if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Generate captions por test samples')
parser.add_argument('-chckpt', '--checkpoint_path', type=str, default='pretrain/chckpt.pt',
help='Set the path to pre-trained model (default is pretrain/chckpt.pt).')
parser.add_argument('-data', '--dataset_folder', type=str, default='data/MSVD',
help='Set the path to dataset folder (default is data/MSVD).')
parser.add_argument('-out', '--output_folder', type=str, default='results/MSVD',
help='Set the path to output folder (default is results/MSVD).')
args = parser.parse_args()
# load vocabulary
with open(os.path.join(args.dataset_folder, 'corpus.pkl'), "rb") as f:
corpus = pickle.load(f)
idx2word_dict = corpus[4]
vocab = Vocabulary.from_idx2word_dict(idx2word_dict, False)
print('Size of vocabulary: {}'.format(len(vocab)))
# Pretrained Embedding
pretrained_embedding = torch.Tensor(corpus[5])
cnn_feature_size = 2048
c3d_feature_size = 4096
i3d_feature_size = 400
eco_feature_size = 1536
res_eco_features_size = 3584
cnn_global_size = 512
projected_size = 512
hidden_size = 1024 # Number of hidden layer units of the cyclic network
mid_size = 128 # The middle of the boundary detection layer represents the dimension
