else:
# create new folder.
t = datetime.datetime.now()
cur_time = '%s-%s-%s' %(t.day, t.month, t.hour)
save_path = os.path.join(opt.outf, opt.decoder + '.' + cur_time)
try:
os.makedirs(save_path)
except OSError:
pass
####################################################################################
# Data Loader
####################################################################################
dataset = dl.train(input_img_h5=opt.input_img_h5, input_ques_h5=opt.input_ques_h5,
input_json=opt.input_json, negative_sample = opt.negative_sample,
num_val = opt.num_val, data_split = 'train')
dataset_val = dl.validate(input_img_h5=opt.input_img_h5, input_ques_h5=opt.input_ques_h5,
input_json=opt.input_json, negative_sample = opt.negative_sample,
num_val = opt.num_val, data_split = 'test')
dataloader = torch.utils.data.DataLoader(dataset, batch_size=opt.batchSize,
shuffle=True, num_workers=int(opt.workers))
dataloader_val = torch.utils.data.DataLoader(dataset_val, batch_size=1,
shuffle=False, num_workers=int(opt.workers))
####################################################################################
# Build the Model
####################################################################################
else:
# create new folder.
t = datetime.datetime.now()
cur_time = '%s-%s-%s' %(t.day, t.month, t.hour)
save_path = os.path.join(opt.outf, opt.decoder + '.' + cur_time)
try:
os.makedirs(save_path)
except OSError:
pass
####################################################################################
# Data Loader
####################################################################################
dataset = dl.train(input_img_h5=opt.input_img_h5, input_ques_h5=opt.input_ques_h5,
input_json=opt.input_json, negative_sample = opt.negative_sample,
num_val = opt.num_val, data_split = 'train')
dataset_val = dl.validate(input_img_h5=opt.input_img_h5, input_ques_h5=opt.input_ques_h5,
input_json=opt.input_json, negative_sample = opt.negative_sample,
num_val = opt.num_val, data_split = 'test')
dataloader = torch.utils.data.DataLoader(dataset, batch_size=opt.batchSize,
shuffle=True, num_workers=int(opt.workers))
dataloader_val = torch.utils.data.DataLoader(dataset_val, batch_size=1,
shuffle=False, num_workers=int(opt.workers))
####################################################################################
# Build the Model
####################################################################################
if __name__ == '__main__':
args = parse_args()
os.environ["CUDA_VISIBLE_DEVICES"] = str(args.gpuid)
args.seed = random.randint(1, 10000)
torch.manual_seed(args.seed)
torch.cuda.manual_seed(args.seed)
torch.backends.cudnn.benchmark = True
batch_size = args.batch_size
train_dataset = dl.train(input_img_h5=args.input_img_h5,
input_imgid=args.input_imgid,
input_ques_h5=args.input_ques_h5,
input_json=args.input_json,
negative_sample=args.negative_sample,
num_val=args.num_val,
data_split='train')
eval_dateset = dl.validate(input_img_h5=args.input_img_h5,
input_imgid=args.input_imgid,
input_ques_h5=args.input_ques_h5,
input_json=args.input_json,
negative_sample=args.negative_sample,
num_val=args.num_val,
data_split='val')
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=args.batch_size,
shuffle=True,
