shuffle=not args.get('sort_dataset'),
num_workers=args.get('num_workers'))
# test_dataset = TextDataset(test_data, dictionary, args.get('sort_dataset'), args.get('min_length'), args.get('max_length'))
# test_dataloader = TextDataLoader(dataset=test_dataset, dictionary=dictionary, batch_size=args.get('batch_size'), shuffle = not args.get('sort_dataset'))
logger.info("Training...")
# trainable_params = [p for p in model.parameters() if p.requires_grad]
if args.get('optimizer') == 'Adam':
optimizer = Adam(model.parameters(), lr=args.get('initial_lr'))
elif args.get('optimizer') == 'Adadelta':
optimizer = Adadelta(params=trainable_params,
lr=args.get('initial_lr'),
weight_decay=0.95)
else:
raise NotImplementedError()
lr_plateau = lr_scheduler.ReduceLROnPlateau(optimizer, factor=0.2, patience=5)
criterion = nn.CrossEntropyLoss
trainer = Trainer(model,
train_dataloader,
val_dataloader,
criterion=criterion,
optimizer=optimizer,
lr_schedule=args.get('lr_schedule'),
lr_scheduler=lr_plateau,
use_gpu=args.get('use_gpu'),
logger=logger)
trainer.run(epochs=args.get('epochs'))
logger.info("Evaluating...")
logger.info('Best Model: {}'.format(trainer.best_checkpoint_filepath))
train_dataset = TextDataset(train_data, dictionary, args.sort_dataset, args.min_length, args.max_length)
train_dataloader = TextDataLoader(dataset=train_dataset, dictionary=dictionary, batch_size=args.batch_size)
val_dataset = TextDataset(val_data, dictionary, args.sort_dataset, args.min_length, args.max_length)
val_dataloader = TextDataLoader(dataset=val_dataset, dictionary=dictionary, batch_size=64)
test_dataset = TextDataset(test_data, dictionary, args.sort_dataset, args.min_length, args.max_length)
test_dataloader = TextDataLoader(dataset=test_dataset, dictionary=dictionary, batch_size=64)
logger.info("Constructing model...")
model = args.model(n_classes=preprocessor.n_classes, dictionary=dictionary, args=args)
if args.use_gpu:
model = model.cuda()
logger.info("Training...")
trainable_params = [p for p in model.parameters() if p.requires_grad]
if args.optimizer == 'Adam':
optimizer = Adam(params=trainable_params, lr=args.initial_lr)
if args.optimizer == 'Adadelta':
optimizer = Adadelta(params=trainable_params, lr=args.initial_lr, weight_decay=0.95)
lr_plateau = lr_scheduler.ReduceLROnPlateau(optimizer, factor=0.7, patience=5, min_lr=0.0001)
criterion = nn.CrossEntropyLoss
trainer = Trainer(model, train_dataloader, val_dataloader,
criterion=criterion, optimizer=optimizer,
lr_schedule=args.lr_schedule, lr_scheduler=lr_plateau,
use_gpu=args.use_gpu, logger=logger)
trainer.run(epochs=args.epochs)
logger.info("Evaluating...")
logger.info('Best Model: {}'.format(trainer.best_checkpoint_filepath))
model.load_state_dict(torch.load(trainer.best_checkpoint_filepath)) # load best model
evaluator = Evaluator(model, test_dataloader, use_gpu=args.use_gpu, logger=logger)
evaluator.evaluate()
