def test_procedure(self, test_data, mode):
confusion_matrics = np.zeros([self.num_class, self.num_class],
dtype="int")
tst_batch_num = int(np.ceil(test_data[0].shape[0] / self.bs))
for step in range(tst_batch_num):
_testImg = test_data[0][step * self.bs:step * self.bs + self.bs]
_testLab = test_data[1][step * self.bs:step * self.bs + self.bs]
matrix_row, matrix_col = self.sess.run(self.distribution,
feed_dict={
self.x: _testImg,
self.y: _testLab,
self.is_training: False
})
for m, n in zip(matrix_row, matrix_col):
confusion_matrics[m][n] += 1
test_accuracy = float(
np.sum([confusion_matrics[q][q] for q in range(self.num_class)
])) / float(np.sum(confusion_matrics))
detail_test_accuracy = [
confusion_matrics[i][i] / np.sum(confusion_matrics[i])
for i in range(self.num_class)
]
log0 = "Test mode {}".format(mode)
log1 = "Test Accuracy : %g" % test_accuracy
log2 = np.array(confusion_matrics.tolist())
log3 = ''
for j in range(self.num_class):
log3 += 'category %s test accuracy : %g\n' % (
FineTuning_utils.pulmonary_category[j],
detail_test_accuracy[j])
log3 = log3[:-1]
log4 = 'F_Value : %g' % self.f_value(confusion_matrics)
FineTuning_utils.save2file(log0, self.ckptDir, self.model)
FineTuning_utils.save2file(log1, self.ckptDir, self.model)
FineTuning_utils.save2file(log2, self.ckptDir, self.model)
FineTuning_utils.save2file(log3, self.ckptDir, self.model)
FineTuning_utils.save2file(log4, self.ckptDir, self.model)
src_training = DA_init.loadPickle(FineTuning_utils.experimentalPath,
src_name + '_training.pkl')
src_validation = DA_init.loadPickle(FineTuning_utils.experimentalPath,
src_name + '_validation.pkl')
src_test = DA_init.loadPickle(FineTuning_utils.experimentalPath,
src_name + '_test.pkl')
tar_training = DA_init.loadPickle(FineTuning_utils.experimentalPath,
tar_name + '_training.pkl')
tar_validation = DA_init.loadPickle(FineTuning_utils.experimentalPath,
tar_name + '_validation.pkl')
tar_test = DA_init.loadPickle(FineTuning_utils.experimentalPath,
tar_name + '_test.pkl')
src_training = FineTuning_utils.normalizeInput(src_training, mode='Paired')
src_validation = FineTuning_utils.normalizeInput(src_validation, mode='Paired')
src_test = FineTuning_utils.normalizeInput(src_test, mode='Paired')
tar_training = FineTuning_utils.normalizeInput(tar_training, mode='Paired')
tar_validation = FineTuning_utils.normalizeInput(tar_validation, mode='Paired')
tar_test = FineTuning_utils.normalizeInput(tar_test, mode='Paired')
# 取目标域数据集中指定百分比的数据参与训练
tar_training = FineTuning_utils.getPartialDataSet(
tar_training, keep_percentage=args.target_percentage)
training = [
np.concatenate((src_training[0], tar_training[0]), axis=0),
np.concatenate((src_training[1], tar_training[1]), axis=0)
]
src_training = DA_init.loadPickle(FineTuning_utils.experimentalPath,
'source_training.pkl')
src_validation = DA_init.loadPickle(FineTuning_utils.experimentalPath,
'source_validation.pkl')
src_test = DA_init.loadPickle(FineTuning_utils.experimentalPath,
'source_test.pkl')
tar_training = DA_init.loadPickle(FineTuning_utils.experimentalPath,
'target_training.pkl')
tar_validation = DA_init.loadPickle(FineTuning_utils.experimentalPath,
'target_validation.pkl')
tar_test = DA_init.loadPickle(FineTuning_utils.experimentalPath,
'target_test.pkl')
src_training = FineTuning_utils.normalizeInput(src_training, mode='Paired')
src_validation = FineTuning_utils.normalizeInput(src_validation, mode='Paired')
src_test = FineTuning_utils.normalizeInput(src_test, mode='Paired')
tar_training = FineTuning_utils.normalizeInput(tar_training, mode='Paired')
tar_validation = FineTuning_utils.normalizeInput(tar_validation, mode='Paired')
tar_test = FineTuning_utils.normalizeInput(tar_test, mode='Paired')
training = [
np.concatenate((src_training[0], tar_training[0]), axis=0),
np.concatenate((src_training[1], tar_training[1]), axis=0)
]
validation = [
np.concatenate((src_validation[0], tar_validation[0]), axis=0),
np.concatenate((src_validation[1], tar_validation[1]), axis=0)
def saveConfiguration(self):
FineTuning_utils.save2file('epoch : %d' % self.eps, self.ckptDir,
self.model)
FineTuning_utils.save2file('restore epoch : %d' % self.res_eps,
self.ckptDir, self.model)
FineTuning_utils.save2file('model : %s' % self.model, self.ckptDir,
self.model)
FineTuning_utils.save2file('ksize : %d' % self.k, self.ckptDir,
self.model)
FineTuning_utils.save2file('out channel 1 : %d' % self.oc1,
self.ckptDir, self.model)
FineTuning_utils.save2file('out channel 2 : %d' % self.oc2,
self.ckptDir, self.model)
FineTuning_utils.save2file('out channel 3 : %d' % self.oc3,
self.ckptDir, self.model)
FineTuning_utils.save2file('learning rate : %g' % self.lr,
self.ckptDir, self.model)
FineTuning_utils.save2file('batch size : %d' % self.bs, self.ckptDir,
self.model)
FineTuning_utils.save2file('image height : %d' % self.img_h,
self.ckptDir, self.model)
FineTuning_utils.save2file('image width : %d' % self.img_w,
self.ckptDir, self.model)
FineTuning_utils.save2file('num class : %d' % self.num_class,
self.ckptDir, self.model)
FineTuning_utils.save2file('train phase : %s' % self.train_phase,
self.ckptDir, self.model)
def train(self):
self.sess.run(tf.global_variables_initializer())
self.itr_epoch = len(self.training_data[0]) // self.bs
self.best_val_accuracy = []
self.best_val_loss = []
training_acc = 0.0
training_loss = 0.0
for e in range(1, self.eps + 1):
for itr in range(self.itr_epoch):
_tr_img_batch, _tr_lab_batch = DA_init.next_batch(
image=self.training_data[0],
label=self.training_data[1],
batch_size=self.bs)
_train_accuracy, _train_loss, _ = self.sess.run(
[self.accuracy, self.loss, self.train_op],
feed_dict={
self.x: _tr_img_batch,
self.y: _tr_lab_batch,
self.is_training: True
})
training_acc += _train_accuracy
training_loss += _train_loss
summary = self.sess.run(self.merged,
feed_dict={
self.x: _tr_img_batch,
self.y: _tr_lab_batch,
self.is_training: False
})
training_acc = float(training_acc / self.itr_epoch)
training_loss = float(training_loss / self.itr_epoch)
validation_acc, validation_loss = self.validation_procedure()
self.best_val_accuracy.append(validation_acc)
self.best_val_loss.append(validation_loss)
log1 = "Epoch: [%d], Training Accuracy: [%g], Validation Accuracy: [%g], Loss Training: [%g] " \
"Loss_validation: [%g], Time: [%s]" % \
(e, training_acc, validation_acc, training_loss, validation_loss, time.ctime(time.time()))
self.plt_epoch.append(e)
self.plt_training_accuracy.append(training_acc)
self.plt_training_loss.append(training_loss)
self.plt_validation_accuracy.append(validation_acc)
self.plt_validation_loss.append(validation_loss)
FineTuning_utils.plotAccuracy(x=self.plt_epoch,
y1=self.plt_training_accuracy,
y2=self.plt_validation_accuracy,
figName=self.model,
line1Name='training',
line2Name='validation',
savePath=self.ckptDir)
FineTuning_utils.plotLoss(x=self.plt_epoch,
y1=self.plt_training_loss,
y2=self.plt_validation_loss,
figName=self.model,
line1Name='training',
line2Name='validation',
savePath=self.ckptDir)
FineTuning_utils.save2file(log1, self.ckptDir, self.model)
self.writer.add_summary(summary, e)
self.saver.save(self.sess,
self.ckptDir + self.model + '-' + str(e))
self.test_procedure(self.src_test_data, mode='Source')
self.test_procedure(self.tar_test_data, mode='Target')
training_acc = 0.0
training_loss = 0.0
self.best_val_index = self.best_val_accuracy.index(
max(self.best_val_accuracy))
log2 = 'Highest Validation Accuracy : [%g], Epoch : [%g]' % (
self.best_val_accuracy[self.best_val_index],
self.best_val_index + 1)
FineTuning_utils.save2file(log2, self.ckptDir, self.model)
self.best_val_index_loss = self.best_val_loss.index(
min(self.best_val_loss))
log3 = 'Lowest Validation Loss : [%g], Epoch : [%g]' % (
self.best_val_loss[self.best_val_index_loss],
self.best_val_index_loss + 1)
FineTuning_utils.save2file(log3, self.ckptDir, self.model)
parser.add_argument('-img_height', default=32, type=int)
parser.add_argument('-img_width', default=32, type=int)
args = parser.parse_args()
os.environ['CUDA_DEVICE_ORDER'] = 'PCI_BUS_ID'
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
if args.data_domain == 'Source':
training = DA_init.loadPickle(FineTuning_utils.experimentalPath,
'target_training.pkl')
validation = DA_init.loadPickle(FineTuning_utils.experimentalPath,
'target_validation.pkl')
test = DA_init.loadPickle(FineTuning_utils.experimentalPath,
'target_test.pkl')
training = FineTuning_utils.normalizeInput(training, mode='Paired')
validation = FineTuning_utils.normalizeInput(validation, mode='Paired')
test = FineTuning_utils.normalizeInput(test, mode='Paired')
reloadPath = '../checkpoint/bl_f16_s2t/bl_f16_s2t-148'
print('training image shape', str(training[0].shape))
print('training label shape', str(training[1].shape))
print('validation image shape', str(validation[0].shape))
print('validation label shape', validation[1].shape)
print('test image shape', test[0].shape)
print('test label shape', test[1].shape)
if args.data_domain == 'Target':