MarcusNerva / HMN

[CVPR2022] Official code for Hierarchical Modular Network for Video Captioning. Our proposed HMN is implemented with PyTorch.
MIT License
52 stars 9 forks source link

FileNotFoundError: [Errno 2] No such file or directory: './data/MSVD/MSVD_splits/MSVD_train_list.pkl' #4

Closed adeljalalyousif closed 2 years ago

adeljalalyousif commented 2 years ago

Really great job, but how can I get the _MSVDsplits files : MSVD_test_list.pkl MSVD_train_list.pkl
MSVD_valid_list.pkl
I get this error while running main.py and the (split_data.py) is not working because the data files are not available: parser = argparse.ArgumentParser() parser.add_argument('--dataset_name', type=str, default='-1', help='dataset name (MSVD | MSRVTT)') parser.add_argument('--split_dir', type=str, default='-1', help='dir contains split_list') parser.add_argument('--data_path', type=str, default='-1', help='the path of unsplited data') parser.add_argument('--data_name', type=str, default='-1', help='name of unsplited data') parser.add_argument('--target_dir', type=str, default='-1', help='where do you want to place your data') parser.add_argument('--split_objects', action='store_true')

Thank you so much...

MarcusNerva commented 2 years ago

Problem solved, splits.pkl have been uploaded. Please check again.

adeljalalyousif commented 2 years ago

Thank you so much for your reply. I need your advice please. I am a PhD student working on real-time video captioning, Which one is faster to inference (CNN + LSTM) or (CNN + Transformer) or something else? Can you provide me with the inference file please , ajalal289@gmail.com. thanks again