def run_experiment(parser, use_gpu):
# parse experiment specific command line arguments
parser.add_argument('--learning-rate', dest='learning_rate', type=float,
default=0.01, help='Learning rate to use during training.')
args, unknown = parser.parse_known_args()
# pre-process data
process_raw_data(use_gpu, force_pre_processing_overwrite=False)
# run experiment
training_file = "data/preprocessed/sample.txt.hdf5"
validation_file = "data/preprocessed/sample.txt.hdf5"
model = ExampleModel(21, args.minibatch_size, use_gpu=use_gpu) # embed size = 21
train_loader = contruct_dataloader_from_disk(training_file, args.minibatch_size)
validation_loader = contruct_dataloader_from_disk(validation_file, args.minibatch_size)
print("TRAIN LOADER CONTENT", train_loader)
train_model_path = train_model(data_set_identifier="TRAIN",
model=model,
train_loader=train_loader,
validation_loader=validation_loader,
learning_rate=args.learning_rate,
minibatch_size=args.minibatch_size,
eval_interval=args.eval_interval,
hide_ui=args.hide_ui,
use_gpu=use_gpu,
minimum_updates=args.minimum_updates)
print(train_model_path)
def run_experiment():
# pre-process data
process_raw_data(False, force_pre_processing_overwrite=False)
# run experiment
# training_file = args.input_file
training_file = settings.BASE_DIR + "/protAPI/proteinnet/data/preprocessed/sample.txt.hdf5"
validation_file = settings.BASE_DIR + "/protAPI/proteinnet/data/preprocessed/sample.txt.hdf5"
# validation_file = args.input_file
model = MyModel(21, 5, use_gpu=False) # embed size = 21
train_loader = contruct_dataloader_from_disk(training_file, 5)
validation_loader = contruct_dataloader_from_disk(validation_file, 5)
train_model_path = train_model(data_set_identifier="TRAINXX",
model=model,
train_loader=train_loader,
validation_loader=validation_loader,
learning_rate=0.1,
minibatch_size=5,
eval_interval=5,
hide_ui=True,
use_gpu=False,
minimum_updates=1) # Epochs
print("Completed training, trained model stored at:")
print(train_model_path)
def run_experiment(parser, use_gpu):
# parse experiment specific command line arguments
parser.add_argument('--learning-rate', dest='learning_rate', type=float,
default=0.01, help='Learning rate to use during training.')
parser.add_argument('--input-file', dest='input_file', type=str,
default='data/preprocessed/protein_net_testfile.txt.hdf5')
args, _unknown = parser.parse_known_args()
# pre-process data
process_raw_data(use_gpu, force_pre_processing_overwrite=False)
# run experiment
training_file = args.input_file
validation_file = args.input_file
model = MyModel(21, args.minibatch_size, use_gpu=use_gpu) # embed size = 21
train_loader = contruct_dataloader_from_disk(training_file, args.minibatch_size)
validation_loader = contruct_dataloader_from_disk(validation_file, args.minibatch_size)
train_model_path = train_model(data_set_identifier="TRAIN",
model=model,
train_loader=train_loader,
validation_loader=validation_loader,
learning_rate=args.learning_rate,
minibatch_size=args.minibatch_size,
eval_interval=args.eval_interval,
hide_ui=args.hide_ui,
use_gpu=use_gpu,
minimum_updates=args.minimum_updates)
print("Completed training, trained model stored at:")
print(train_model_path)
def run_training(model_name, epochs, author, desc=""):
# pre-process data
process_raw_data(False, force_pre_processing_overwrite=False)
model_name = model_name.replace(' ', '')
# run experiment
# training_file = args.input_file
training_file = settings.BASE_DIR + "/protAPI/proteinnet/data/preprocessed/sample.txt.hdf5"
validation_file = settings.BASE_DIR + "/protAPI/proteinnet/data/preprocessed/sample.txt.hdf5"
# validation_file = args.input_file
# try:
dinamic_model = getattr(
importlib.import_module("protAPI.proteinnet.custom_models"),
model_name)
model = dinamic_model(21, use_gpu=False) # embed size = 21
train_loader = contruct_dataloader_from_disk(training_file, 5)
validation_loader = contruct_dataloader_from_disk(validation_file, 5)
train_model_path = train_model(data_set_identifier="TRAINXX",
model=model,
train_loader=train_loader,
validation_loader=validation_loader,
learning_rate=0.1,
minibatch_size=5,
eval_interval=5,
hide_ui=True,
use_gpu=False,
minimum_updates=epochs) # Epochs
print("Completed training, trained model stored at:")
print(train_model_path)
model_trained = ModelTrained(author=author,
name=model_name,
description=desc,
file=train_model_path)
model_trained.save()
send_report_mail("*****@*****.**",
title="Entrenamiento Listo",
html="",
file_paths=[train_model_path],
text="Tu modelo esta listo para que lo pruebes ")
def run_training(model_name, epochs, author, desc=""):
# pre-process data
epochs = int(epochs)
author = User.objects.get(pk=author)
# model_from_db = ModelStructure.objects.get(name=model_name)
# file_path = settings.BASE_DIR + "/protApi/proteinnet/custom_models.py"
# f = open(file_path, "a")
# f.write(model_from_db.code)
# f.close()
process_raw_data(False, force_pre_processing_overwrite=False)
model_name = model_name.replace(' ', '')
# run experiment
# training_file = args.input_file
training_file = settings.BASE_DIR + "/protAPI/proteinnet/data/preprocessed/sample.txt.hdf5"
validation_file = settings.BASE_DIR + "/protAPI/proteinnet/data/preprocessed/sample.txt.hdf5"
# validation_file = args.input_file
try:
dinamic_model = getattr(
importlib.import_module("protAPI.proteinnet.custom_models"),
model_name)
model = dinamic_model(21, use_gpu=False) # embed size = 21
train_loader = contruct_dataloader_from_disk(training_file, 5)
validation_loader = contruct_dataloader_from_disk(validation_file, 5)
train_model_path = train_model(data_set_identifier="TRAINXX",
model=model,
train_loader=train_loader,
validation_loader=validation_loader,
learning_rate=0.1,
minibatch_size=5,
eval_interval=5,
hide_ui=True,
use_gpu=False,
minimum_updates=epochs) # Epochs
print("Completed training, trained model stored at:")
print(train_model_path)
model_trained = ModelTrained(author=author,
name=model_name,
description=desc,
file=train_model_path)
model_trained.save()
print("Sending mail to", author.email)
send_report_mail(author.email,
title="Entrenamiento Listo",
html="",
file_paths=[train_model_path],
text="Tu modelo esta listo para que lo pruebes ")
except Exception as e:
print("Error en entrenamiento:", e)
print("Sending mail to", author.email)
send_report_mail(
author.email,
title="Entrenamiento Fallido",
html=
"Se detecto un error al intentar entrenar tu modelo: <h5 style='color:red'>"
+ str(e) + "</h5>",
file_paths=[],
text="Se detecto un error al intentar entrenar tu modelo:\n")