def TestModel(self,
sess,
writer,
datapath='',
str_dataset='eval',
data_count=32,
out_report=False,
show_ratio=True,
step=0):
'''
测试检验模型效果
'''
data = DataSpeech(self.datapath, str_dataset)
# data.LoadDataList(str_dataset)
num_data = sum(data.DataNum) # 获取数据的数量
if (data_count <= 0 or data_count >
num_data): # 当data_count为小于等于0或者大于测试数据量的值时，则使用全部数据来测试
data_count = num_data
try:
ran_num = random.randint(0, num_data - 1) # 获取一个随机数
overall_p = 0
overall_n = 0
overall_tp = 0
overall_tn = 0
accuracy = 0
sensitivity = 0
specificity = 0
score = 0
nowtime = time.strftime('%Y%m%d_%H%M%S',
time.localtime(time.time()))
txt_obj = []
if (out_report == True):
txt_obj = open('Test_Report_' + str_dataset + '_' + nowtime +
'.txt',
'w',
encoding='UTF-8') # 打开文件并读入
start = time.time()
cm_pre = []
cm_lab = []
map = {0: 'normal', 1: 'bowel sounds'}
# data_count = 200
for i in tqdm(range(data_count)):
data_input, data_labels = data.GetData(
(ran_num + i) % num_data,
mode='non-repetitive') # 从随机数开始连续向后取一定数量数据
predictions = []
if len(data_input) <= AUDIO_LENGTH:
data_in = np.zeros(
(1, AUDIO_LENGTH, AUDIO_FEATURE_LENGTH, 1),
dtype=np.float)
data_in[0, 0:len(data_input)] = data_input
data_pre = self.model.predict_on_batch(data_in)
predictions = np.argmax(data_pre[0], axis=0)
else:
assert (0)
# print('predictions:',predictions)
# print('data_pre:',np.argmax(data_pre[0], axis=0))
# print ('data_label:',data_labels[0])
cm_pre.append(map[predictions])
cm_lab.append(map[data_labels[0]])
tp, fp, tn, fn = Comapare2(predictions,
data_labels[0]) # 计算metrics
overall_p += tp + fn
overall_n += tn + fp
overall_tp += tp
overall_tn += tn
txt = ''
if (out_report == True):
txt += str(i) + '\n'
txt += 'True:\t' + str(data_labels) + '\n'
txt += 'Pred:\t' + str(data_pre) + '\n'
txt += '\n'
txt_obj.write(txt)
if overall_p != 0:
sensitivity = overall_tp / overall_p * 100
sensitivity = round(sensitivity, 2)
else:
sensitivity = 'None'
if overall_n != 0:
specificity = overall_tn / overall_n * 100
specificity = round(specificity, 2)
else:
specificity = 'None'
if sensitivity != 'None' and specificity != 'None':
score = (sensitivity + specificity) / 2
score = round(score, 2)
else:
score = 'None'
accuracy = (overall_tp + overall_tn) / (overall_p +
overall_n) * 100
accuracy = round(accuracy, 2)
end = time.time()
dtime = round(end - start, 2)
# print('*[测试结果] 片段识别 ' + str_dataset + ' 敏感度：', sensitivity, '%, 特异度： ', specificity, '%, 得分： ', score, ', 准确度： ', accuracy, '%, 用时: ', dtime, 's.')
strg = '*[测试结果] 片段识别 {0} 敏感度：{1}%, 特异度： {2}%, 得分： {3}, 准确度： {4}%, 用时: {5}s.'.format(
str_dataset, sensitivity, specificity, score, accuracy, dtime)
tqdm.write(strg)
assert (len(cm_lab) == len(cm_pre))
img_cm = plot_confusion_matrix(cm_lab,
cm_pre,
list(map.values()),
tensor_name='MyFigure/cm',
normalize=False)
writer.add_summary(img_cm, global_step=step)
summary = tf.Summary()
summary.value.add(tag=str_dataset + '/sensitivity',
simple_value=sensitivity)
summary.value.add(tag=str_dataset + '/specificity',
simple_value=specificity)
summary.value.add(tag=str_dataset + '/score', simple_value=score)
summary.value.add(tag=str_dataset + '/accuracy',
simple_value=accuracy)
writer.add_summary(summary, global_step=step)
if (out_report == True):
txt = '*[测试结果] 片段识别 ' + str_dataset + ' 敏感度：' + sensitivity + '%, 特异度： ' + specificity + '%, 得分： ' + score + ', 准确度： ' + accuracy + '%, 用时: ' + dtime + 's.'
txt_obj.write(txt)
txt_obj.close()
metrics = {
'data_set': str_dataset,
'sensitivity': sensitivity,
'specificity': specificity,
'score': score,
'accuracy': accuracy
}
return metrics
except StopIteration:
print('[Error] Model Test Error. please check data format.')
def TrainModel(self,
datapath,
epoch=2,
batch_size=32,
load_weights=False,
filename='model_set/speech_model25'):
assert (batch_size % CLASS_NUM == 0)
data = DataSpeech(datapath, 'train')
num_data = sum(data.DataNum) # 获取数据的数量
os.system('pkill tensorboard')
os.system('rm -rf ./checkpoints/files_summary/* ')
train_writter = tf.summary.FileWriter(
os.path.join(os.getcwd(), 'checkpoints', 'files_summary'))
os.system(
'tensorboard --logdir=/home/zhaok14/example/PycharmProjects/setsail/individual_spp/checkpoints/files_summary/ &'
)
print('\n')
print(90 * '*')
print(90 * '*')
iterations_per_epoch = min(
data.DataNum) // (batch_size // CLASS_NUM) + 1
# iterations_per_epoch = 2
print('trainer info:')
print('training data size: %d' % num_data)
print('increased epoches: ', epoch)
print('minibatch size: %d' % batch_size)
print('iterations per epoch: %d' % iterations_per_epoch)
with k.get_session() as sess:
train_writter.add_graph(sess.graph)
if load_weights == True:
try:
# modelpath = os.path.join(os.getcwd(), 'network&&weights', 'spectrogram', 'inception','spec_inception.h5')
self.model = load_model(modelpath,
custom_objects={
'focal_loss': focal_loss,
'focal_loss_fixed':
focal_loss()
})
print('Successfully loading the model.')
except:
print('Loading weights failed. Train from scratch.')
sess.run(tf.global_variables_initializer())
best_score = 0
for i in range(0, epoch):
iteration = 0
yielddatas = data.data_genetator(batch_size, epoch)
pbar = tqdm(yielddatas)
for input, labels in pbar:
loss = self.model.train_on_batch(input[0], labels)
train_summary = tf.Summary()
train_summary.value.add(tag='loss', simple_value=loss)
train_writter.add_summary(
train_summary, iteration + i * iterations_per_epoch)
pr = 'epoch:%d/%d,iteration: %d/%d ,loss: %s' % (
epoch, i, iterations_per_epoch, iteration, loss)
pbar.set_description(pr)
if iteration == iterations_per_epoch:
break
else:
iteration += 1
pbar.close()
if i % 1 == 0:
self.TestModel(sess=sess,
datapath=self.datapath,
str_dataset='train',
data_count=1000,
out_report=False,
writer=train_writter,
step=i)
metrics = self.TestModel(sess=sess,
datapath=self.datapath,
str_dataset='eval',
data_count=-1,
out_report=False,
writer=train_writter,
step=i)
if (metrics['score'] >= best_score and i > 0):
self.metrics = metrics
self.metrics['epoch'] = i
best_score = metrics['score']
self.model.save(self.savpath)
print('The best metrics took place in the epoch: ',
self.metrics['epoch'])
print(
'Sensitivity: {}; Specificity: {}; Score: {}; Accuracy: {}'.format(
self.metrics['sensitivity'], self.metrics['specificity'],
self.metrics['score'], self.metrics['accuracy']))
def TrainModel(self, datapath,epoch=10, batch_size=32):
assert (batch_size % CLASS_NUM == 0)
data = DataSpeech(datapath, 'train')
num_data = sum(data.DataNum) # 获取数据的数�?
os.system('pkill tensorboard')
os.system('rm -rf ./checkpoints/files_summary/* ')
train_writter = tf.summary.FileWriter(os.path.join(os.getcwd(), 'checkpoints', 'files_summary'))
os.system('tensorboard --logdir=/home/zhaok14/example/PycharmProjects/setsail/individual_spp/checkpoints/files_summary/ &')
print('\n')
print(90 * '*')
print(90 * '*')
iterations_per_epoch = min(data.DataNum) // (batch_size // CLASS_NUM) + 1
# iterations_per_epoch = 1
print('trainer info:')
print('training data size: %d' % num_data)
print('increased epoches: ', epoch)
print('minibatch size: %d' % batch_size)
print('iterations per epoch: %d' % iterations_per_epoch)
sess = k.get_session()
train_writter.add_graph(sess.graph)
sess.run(tf.global_variables_initializer())
best_score = 0
# epoch = 2
duration = 0
for i in range(0, epoch):
iteration = 0
yielddatas = data.data_genetator(batch_size,epoch)
pbar = tqdm(yielddatas)
for input, labels in pbar:
stime = time.time()
loss = self.model.train_on_batch(input[0],labels)
# temp = self.model.predict_on_batch(input[0])
dtime = time.time() - stime
duration = duration + dtime
# okay = self.model.predict_on_batch(input[0])
# compare = self.interlayer.predict_on_batch(input[0])
train_summary = tf.Summary()
train_summary.value.add(tag='loss', simple_value=loss)
train_writter.add_summary(train_summary, iteration + i * iterations_per_epoch)
pr = 'epoch:%d/%d,iteration: %d/%d ,loss: %s' % (epoch, i, iterations_per_epoch, iteration, loss)
pbar.set_description(pr)
if iteration == iterations_per_epoch:
break
else:
iteration += 1
pbar.close()
if i % 1 == 0:
tmetrics = self.TestModel(sess=sess, datapath=datapath, str_dataset='train', data_count=1000, out_report=False, writer=train_writter, step=i)
metrics = self.TestModel(sess=sess, datapath=datapath, str_dataset='eval', data_count=-1, out_report=False, writer=train_writter, step=i)
if i > 0:
if metrics['score'] >= best_score:
self.metrics = metrics
self.metrics['epoch'] = i
best_score = metrics['score']
self.savpath = []
self.savpath.append((self.baseSavPath[0] + '_epoch' + str(i) + '.h5'))
self.savpath.append((self.baseSavPath[1] + '_epoch' + str(i) + '.h5'))
self.model.save(self.savpath[0])
self.model.save_weights(self.savpath[1])
if 'epoch' in self.metrics.keys():
print('The best metric after restriction took place in the epoch: ', self.metrics['epoch'])
print('Sensitivity: {}; Specificity: {}; Score: {}; Accuracy: {}'.format(self.metrics['sensitivity'],self.metrics['specificity'],self.metrics['score'],self.metrics['accuracy']))
self.TestGenerability(weightspath=self.savpath[1])
else:
print('The restricted best metric is not found. Done!')
# path_test = '/home/zhaok14/example/PycharmProjects/setsail/individual_spp/network&&weights/spectrogram/mlp/spec_mlp_weights_epoch12.h5'
# self.TestGenerability(weightspath=path_test)
print('Training duration: {}s'.format(round(duration,2)))
def TrainModel(self,
datapath,
epoch=2,
batch_size=32,
load_model=False,
filename='model_set/speech_model25'):
'''
训练模型
参数：
datapath: 数据保存的路径
epoch: 迭代轮数
save_step: 每多少步保存一次模型
filename: 默认保存文件名，不含文件后缀名
'''
'''
currently dont involve in load model function and txt export function.
'''
assert (batch_size % 2 == 0)
data = DataSpeech(datapath, 'train')
num_data = sum(data.DataNum) # 获取数据的数量
os.system('pkill tensorboard')
os.system('rm -rf ./checkpoints/files_summary/* ')
train_writter = tf.summary.FileWriter(
os.path.join(os.getcwd(), 'checkpoints', 'files_summary'))
os.system(
'tensorboard --logdir=/home/zhaok14/example/PycharmProjects/setsail/individual_spp/checkpoints/files_summary/ &'
)
print('\n')
print(90 * '*')
print(90 * '*')
iterations_per_epoch = min(
data.DataNum) // (batch_size // CLASS_NUM) + 1
# iterations_per_epoch = 2
print('trainer info:')
print('training data size: %d' % num_data)
print('increased epoches: ', epoch)
print('minibatch size: %d' % batch_size)
print('iterations per epoch: %d' % iterations_per_epoch)
self.graph = tf.Graph()
model_summary = self.CreateModel(graph=self.graph)
with tf.Session(graph=self.graph) as sess:
train_writter.add_graph(sess.graph)
saver = tf.train.Saver(max_to_keep=1)
if load_model == True:
try:
saver.restore(
sess,
os.path.join(os.getcwd(), 'checkpoints', 'files_model',
'speech-f' + str(0) +
'.module')) # two files in a folder.
except:
print('Loading weights failed. Train from scratch.')
sess.run(tf.global_variables_initializer())
best_score = 0
for i in range(0, epoch):
iteration = 0
yielddatas = data.data_genetator(batch_size, epoch)
pbar = tqdm(yielddatas)
for input, _ in pbar:
feed = {
self.input_data: input[0],
self.label: input[1],
self.is_train: True
}
_, loss, train_summary = sess.run(
[self.optimize, self.loss, model_summary],
feed_dict=feed)
train_writter.add_summary(
train_summary, iteration + i * iterations_per_epoch)
pr = 'epoch:%d/%d,iteration: %d/%d ,loss: %s' % (
epoch, i, iterations_per_epoch, iteration, loss)
pbar.set_description(pr)
if iteration == iterations_per_epoch:
break
else:
iteration += 1
pbar.close()
if i % 1 == 0:
self.TestModel(sess=sess,
datapath=self.datapath,
str_dataset='train',
data_count=-1,
out_report=False,
writer=train_writter,
step=i)
metrics = self.TestModel(sess=sess,
datapath=self.datapath,
str_dataset='eval',
data_count=-1,
out_report=False,
writer=train_writter,
step=i)
if (metrics['score'] > best_score and i > 0):
self.metrics = metrics
self.metrics['epoch'] = i
best_score = metrics['score']
saver.save(sess,
os.path.join(
os.getcwd(), 'checkpoints',
'files_model',
'speech-f' + str(0) + '.module'),
global_step=i)
print('The best metrics took place in the epoch: ',
self.metrics['epoch'])
print(
'Sensitivity: {}; Specificity: {}; Score: {}; Accuracy: {}'.format(
self.metrics['sensitivity'], self.metrics['specificity'],
self.metrics['score'], self.metrics['accuracy']))
import matplotlib.pyplot as plt
import sys
sys.path.append('../')
from skimage.feature import hog
from skimage import exposure
import numpy as np
from release.readdata_bowel import DataSpeech
datapath = '/home/zhaok14/example/PycharmProjects/setsail/individual_spp/bowelsounds/perfect'
traindata = DataSpeech(datapath, 'train')
oimage, _ = traindata.GetData(10, mode='non-repetitive')
image = np.squeeze(oimage)
fd, hog_image = hog(image,
orientations=8,
pixels_per_cell=(16, 16),
cells_per_block=(1, 1),
visualise=True)
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(8, 4), sharex=True, sharey=True)
ax1.axis('off')
ax1.imshow(image, cmap=plt.cm.gray)
ax1.set_title('Input image')
# Rescale histogram for better display
hog_image_rescaled = exposure.rescale_intensity(hog_image, in_range=(0, 10))
ax2.axis('off')
ax2.imshow(hog_image_rescaled, cmap=plt.cm.gray)