def __load_folder(folder, class_name):
image_dict = dict()
path = ROOT_DIR + '\\dataset\\' + folder + '\\' + class_name + '\\'
# Get all files in path
for f in glob.iglob(path + '*'):
# Is image
if re.match('.*\.png$', f):
# Put images into dict with file name (without path) as index. Images get normalized, then converted to
# PyTorch tensors, then permuted to (Channels, Height, Width)
image_dict[f[len(path):]] = torch.from_numpy(
normalize(__load_image(f))).permute((2, 0, 1))
out = list()
for f in glob.iglob(path + '*'):
# Is poses.txt
if re.match('.*poses\.txt$', f):
lines = open(f, 'r').readlines()
for i in range(len(lines) // 2):
pose_strings = lines[i * 2 + 1].split()
pose = np.array(
(float(pose_strings[0]), float(pose_strings[1]),
float(pose_strings[2]), float(pose_strings[3])))
out.append((image_dict[lines[i * 2][2:-1]], class_name, pose,
path + lines[i * 2][2:-1]))
return out
def prepare_data(names, feat_dict):
X = np.array([feat_dict[name_i] for name_i in names])
X = norm.normalize(X, 'all')
X = np.expand_dims(X, axis=-1)
y = [data.parse_name(name_i)[0] - 1 for name_i in names]
y = keras.utils.to_categorical(y)
return X, y
def infer():
message = request.json
sample = message['sample']
result = normalize(sample)
print('INPUT: ', sample)
print('RESULT: ', result)
return send_response({'result': result})
def model(data, n_rules):
# numpy and norm
x, y = data.dataset.tensors
y = y.float()
x = x.numpy()
x, minimum, maximum = normalize(data=x)
x = x.astype(float)
# cmeans
# como o numero de entradas é constante n de regras = n de funcoes de
# pertinencia = numero de centros
modelo = cmenas(k=n_rules)
modelo.train(data=x, MAX=15, tol=1e-2)
centros = modelo.C
# denorm
centros = denormalize(data=centros, m=minimum, M=maximum)
names = [
'radius_mean', 'texture_mean', 'perimeter_mean', 'area_mean',
'smoothness_mean', 'compactness_mean', 'concavity_mean'
'conc_mean', 'points_mean', 'symmetry_mean'
]
def mk_var(name, centros, i):
return (name, make_gauss_mfs(3,
[centros[n, i] for n in range(n_rules)]))
invardefs = [mk_var(name, centros, i) for i, name in enumerate(names)]
outvars = ['diagnosis']
model = anfis.AnfisNet('breast-cancer', invardefs, outvars)
return model
def model(data, n_rules):
# numpy and norm
x, y = data.dataset.tensors
x = x.numpy()
x, minimum, maximum = normalize(data=x)
# cmeans
# como o numero de entradas é constante n de regras = n de funcoes de
# pertinencia = numero de centros
modelo = cmenas(k=n_rules)
modelo.train(data=x, MAX=15, tol=1e-2)
centros = modelo.C
# denorm
centros = denormalize(data=centros, m=minimum, M=maximum)
def mk_var(name, centros, i): # de iris_example
return (name,
make_gauss_mfs(1,
[centros[0, i], centros[1, i], centros[2, i]]))
def mk_var(name, centros, i): # de iris_example
return (name, make_gauss_mfs(1,
[centros[n, i] for n in range(n_rules)]))
invardefs = [
mk_var(name, centros, i) for i, name in enumerate(
['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm'])
]
outvars = ['Species']
model = anfis.AnfisNet('iris', invardefs, outvars)
return model
def normalize_multi(pair, values):
for i in values:
normalize(pair, i)
from csvread import readcsv
from neuron3to4lyr import NN
from norm import normalize
ismr = readcsv('ismr.csv')
nino3 = readcsv('nino3.csv')
ismr_norm = normalize(ismr)
nino3_norm = normalize(nino3)
no_of_months = len(ismr)
ismr_nino3 = [[[None], [None]] for x in xrange(no_of_months)]
ismr_nino3_train = [[[None], [None]] for x in xrange(no_of_months - 500)]
ismr_nino3_test = [[[None], [None]] for x in xrange(500)]
#for i in range(no_of_months):
# ismr_nino3[i][0][0] = ismr[i]
# ismr_nino3[i][1][0] = nino3[i]
#
#ismr_nino3_train = ismr_nino3[0:no_of_months-500-1]
#ismr_nino3_test = ismr_nino3[no_of_months-500:no_of_months-1]
## create a network with two input, two hidden, and one output nodes
#n = NN(1, 4, 2 , 1)
## train it with some patterns
#n.train(ismr_nino3_train)
## save a network
## test it
#n.test(ismr_nino3_test)
#
#
def infer():
message = request.json
sample = message['sample']
result = normalize(sample)
print('INPUT: ', sample)
print('RESULT: ', result)
return send_response({'result': result})
if __name__ == '__main__':
config = configparser.ConfigParser()
config.read("conf/config.cfg")
# dict
abbre_dict = utils.read_txt_two_cols(config['resources']['abbre_path'])
try:
oov_dict = utils.read_oov(config['resources']['oov_path'])
except:
oov_dict = {}
# init api
# app.debug = True
# host = os.environ.get('IP', '0.0.0.0')
# port = int(os.environ.get('PORT', 11993))
# app.run(host=host, port=port, threaded=True, use_reloader=False)
# app.run()
while True:
inp = input('nhap input vao day: ')
result = normalize(inp)
print('result: ', result)
def test_fromAndTos(self):
self.assertAlmostEqual(normalize(5, 20), 5.011552452941506)
