def resnet50(pretrained=False, **kwargs):
model = ResNet(MyBottleneck, [3, 4, 6, 3], **kwargs)
if pretrained:
model.load_state_dict(load(pretrained))
model.eval()
return model
short_name, extension = os.path.splitext(img_file_name)
img_id_int = int(short_name.split('_')[-1])
img_id = str(img_id_int)
img = os.path.join(self.root, 'vqa', 'image', self.split,
img_file_name)
img = Image.open(img).convert('RGB')
return img_id, transform(img)
def __len__(self):
return self.length
batch_size = 50
resnet = ResNet().to(device)
resnet.eval()
def create_dataset(split):
dataset = VQAImg(vqa_root, split)
dataloader = DataLoader(dataset, batch_size=batch_size, num_workers=4)
total_img_num = len(dataset)
print('found {} images in {} split ...'.format(total_img_num, split))
f = h5py.File('data/vqa/spatial/{}_spatial.hdf5'.format(split),
'w',
libver='latest')
dset = f.create_dataset('data', (total_img_num, 2048, 7, 7), dtype='f4')
info = {}
