def _training_DNN(self):
trX, trY, self.missing_filename_list, = read_features(self.test_number, self.n_input_f, self.n_output_f)
trX = trX[:,1:self.n_input_f]
trY = trY[:,1:self.n_output_f]
print trX.shape
print trY.shape
print self.nloop, self.n_hidden_layer, self.n_input_f, self.n_hidden_f, self.n_output_f
X = T.fmatrix()
Y = T.fmatrix()
py_x = self._model(X, self.params, self.bias)
y_x = py_x
cost = T.mean(T.sqr(py_x - Y))
updates = self._sgd(cost, self.params, self.bias)
train = theano.function(inputs=[X, Y], outputs=cost, updates=updates, allow_input_downcast=True)
self.predict = theano.function(inputs=[X], outputs=y_x, allow_input_downcast=True)
for i in range(self.nloop, self.nloop + 0 ):
print i
#logging.debug('loop' + str(i))
error_total = 0
arr_X_Y = zip(range(0, len(trX), 128), range(128, len(trX), 128))
for start, end in arr_X_Y:
cost = train(trX[start:end], trY[start:end])
error_total += cost
#print cost
last_element = arr_X_Y[len(arr_X_Y)-1][0]
if last_element < len(trX):
cost = train(trX[last_element: len(trX)], trY[last_element:len(trY)])
error_total += cost
print error_total / len(trX)
save_weight_info( self.filename, i, self.n_hidden_layer, self.n_input_f, self.n_hidden_f, self.n_output_f, self.params, error_total, self.bias)
self.id_file = 1 - self.id_file
self.filename = self.weight_folder + 'id_' + str(self.id_file) + ".txt"
def _training_DNN(self):
trX, trY, self.missing_filename_list, self.test_number = read_features()
load_params = False
id_file = 0
weight_folder = '../weight_DNN/SQR/' + self.hidden_layer + self.artic + 'test_' + str(self.test_number) + '/'
if not os.path.exists(weight_folder):
os.makedirs(weight_folder)
filename = weight_folder + 'Phonemic_DNN_SGD_id_' + str(id_file) + ".txt"
if load_params:
self.nloop,self.n_hidden_layer, self.n_input_f, self.n_hidden_f, self.n_output_f, params = load_weight_info(filename)
else:
self.nloop = 0
self.n_hidden_layer = 5
self.n_input_f = 109
self.n_hidden_f = 512
self.n_output_f = 37
params = load_initial_info(self.n_hidden_layer, self.n_input_f, self.n_hidden_f, self.n_output_f)
trX = trX[:,1:self.n_input_f]
trY = trY[:,1:self.n_output_f]
print trX.shape
print trY.shape
print self.nloop, self.n_hidden_layer, self.n_input_f, self.n_hidden_f, self.n_output_f
X = T.fmatrix()
Y = T.fmatrix()
py_x = self._model(X, params)
y_x = py_x
#cost = T.mean(T.nnet.categorical_crossentropy(py_x, Y))
cost = T.mean(T.sqr(py_x - Y))
#params = [w_h, w_h1, w_h2, w_h3, w_o]
updates = self._sgd(cost, params)
train = theano.function(inputs=[X, Y], outputs=cost, updates=updates, allow_input_downcast=True)
self.predict = theano.function(inputs=[X], outputs=y_x, allow_input_downcast=True)
#LOG_FILENAME = 'DNN.log'
#logging.basicConfig(filename=LOG_FILENAME,level=logging.DEBUG)
for i in range(self.nloop, self.nloop + 1000):
print i
#logging.debug('loop' + str(i))
error_total = 0
arr_X_Y = zip(range(0, len(trX), 128), range(128, len(trX), 128))
for start, end in arr_X_Y:
cost = train(trX[start:end], trY[start:end])
error_total += cost
#print cost
last_element = arr_X_Y[len(arr_X_Y)-1][0]
if last_element < len(trX):
cost = train(trX[last_element: len(trX)], trY[last_element:len(trY)])
error_total += cost
print error_total / len(trX)
save_weight_info( filename, i, self.n_hidden_layer, self.n_input_f, self.n_hidden_f, self.n_output_f, params, error_total)
id_file = 1 - id_file
filename = weight_folder + 'Phonemic_DNN_SGD_id_' + str(id_file) + ".txt"
def _training_DNN(self):
trX, trY, self.missing_filename_list, = read_features(self.test_number, self.n_input_f, self.n_output_f)
trX = trX[:, 1 : self.n_input_f]
trY = trY[:, 1 : self.n_output_f]
print trX.shape
print trY.shape
print self.nloop, self.n_hidden_layer, self.n_input_f, self.n_hidden_f, self.n_output_f
X = T.fmatrix()
Y = T.fmatrix()
py_x = self._model(X, self.params)
y_x = py_x
# cost = T.mean(T.nnet.categorical_crossentropy(py_x, Y))
cost = T.mean(T.sqr(py_x - Y))
# params = [w_h, w_h1, w_h2, w_h3, w_o]
updates = self._sgd(cost, self.params)
train = theano.function(inputs=[X, Y], outputs=cost, updates=updates, allow_input_downcast=True)
self.predict = theano.function(inputs=[X], outputs=y_x, allow_input_downcast=True)
# LOG_FILENAME = 'DNN.log'
# logging.basicConfig(filename=LOG_FILENAME,level=logging.DEBUG)
for i in range(self.nloop, self.nloop + 500):
print i
# logging.debug('loop' + str(i))
error_total = 0
arr_X_Y = zip(range(0, len(trX), 128), range(128, len(trX), 128))
for start, end in arr_X_Y:
cost = train(trX[start:end], trY[start:end])
error_total += cost
# print cost
last_element = arr_X_Y[len(arr_X_Y) - 1][0]
if last_element < len(trX):
cost = train(trX[last_element : len(trX)], trY[last_element : len(trY)])
error_total += cost
print error_total / len(trX)
save_weight_info(
self.filename,
i,
self.n_hidden_layer,
self.n_input_f,
self.n_hidden_f,
self.n_output_f,
self.params,
error_total,
)
self.id_file = 1 - self.id_file
self.filename = self.weight_folder + "Phonemic_DNN_SGD_id_" + str(self.id_file) + ".txt"
def deep_neural_network():
trX, trY = read_features()
X = T.fmatrix()
Y = T.fmatrix()
load_params = False
hidden_layer = '6_layers/' # = n_hidden layer below
artic = 'artic/'
measure = 'SQR/'
id_file = 0
weight_folder = '../weight_DNN/' + hidden_layer + measure + artic
if not os.path.exists(weight_folder):
os.makedirs(weight_folder)
filename = weight_folder + 'Phonemic_DNN_SGD_id_' + str(id_file) + ".txt"
if load_params:
nloop,n_hidden_layer, n_input_f, n_hidden_f, n_output_f, params, bias = load_weight_info(filename)
else:
print "load Initial"
nloop = 0
n_hidden_layer = 1
n_input_f = 20
n_hidden_f = 100
n_output_f = 15
params, bias = load_initial_info(n_hidden_layer, n_input_f, n_hidden_f, n_output_f)
trX = trX[:,1:n_input_f]
trY = trY[:,1:n_output_f]
#trX = trX[1:200,1:2]
#trY = trY[1:200:,1:2]
print trX.shape
print trY.shape
print nloop,n_hidden_layer, n_input_f, n_hidden_f, n_output_f
#print params
print "_-----------"
#print bias
py_x = model(X, params, bias)
y_x = py_x
#cost = T.mean(T.nnet.categorical_crossentropy(py_x, Y))
cost = T.mean(T.sqr(py_x - Y))
updates = sgd(cost, params, bias)
# for u in xrange(len(params)):
# print params[u]
# c = params[u].get_value()
# print c.shape
# for u in xrange(len(bias)):
# print bias[u]
# c = bias[u].get_value()
# print c.shape
#exit()
train = theano.function(inputs=[X, Y], outputs=cost, updates=updates, allow_input_downcast=True)
predict = theano.function(inputs=[X], outputs=y_x, allow_input_downcast=True)
LOG_FILENAME = 'DNN.log'
logging.basicConfig(filename=LOG_FILENAME,level=logging.DEBUG)
for i in range(nloop, nloop + 10):
print "i ", i
#logging.debug('loop' + str(i))
error_total = 0
arr_X_Y = zip(range(0, len(trX), 128), range(128, len(trX), 128))
#arr_X_Y = zip(range(0, len(trX), 1), range(1, len(trX), 1))
for start, end in arr_X_Y:
cost = train(trX[start:end], trY[start:end])
error_total += cost
#print cost
print error_total
# last_element = arr_X_Y[len(arr_X_Y)-1][0]
# if last_element < len(trX):
# cost = train(trX[last_element: len(trX)], trY[last_element:len(trY)])
# error_total += cost
# print error_total / len(trX)
save_weight_info( filename, i, n_hidden_layer, n_input_f, n_hidden_f, n_output_f, params, error_total, bias)
id_file = 1 - id_file
filename = weight_folder + 'Phonemic_DNN_SGD_id_' + str(id_file) + ".txt"
#exit()
#plt.plot(trX,trY,'.')
#plt.plot(trX,trX * w.get_value() + b.get_value(), "red")
exit()
feature_out_dir = '/home/danglab/Phong/norm/output_norm/'
test_dir = '/home/danglab/Phong/TestData/Features_Norm/minus/6dB/'
dnn_predict_dir = '/home/danglab/DNN_Predict/DNN_Bias/'+ measure + artic + 'minus/6dB/'
if not os.path.exists(dnn_predict_dir):
os.makedirs(dnn_predict_dir)
listtest = sorted(os.listdir(test_dir))
cnt = 0
for afile in listtest:
#print afile #usctimit_ema_f1_001_005_100ms_noise_in.txt
test_arr, factors = read_file_test(test_dir + afile, n_input_f, "factors") #read a missing_feature
find_ = [m.start() for m in re.finditer('_', afile)]
file_mat = (afile.replace(afile[find_[4]:find_[6]],'')).replace('in.','out.') #usctimit_ema_f1_001_005_out.txt
#test_res_arr = read_file_test(feature_out_dir + file_mat, n_output_f) #read an original output feature
energy = test_arr[:,0] #ko cho energy vao DNN
test_arr = test_arr[:,1:n_input_f]
print factors
write_predict_2_file(dnn_predict_dir + afile.replace(afile[find_[5]:find_[6]],'').replace("_out",''), energy, predict(test_arr), factors) # write result to file
def deep_neural_network():
trX, trY = read_features()
trX, mask, max_x = abs_normal_matrix(trX)
for u in xrange(trX.shape[0]):
trY[u] = np.concatenate((trX[u][0:13], trX[u][37:37+24]))
#print trX.shape
#print trY.shape
X = T.fmatrix()
Y = T.fmatrix()
load_params = True
hidden_layer = '6_layers/' # = n_hidden layer below
artic = 'artic/'
id_file = 0
weight_folder = '../weight_DNN/' + hidden_layer + artic
if not os.path.exists(weight_folder):
os.makedirs(weight_folder)
filename = weight_folder + 'Phonemic_DNN_SGD_id_' + str(id_file) + ".txt"
if load_params:
nloop,n_hidden_layer, n_input_f, n_hidden_f, n_output_f, params = load_weight_info(filename)
else:
nloop = 0
n_hidden_layer = 6
n_input_f = 109
n_hidden_f = 512
n_output_f = 37
params = load_initial_info(n_hidden_layer, n_input_f, n_hidden_f, n_output_f)
trX = trX[:,1:n_input_f]
print trX.max(), trX.min()
trY = trY[:,1:n_output_f]
print trY.max(), trY.min()
#print trX.shape
#print trY.shape
print "trX"
#print trX
print "trY"
#print trY
print nloop,n_hidden_layer, n_input_f, n_hidden_f, n_output_f
py_x = model(X, params)
y_x = py_x
#cost = T.mean(T.nnet.categorical_crossentropy(py_x, Y))
cost = T.mean(T.sqr(py_x - Y))
#params = [w_h, w_h1, w_h2, w_h3, w_o]
updates = sgd(cost, params)
train = theano.function(inputs=[X, Y], outputs=cost, updates=updates, allow_input_downcast=True)
predict = theano.function(inputs=[X], outputs=y_x, allow_input_downcast=True)
LOG_FILENAME = 'DNN.log'
logging.basicConfig(filename=LOG_FILENAME,level=logging.DEBUG)
for i in range(nloop, nloop + 1):
print i
#logging.debug('loop' + str(i))
error_total = 0
arr_X_Y = zip(range(0, len(trX), 128), range(128, len(trX), 128))
for start, end in arr_X_Y:
cost = train(trX[start:end], trY[start:end])
error_total += cost
#print cost
last_element = arr_X_Y[len(arr_X_Y)-1][0]
#logging.warning(str(params[n_hidden_layer - 1].get_value()))
if last_element < len(trX):
cost = train(trX[last_element: len(trX)], trY[last_element:len(trY)])
error_total += cost
print error_total #/ len(trX)
save_weight_info( filename, i, n_hidden_layer, n_input_f, n_hidden_f, n_output_f, params, error_total)
id_file = 1 - id_file
filename = weight_folder + 'Phonemic_DNN_SGD_id_' + str(id_file) + ".txt"
#feature_out_dir = '/home/danglab/Phong/norm/output_norm/'
test_dir = '/home/danglab/Phong/TestData/Features/minus/6dB/'
dnn_predict_dir = '/home/danglab/DNN_Predict/normal_all/' + artic + 'minus/6dB/'
if not os.path.exists(dnn_predict_dir):
os.makedirs(dnn_predict_dir)
listtest = sorted(os.listdir(test_dir))
cnt = 0
for afile in listtest:
#print afile #usctimit_ema_f1_001_005_100ms_noise_in.txt
test_arr = read_file_test(test_dir + afile, n_input_f, "factors") #read a missing_feature
find_ = [m.start() for m in re.finditer('_', afile)]
file_mat = (afile.replace(afile[find_[4]:find_[6]],'')).replace('in.','out.') #usctimit_ema_f1_001_005_out.txt
#test_res_arr = read_file_test(feature_out_dir + file_mat, n_output_f) #read an original output feature
test_arr, mask, max_arr = abs_normal_matrix(test_arr)
#print test_arr
energy = test_arr[:,0] #ko cho energy vao DNN
test_arr = test_arr[:,1:n_input_f]
#print "max_arr", max_arr
write_predict_2_file(dnn_predict_dir + afile.replace(afile[find_[5]:find_[6]],'').replace("_out",''), energy, predict(test_arr), mask, max_arr) # write result to file