def derivative_Gaussian(x, complete=True, p=1):
if complete:
b = 10
else:
b = 1.25
filt = (x * b) * np.exp(-(x * b)**2 / 2)
return normalization(filt, p=p)
def test():
print('start')
for patient in os.listdir('/mnt/hd1/puwenbo/Dataset/T1T2/moving/'):
print('do ' + patient + 'now')
elastixImageFilter = sitk.ElastixImageFilter()
fix = sitk.ReadImage('/mnt/hd1/puwenbo/Dataset/T1T2/fixed/' + patient)
elastixImageFilter.SetFixedImage(fix)
elastixImageFilter.SetMovingImage(sitk.ReadImage('/mnt/hd1/puwenbo/Dataset/T1T2/moving/' + patient))
elastixImageFilter.SetParameterMap(helper.p)
elastixImageFilter.SetOutputDirectory('/mnt/hd1/puwenbo/Dataset/T1T2/output/')
elastixImageFilter.Execute()
res = helper.normalization(sitk.GetArrayFromImage(elastixImageFilter.GetResultImage()))
sitk.WriteImage(sitk.GetImageFromArray(res), '/mnt/hd1/puwenbo/Dataset/T1T2/output/'+ patient)
def conv_filter(x, name='Gaussian', complete=True, p=1):
if complete:
b = 10
else:
b = 1.25
if name == 'Gaussian':
filt = np.exp(-(x * b)**2 / 2)
elif name == 'derivative':
filt = (x * b) * np.exp(-(x * b)**2 / 2)
elif name == 'averaging':
b = 1.25
filt = np.exp(-(x * b)**2 / 2)
else:
print(name, 'Filter not implemented')
raise ValueError
return normalization(filt, p=p)
confusion_set = ['than', 'then']
# minimum occurence of tokens in training data
# tokens with less occurences will be substituted to 'U' for unknown
# 'U' can also serve as substitute for unseen tokens at test time
min_occurrence = 20
### END SETTINGS ###
# init
if not os.path.exists(work_dir):
os.makedirs(work_dir)
with open(corpus_file) as f:
sents = [[helper.normalization(twp.split('|')[0].lower()) for twp in line.split()] for line in f]
train_sents = list(helper.acs(sents, preserve_tokens))
token_embeddings = helper.TokenEmbeddings(train_sents, min_occurrence)
if timestamp and start_epoch and start_iteration:
errors = helper.load_errors('%s-%d-%d.errors' % (timestamp, start_epoch, start_iteration), work_dir)
load_weights = '%s-%d-%d.weights' % (timestamp, start_epoch, start_iteration)
print('init previous states...')
print('timestamp: ', timestamp)
print('start_epoch: ', start_epoch)
print('start_iteration: ', start_iteration)
else:
errors = []
start_epoch = 0
start_iteration = 0
def StandingStill(x):
filt = np.ones(x.shape)
return normalization(filt)
def TurnDown(x):
l = 10
filt = (1 + np.exp(l * x))**(-1)
return normalization(filt)
def TurnUp(x):
l = 10
filt = (1 + np.exp(-l * x))**(-1)
return normalization(filt)