def extract_imgs_feat():
encoder = Encoder(opt.resnet101_file)
encoder.to(opt.device)
encoder.eval()
imgs = os.listdir(opt.imgs_dir)
imgs.sort()
if not os.path.exists(opt.out_feats_dir):
os.makedirs(opt.out_feats_dir)
with h5py.File(os.path.join(opt.out_feats_dir, '%s_fc.h5' % opt.dataset_name)) as file_fc, \
h5py.File(os.path.join(opt.out_feats_dir, '%s_att.h5' % opt.dataset_name)) as file_att:
try:
for img_nm in tqdm.tqdm(imgs, ncols=100):
img = skimage.io.imread(os.path.join(opt.imgs_dir, img_nm))
with torch.no_grad():
img = encoder.preprocess(img)
img = img.to(opt.device)
img_fc, img_att = encoder(img)
file_fc.create_dataset(img_nm,
data=img_fc.cpu().float().numpy())
file_att.create_dataset(img_nm,
data=img_att.cpu().float().numpy())
except BaseException as e:
file_fc.close()
file_att.close()
print(
'--------------------------------------------------------------------'
)
raise e
from opts import parse_opt
from models.decoder import Decoder
from models.encoder import Encoder
opt = parse_opt()
assert opt.test_model, 'please input test_model'
assert opt.image_file, 'please input image_file'
encoder = Encoder(opt.resnet101_file)
encoder.to(opt.device)
encoder.eval()
img = skimage.io.imread(opt.image_file)
with torch.no_grad():
img = encoder.preprocess(img)
img = img.to(opt.device)
fc_feat, att_feat = encoder(img)
print("====> loading checkpoint '{}'".format(opt.test_model))
chkpoint = torch.load(opt.test_model, map_location=lambda s, l: s)
decoder = Decoder(chkpoint['idx2word'], chkpoint['settings'])
decoder.load_state_dict(chkpoint['model'])
print("====> loaded checkpoint '{}', epoch: {}, train_mode: {}".format(
opt.test_model, chkpoint['epoch'], chkpoint['train_mode']))
decoder.to(opt.device)
decoder.eval()
rest, _ = decoder.sample(fc_feat,
att_feat,
beam_size=opt.beam_size,
