transforms.Resize(args.resize))
if args.train:
train_set = ImageDataset(args.train_manifest, train_transforms)
train_loader = DataLoader(train_set,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers)
eval_set = ImageDataset(args.val_manifest, test_transforms)
eval_loader = DataLoader(eval_set,
batch_size=args.batch_size,
shuffle=False,
num_workers=args.num_workers)
logger.add_general_data(model, train_loader)
train(model, criterion, optimizer, train_loader, eval_loader,
args.epochs, lr_scheduler, args.gpu)
print_training_summary(logger, model.name)
else:
training_ = torch.load(args.model_path)
model.load_state_dict(training_["model"])
print(
f"Loaded model {model.name} trained for {training_['epoch']} epochs. Results: {training_['result']}"
)
test_set = ImageDataset(args.test_manifest, test_transforms)
test_loader = DataLoader(test_set,
batch_size=args.batch_size,
shuffle=False,
num_workers=4)
