def main():
global args
args = parser.parse_args()
print("=> using pre-trained model '{}'".format(args.arch))
model = convnets.factory({'arch': args.arch},
cuda=True,
data_parallel=True)
extract_name = 'arch,{}_size,{}'.format(args.arch, args.size)
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
if args.dataset == 'coco':
if 'coco' not in args.dir_data:
raise ValueError('"coco" string not in dir_data')
dataset = datasets.COCOImages(args.data_split,
dict(dir=args.dir_data),
transform=transforms.Compose([
transforms.Scale(args.size),
transforms.CenterCrop(args.size),
transforms.ToTensor(),
normalize,
]))
elif args.dataset == 'vgenome':
if args.data_split != 'train':
raise ValueError('train split is required for vgenome')
if 'vgenome' not in args.dir_data:
raise ValueError('"vgenome" string not in dir_data')
dataset = datasets.VisualGenomeImages(args.data_split,
dict(dir=args.dir_data),
transform=transforms.Compose([
transforms.Scale(args.size),
transforms.CenterCrop(
args.size),
transforms.ToTensor(),
normalize,
]))
data_loader = DataLoader(dataset,
batch_size=args.batch_size,
shuffle=False,
num_workers=args.workers,
pin_memory=True)
dir_extract = os.path.join(args.dir_data, 'extract', extract_name)
path_file = os.path.join(dir_extract, args.data_split + 'set')
os.system('mkdir -p ' + dir_extract)
extract(data_loader, model, path_file, args.mode)
def main():
global args, options, model, cnn, transform, trainset
args = parser.parse_args()
options = {'logs': {'dir_logs': args.dir_logs}}
if args.path_opt is not None:
with open(args.path_opt, 'r') as handle:
options_yaml = yaml.load(handle)
options = utils.update_values(options, options_yaml)
print('## args')
pprint(vars(args))
print('## options')
pprint(options)
trainset = datasets.factory_VQA(options['vqa']['trainsplit'],
options['vqa'])
#options['coco'])
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
transform = transforms.Compose([
transforms.Scale(options['coco']['size']),
transforms.CenterCrop(options['coco']['size']),
transforms.ToTensor(),
normalize,
])
opt_factory_cnn = {'arch': options['coco']['arch']}
cnn = convnets.factory(opt_factory_cnn,
cuda=args.cuda,
data_parallel=False)
model = models.factory(options['model'],
trainset.vocab_words(),
trainset.vocab_answers(),
cuda=args.cuda,
data_parallel=False)
model.eval()
start_epoch, best_acc1, _ = load_checkpoint(
model, None, os.path.join(options['logs']['dir_logs'], args.resume))
my_local_ip = '192.168.0.32'
my_local_port = 3456
run_simple(my_local_ip, my_local_port, application)
def initialize(args, dataset="breast"):
options = {
'logs': {
'dir_logs': args.dir_logs
}
}
if args.path_opt is not None:
with open(args.path_opt, 'r') as handle:
options_yaml = yaml.load(handle)
options = utils.update_values(options, options_yaml)
print("\n>> load trainset...")
trainset = datasets.factory_VQA(options['vqa']['trainsplit'],
options['vqa'],
options['coco'],
options['vgenome'])
print("\n>> load cnn model...")
if dataset == "idrid":
cnn = convnets_idrid.factory(
{'arch': "resnet152_idrid"}, cuda=True, data_parallel=False)
elif dataset == "tools":
cnn = convnets_tools.factory(
{'arch': "resnet152_tools"}, cuda=True, data_parallel=False)
elif dataset == "breast":
cnn = convnets_breast.factory(
{'arch': "resnet152_breast"}, cuda=True, data_parallel=False)
elif dataset == "vqa2":
cnn = convnets.factory(
{'arch': "fbresnet152"}, cuda=True, data_parallel=False)
cnn = cnn.cuda()
print("\n>> load vqa model...")
model = load_vqa_model(args, dataset, args.vqa_model)
model = model.cuda()
return cnn, model, trainset