmax),1)
predict_class = tf.cast(tf.argmax(softmax,axis = 1),tf.uint8)
saver = tf.train.Saver(max_to_keep = ACTIVE_TIME)
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.45
config.gpu_options.allow_growth = False
init = tf.global_variables_initializer()
sess = tf.Session(config = config)
sess.run(init)
saver.restore(sess,PRETRAIN_MODEL_NAME)
def test():
ACC = 0
for i in range(lenn_t):
test_batch = TestData[i*BATCH_SIZE:(i+1)*BATCH_SIZE]
test_label = TestLabels[i*BATCH_SIZE:(i+1)*BATCH_SIZE]
ACC+=sess.run(acc,feed_dict={batch:test_batch,label:test_label,keep_prop:1.0})
return ACC/lenn_t
'''Begin Active Learning!'''
log_file = open('./simple_log/'+Experiment_NAME+'_ALBT_man.txt','w')
pretrain_accuracy = test()
print 'the pre train model accuracy is : ', pretrain_accuracy
log_file.write("the pre train model accuracy is " + str(pretrain_accuracy))
log_file.write("\n")
for a in range(ACTIVE_TIME):
oracle_idx = np.arange(len(OracleData))
oracle_que = []
for i in oracle_idx:
candidate_entropy = sess.run(entropy, feed_dict={batch:unit.changeshape_1(OracleData[i]),keep_prop:1.0})
candidate_predict = sess.run(predict_class, feed_dict={batch:unit.changeshape_1(OracleData[i]),keep_prop:1.0})
oracle_que.append((i,candidate_entropy[0],candidate_predict[0]))
oracle_que = sorted(oracle_que, key = lambda candidate:candidate[1], reverse = True)
temp = {}
tag_queue = []
tag_queue2 = []
tag_queue2_labels = []
for k in range(CLASS_NUM):
temp[str(k)] = []
for k in range(len(oracle_que)):
temp[str(oracle_que[k][2])].append(oracle_que[k])
for k in temp:
temp[k] = sorted(temp[k], key=lambda x:x[1], reverse=True)
idx = 0
temp_class = 0
temp_order = range(CLASS_NUM)
shuffle(temp_order)
while(idx<QUEUE_SIZE):
if len(temp[str(temp_order[temp_class])]) != 0:
tag_queue.append(temp[str(temp_order[temp_class])].pop(0)[0])
idx += 1
temp_class = (temp_class+1)%(CLASS_NUM)
else:
temp_class = (temp_class+1)%(CLASS_NUM)
idx = 0
temp_class = 0
while(idx< GOOD_SIZE ):
if len(temp[str(temp_order[temp_class])]) != 0:
tag_temporary = temp[str(temp_order[temp_class])].pop()
tag_queue2.append(tag_temporary[0])
tag_queue2_labels.append(tag_temporary[2])
idx += 1
temp_class = (temp_class + 1)%(CLASS_NUM)
else:
temp_class = (temp_class + 1)%(CLASS_NUM)
##################################not put back ,x_train+x_oracle
# TrainData = np.concatenate((TrainData,OracleData[tag_queue]))
# TrainData = np.concatenate((TrainData,OracleData[tag_queue2]))
# TrainLabels = np.concatenate((TrainLabels, OracleLabels[tag_queue]))
# TrainLabels = np.concatenate((TrainLabels, OracleLabels[tag_queue2]))
# tag_queue2_rlabels = OracleLabels[tag_queue2]
# np.delete(OracleData, tag_queue + tag_queue2), np.delete(OracleLabels,tag_queue + tag_queue2)
##########################################put back, x_train+x_oracle
# TrainData0 = dc(TrainData)
# TrainLabels0 = dc(TrainLabels)
# TrainData0 = np.concatenate((TrainData0,OracleData[tag_queue]))
# TrainLabels0 = np.concatenate((TrainLabels0,OracleLabels[tag_queue]))
# TrainData = np.concatenate((TrainData0, OracleData[tag_queue2]))
# TrainLabels = np.concatenate((TrainLabels0, OracleLabels[tag_queue2]))
# tag_queue2_rlabels = OracleLabels[tag_queue2]
# np.delete(OracleData, tag_queue), np.delete(OracleLabels,tag_queue)
################################################not put back,x_oracle
if a == 0:
TrainData = np.concatenate((OracleData[tag_queue],OracleData[tag_queue2]))
TrainLabels = np.concatenate((OracleLabels[tag_queue], np.array(tag_queue2_labels)))
else:
TrainData = np.concatenate((TrainData,OracleData[tag_queue]))
TrainData = np.concatenate((TrainData,OracleData[tag_queue2]))
TrainLabels = np.concatenate((TrainLabels, OracleLabels[tag_queue]))
TrainLabels = np.concatenate((TrainLabels, np.array(tag_queue2_labels)))
tag_queue2_rlabels = OracleLabels[tag_queue2]
np.delete(OracleData, tag_queue + tag_queue2), np.delete(OracleLabels,tag_queue + tag_queue2)
train_queue = np.arange(len(TrainData))
best = 0
for i in range(EPOCH_all):
shuffle(train_queue)
for j in range(len(TrainData)/BATCH_SIZE):
trainbatch = TrainData[train_queue[j*BATCH_SIZE:(j+1)*BATCH_SIZE]]
trainlabels = TrainLabels[train_queue[j*BATCH_SIZE:(j+1)*BATCH_SIZE]]
sess.run(opt, feed_dict = {batch:trainbatch, label:trainlabels,keep_prop:0.5})
accuracy = test()
print 'the ',a+1, 'time acmodel acc is:', accuracy
if accuracy > best:
best = accuracy
saver.save(sess,MODEL_PATH+Experiment_NAME+'_ALBT_man_'+str(a+1)+'.ckpt')
print 'the ',a+1,' time acmodel best acc is: ', best
cnn_acc = np.float(np.sum(np.equal(tag_queue2_rlabels,np.array(tag_queue2_labels)))) / GOOD_SIZE
log_file.write("the " + str(a+1) + "time acmodel best acc is " + str(best))
log_file.write("\n")
log_file.write("the " + str(a+1) + "time cnn_que acc is " + str(cnn_acc))
log_file.write("\n")
log_file.close()
return
def Test_model_process():
file_test = FILE_PATH + Experiment_NAME + '_x_test.txt'
# file_test2 = FILE_PATH + Experiment_NAME + '_x_oracle.txt'
ac_methods = ['_ALBT_','_ALBT_man_','_ALST_','_ALRA_'] #_ALBT_,_ALST_,_ALRA_
# OList = unit.LoadCarTxT(file_test2)
TestList = unit.LoadCarTxT(file_test)
# OData, OLabels = unit.Getlist(OList)
TestData, TestLabels = unit.Getlist(TestList)
# TestData = np.concatenate((TestData,OData))
# TestLabels = np.concatenate((TestLabels, OLabels))
batch = tf.placeholder(tf.float32,[None,unit.H,unit.W,unit.Channel])
label = tf.placeholder(tf.uint8,[None])
keep_prop = tf.placeholder(tf.float32)
feature = SharePart(batch,keep_prop)
result = MissionPart(feature)
loss = SoftmaxWithLoss(result,label)
acc = Test(result,label)
opt = train_net(loss)
softmax = tf.nn.softmax(result)
entropy = tf.reduce_sum(-softmax * tf.log(softmax),1)
predict_class = tf.cast(tf.argmax(result,axis = 1),tf.uint8)
saver = tf.train.Saver()
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.9
config.gpu_options.allow_growth = False
init = tf.global_variables_initializer()
sess = tf.Session(config = config)
sess.run(init)
#这是测初始模型时用到的部分，可以忽略
# confunsion_matix = []
# file_report = open(MODEL_PATH+'confusion_matrix/'+Experiment_NAME+'_pre_'+'report.txt','w')
# recall = []
# precision = []
# f1 = []
# support = []
# accuracy = 0
# c_m_t = np.zeros([CLASS_NUM,CLASS_NUM])
# saver.restore(sess,MODEL_PATH+PRETRAIN_MODEL_NAME)
# for i in range(len(TestData)):
# predict_label = sess.run(predict_class,feed_dict = { batch:unit.changeshape_1(TestData[i]),keep_prop:1.0})
# c_m_t[TestLabels[i],predict_label] += 1
# confunsion_matix.append(c_m_t)
# np.save(MODEL_PATH+'confusion_matrix/'+Experiment_NAME+'_pre'+'.npy',c_m_t)
# file_report.write(" stage " + "confusion_matrix with testsets\n" )
# file_report.write(" "+"precision".rjust(10,)+"recall".rjust(10,)+"f1-score".rjust(10,)+"support".rjust(10,)+'\n')
# plotconfusion(c_m_t,MODEL_PATH+'confusion_matrix/'+Experiment_NAME+'_pre',CLASS_NUM)
# for i in range(CLASS_NUM):
# accuracy += c_m_t[i,i]
# try:
# recall.append(round(c_m_t[i,i]/np.sum(c_m_t[i]),3))
# except:
# recall.apprend(round(0,3))
# try:
# precision.append(round(c_m_t[i,i]/np.sum(c_m_t[:,i]),3))
# except:
# precision.append(round(0,3))
# try:
# f1.append(round(2*recall[i]*precision[i]/(recall[i]+precision[i]),3))
# except:
# f1.append(round(0,3))
# support.append(np.sum(c_m_t[i]))
# file_report.write(str(i).rjust(10,)+str(precision[i]).rjust(10,)+str(recall[i]).rjust(10,)+str(f1[i]).rjust(10,)+str(support[i]).rjust(10,)+'\n')
# try:
# recall_avg = round(np.sum(np.array(recall))/CLASS_NUM,3)
# except:
# recall_avg = 0
# try:
# precision_avg = round(np.sum(np.array(precision))/CLASS_NUM,3)
# except:
# precision_avg = 0
# try:
# f1_avg = round(np.sum(np.array(f1))/CLASS_NUM,3)
# except:
# f1_avg = 0
# support_num = np.sum(np.array(support))
# accuracy = round(accuracy/support_num,5)
# file_report.write("average".rjust(10,)+str(precision_avg).rjust(10,)+str(recall_avg).rjust(10,)+str(f1_avg).rjust(10,)+str(support_num).rjust(10,)+'\n')
# file_report.write(" stage acc is " +str(accuracy))
# file_report.write("\n\n\n\n")
# file_report.close()
#
for ac_method in ac_methods:
file_report = open('./confusion_matrix/'+Experiment_NAME+ac_method+'report.txt','w')
for a in range(ACTIVE_TIME):
recall = []
precision = []
f1 = []
support = []
accuracy = 0
c_m_t = np.zeros([CLASS_NUM,CLASS_NUM])
saver.restore(sess,MODEL_PATH+Experiment_NAME+ac_method+str(a+1)+'.ckpt')
for i in range(len(TestData)):
predict_label = sess.run(predict_class,feed_dict = { batch:unit.changeshape_1(TestData[i]),keep_prop:1.0})
c_m_t[TestLabels[i],predict_label] += 1
confunsion_matix.append(c_m_t)
np.save('./confusion_matrix/'+Experiment_NAME+ac_method+str(a+1)+'.npy',c_m_t)
# np.save('./confusion_matrix/'+Experiment_NAME+'_pre'+'.npy',c_m_t)
file_report.write(str(a+1) + " stage " + "confusion_matrix with testsets\n" )
file_report.write(" "+"precision".rjust(10,)+"recall".rjust(10,)+"f1-score".rjust(10,)+"support".rjust(10,)+'\n')
plotconfusion(c_m_t,'./confusion_matrix/'+Experiment_NAME+ac_method+str(a+1),CLASS_NUM)
# plotconfusion(c_m_t,'./confusion_matrix/'+Experiment_NAME+'_pre',CLASS_NUM)
for i in range(CLASS_NUM):
accuracy += c_m_t[i,i]
try:
recall.append(round(c_m_t[i,i]/np.sum(c_m_t[i]),3))
except:
recall.apprend(round(0,3))
try:
precision.append(round(c_m_t[i,i]/np.sum(c_m_t[:,i]),3))
except:
precision.append(round(0,3))
try:
f1.append(round(2*recall[i]*precision[i]/(recall[i]+precision[i]),3))
except:
f1.append(round(0,3))
support.append(np.sum(c_m_t[i]))
file_report.write(str(i).rjust(10,)+str(precision[i]).rjust(10,)+str(recall[i]).rjust(10,)+str(f1[i]).rjust(10,)+str(support[i]).rjust(10,)+'\n')
try:
recall_avg = round(np.sum(np.array(recall))/CLASS_NUM,3)
except:
recall_avg = 0
try:
precision_avg = round(np.sum(np.array(precision))/CLASS_NUM,3)
except:
precision_avg = 0
try:
f1_avg = round(np.sum(np.array(f1))/CLASS_NUM,3)
except:
f1_avg = 0
support_num = np.sum(np.array(support))
accuracy = round(accuracy/support_num,5)
file_report.write("average".rjust(10,)+str(precision_avg).rjust(10,)+str(recall_avg).rjust(10,)+str(f1_avg).rjust(10,)+str(support_num).rjust(10,)+'\n')
file_report.write(str(a+1) + " stage acc is " +str(accuracy))
file_report.write("\n\n\n\n")
file_report.close()
return
def entropy_active():
#载入数据
TrainData, TrainLabels, OracleData, OracleLabels,\
TestData, TestLabels, _, _, lenn_s, lenn_t, _ = load_process()
batch = tf.placeholder(tf.float32,[None,unit.H,unit.W,unit.Channel])
label = tf.placeholder(tf.uint8,[None])
keep_prop = tf.placeholder(tf.float32)
feature = SharePart(batch,keep_prop)
result = MissionPart(feature)
loss = SoftmaxWithLoss(result,label)
acc = Test(result,label)
opt = train_net(loss)
softmax = tf.nn.softmax(result)
entropy = tf.reduce_sum(-softmax * tf.log(softmax),1)
predict_class = tf.cast(tf.argmax(softmax,axis = 1),tf.uint8)
saver = tf.train.Saver(max_to_keep = ACTIVE_TIME)
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.45
config.gpu_options.allow_growth = False
init = tf.global_variables_initializer()
sess = tf.Session(config = config)
sess.run(init)
saver.restore(sess,PRETRAIN_MODEL_NAME)
def test():
ACC = 0
for i in range(lenn_t):
test_batch = TestData[i*BATCH_SIZE:(i+1)*BATCH_SIZE]
test_label = TestLabels[i*BATCH_SIZE:(i+1)*BATCH_SIZE]
ACC+=sess.run(acc,feed_dict={batch:test_batch,label:test_label,keep_prop:1.0})
return ACC/lenn_t
'''Begin Active Learning!'''
log_file = open('./simple_log/'+Experiment_NAME+'_ALST.txt','w')
pretrain_accuracy = test()
print 'the pre train model accuracy is : ', pretrain_accuracy
log_file.write("the pre train model accuracy is " + str(pretrain_accuracy))
log_file.write("\n")
#整个主动过程
for a in range(ACTIVE_TIME):
oracle_idx = np.arange(len(OracleData))
oracle_que = []
#计算每个样本的信息熵
for i in oracle_idx:
candidate_entropy = sess.run(entropy, feed_dict={batch:unit.changeshape_1(OracleData[i]),keep_prop:1.0})
candidate_predict = sess.run(predict_class, feed_dict={batch:unit.changeshape_1(OracleData[i]),keep_prop:1.0})
oracle_que.append((i,candidate_entropy[0],candidate_predict[0]))
oracle_que = sorted(oracle_que, key = lambda candidate:candidate[1], reverse = True)
#oracle_que 包含了三个变量，[图片编号；信息熵；预测标签]
#这里要注意temp变量的格式，他的下层每个类目是字符型的名称，名称与类目成对应关系。每个图片按照预测标签存放在temp名下，并进行信息熵排序
temp = {}
tag_queue = []
for k in range(CLASS_NUM):
temp[str(k)] = []
for k in range(len(oracle_que)):
temp[str(oracle_que[k][2])].append(oracle_que[k])
for k in temp:
temp[k] = sorted(temp[k], key=lambda x:x[1], reverse=True)
#先对类目进行洗牌，然后按照次序从中一个一个挑选，直到选满QUEUE_SIZE
idx = 0
temp_class = 0
temp_order = range(CLASS_NUM)
shuffle(temp_order)
while(idx<QUEUE_SIZE):
if len(temp[str(temp_order[temp_class])]) != 0:
tag_queue.append(temp[str(temp_order[temp_class])].pop(0)[0])
idx += 1
temp_class = (temp_class+1)%(CLASS_NUM)
else:
temp_class = (temp_class+1)%(CLASS_NUM)
if a == 0 :
TrainData = OracleData[tag_queue]
TrainLabels = OracleLabels[tag_queue]
np.delete(OracleData, tag_queue), np.delete(OracleLabels,tag_queue) #标注后将数据从无标样本池中删除
else:
TrainData = np.concatenate((TrainData,OracleData[tag_queue]))
TrainLabels = np.concatenate((TrainLabels, OracleLabels[tag_queue]))
np.delete(OracleData, tag_queue), np.delete(OracleLabels,tag_queue)
train_queue = np.arange(len(TrainData))
best = 0
for i in range(EPOCH_all):
shuffle(train_queue)
for j in range(len(TrainData)/BATCH_SIZE):
trainbatch = TrainData[train_queue[j*BATCH_SIZE:(j+1)*BATCH_SIZE]]
trainlabels = TrainLabels[train_queue[j*BATCH_SIZE:(j+1)*BATCH_SIZE]]
sess.run(opt, feed_dict = {batch:trainbatch, label:trainlabels,keep_prop:0.5})
accuracy = test()
print 'the ',a+1, 'time acmodel acc is:', accuracy
if accuracy > best:
best = accuracy
saver.save(sess,MODEL_PATH+Experiment_NAME+'_ALST_'+str(a+1)+'.ckpt')
print 'the ',a+1,' time acmodel best acc is: ', best
log_file.write("the " + str(a+1) + "time acmodel best acc is " + str(best))
log_file.write("\n")
return