logging.info("Loading the datasets...")
# load data
data_loader = DataLoader(params)
train_data_path = os.path.join(args.data_dir, 'train', 'train_data.json')
data_loader.load_data(train_data_path,
split='train',
size_limit=args.dataset_size_limit)
# data_loader.split_data(split_ratio=params.split_ratio)
val_data_path = os.path.join(args.data_dir, 'val', 'val_data.json')
data_loader.load_data(val_data_path,
'val',
size_limit=args.dataset_size_limit)
# specify the train and val dataset sizes( append in data_loader
params.train_size = data_loader.get_dataset_size('train')
params.val_size = data_loader.get_dataset_size('val')
logging.info("- done.")
# Define the model and optimizer
model = net.Model(params).cuda() if params.cuda else net.Model(params)
# optimizer = optim.Adam(model.parameters(), lr=params.learning_rate)
optimizer = optim.Adadelta(model.parameters(), params.learning_rate)
scheduler = sched.LambdaLR(optimizer, lambda s: 1.) # Constant LR
# fetch loss function and metrics
loss_fn = model.loss_fn
metrics = {'EM': model.exact_match_score, 'f1': model.f1_score}
# Train the model
torch.manual_seed(230)
if params.cuda: torch.cuda.manual_seed(230)
# Get the logger
utils.set_logger(os.path.join(args.model_dir, 'evaluate.log'))
# Create the input data pipeline
logging.info("Creating the dataset...")
# load data
print(params)
data_loader = DataLoader(params)
data = data_loader.load_data(args.test_data_path)
# specify the test set size
params.test_size = data_loader.get_dataset_size('all')
test_data_iterator = data_loader.data_iterator(split='all', batch_size=params.batch_size)
logging.info("- done.")
# Define the model
model = net.Model(params).cuda() if params.cuda else net.Model(params)
loss_fn = model.loss_fn
metrics = {
'EM': model.exact_match_score,
'f1': model.f1_score
}
logging.info("Starting evaluation")