def train_deepsurv(x_train, y_train, x_test, y_test, **kwargs):
# Standardize the datasets
train_mean = x_train.mean(axis=0)
train_std = x_train.std(axis=0)
x_train = (x_train - train_mean) / train_std
x_test = (x_test - train_mean) / train_std
train_data = format_to_deepsurv(x_train, y_train)
valid_data = format_to_deepsurv(x_test, y_test)
hyperparams = get_hyperparams(kwargs)
# Set up Tensorboard loggers
# TODO improve the model_id for Tensorboard to better partition runs
model_id = str(hash(str(hyperparams)))
run_id = model_id + '_' + str(uuid.uuid4())
logger = TensorboardLogger(
'hyperparam_search',
os.path.join(logdir, "tensor_logs", model_id, run_id))
network = deepsurv.DeepSurv(n_in=x_train.shape[1], **hyperparams)
metrics = network.train(train_data,
n_epochs=num_epochs,
logger=logger,
update_fn=update_fn,
verbose=False)
result = network.get_concordance_index(**valid_data)
main_logger.info(
'Run id: %s | %s | C-Index: %f | Train Loss %f' %
(run_id, str(hyperparams), result, metrics['loss'][-1][1]))
return result
hyperparams = {
'L2_reg': 10.0,
'batch_norm': True,
'dropout': 0.4,
'hidden_layers_sizes': [25, 25],
'learning_rate': 1e-05,
'lr_decay': 0.001,
'momentum': 0.9,
'n_in': train_data['x'].shape[1],
'standardize': True
}
# enable tensorboard
experiment_name = 'test_experiment_sebastian'
logdir = 'logs/tensorboard/'
logger = TensorboardLogger(experiment_name, logdir = logdir)
# create an instance of DeepSurv using the hyperparams defined above
model = deep_surv.DeepSurv(**hyperparams)
# the type of optimizer to use
update_fn = lasagne.updates.nesterov_momentum
# check out http://lasagne.readthedocs.io/en/latest/modules/updates.html
# for other optimizers to use
n_epochs = 10001
# train the model
metrics = model.train(train_data, test_data, n_epochs = n_epochs,
logger = logger, update_fn = update_fn)
args = parse_args()
print("Arguments:",args)
# Load Dataset
print("Loading datasets: " + args.dataset)
datasets = utils.load_datasets(args.dataset)
norm_vals = {
'mean' : datasets['train']['x'].mean(axis =0),
'std' : datasets['train']['x'].std(axis=0)
}
# Train Model
# TODO standardize location of logs + results => have them go into same directory with same UUID of experiment
tensor_log_dir = "/shared/data/logs/tensorboard_" + str(args.dataset) + "_" + str(uuid.uuid4())
logger = TensorboardLogger("experiments.deep_surv", tensor_log_dir, update_freq = 10)
model = deep_surv.load_model_from_json(args.model, args.weights)
if 'valid' in datasets:
valid_data = datasets['valid']
else:
valid_data = None
metrics = model.train(datasets['train'], valid_data, n_epochs = args.num_epochs, logger=logger,
update_fn = utils.get_optimizer_from_str(args.update_fn),
validation_frequency = 100)
# Evaluate Model
with open(args.model, 'r') as fp:
json_model = fp.read()
hyperparams = json.loads(json_model)
train_data = datasets['train']