def load_finetuning_output_txt(self):
txt = open(env_paths.get_dbn_output_txt_path(), "r")
while True:
line = txt.readline()
if not line:
break
self.output_txt.append(line)
def load_finetuning_output_txt(self):
txt = open(env_paths.get_dbn_output_txt_path(),"r")
while True:
line = txt.readline()
if not line:
break
self.output_txt.append(line)
def save_output(self, finetuning = True):
"""
Save the output of the progress of the training process for the pretraining or the finetuning.
@param finetuning: If finetuning is True, the error for finetuning should be saved and vice versa.
"""
p = env_paths.get_dbn_output_txt_path() if finetuning else env_paths.get_rbm_output_txt_path()
out = open(p,"w")
for elem in self.output_txt:
out.write(elem+"\n")
out.close()
self.output_txt = []
def save_output(self, finetuning=True):
"""
Save the output of the progress of the training process for the pretraining or the finetuning.
@param finetuning: If finetuning is True, the error for finetuning should be saved and vice versa.
"""
p = env_paths.get_dbn_output_txt_path(
) if finetuning else env_paths.get_rbm_output_txt_path()
out = open(p, "w")
for elem in self.output_txt:
out.write(elem + "\n")
out.close()
self.output_txt = []
def save_dbn(weight_matrices,fine_tuning_error_train,fine_tuning_error_test,output = None):
"""
Save the deep belief network into serialized files.
@param weight_matrices: the weight matrices of the deep belief network.
"""
s.dump([w.tolist() for w in weight_matrices] , open( env_paths.get_dbn_weight_path(), "wb" ) )
s.dump(fine_tuning_error_train , open( env_paths.get_dbn_training_error_path(), "wb" ) )
s.dump(fine_tuning_error_test , open( env_paths.get_dbn_test_error_path(), "wb" ) )
if not output == None:
out = open(env_paths.get_dbn_output_txt_path(),"w")
for elem in output:
out.write(elem+"\n")
out.close()
def save_dbn(weight_matrices,
fine_tuning_error_train,
fine_tuning_error_test,
output=None):
"""
Save the deep belief network into serialized files.
@param weight_matrices: the weight matrices of the deep belief network.
"""
s.dump([w.tolist() for w in weight_matrices],
open(env_paths.get_dbn_weight_path(), "wb"))
s.dump(fine_tuning_error_train,
open(env_paths.get_dbn_training_error_path(), "wb"))
s.dump(fine_tuning_error_test,
open(env_paths.get_dbn_test_error_path(), "wb"))
if not output == None:
out = open(env_paths.get_dbn_output_txt_path(), "w")
for elem in output:
out.write(elem + "\n")
out.close()
