How to generate these pkl file in the Data Section? about semantics-assistedvideocaptioning HOT 2 CLOSED

I pre-process the annotations and word embedding by command line.
The corpus files consist of six parts: 1. annotations of training split represented by word index; 2. annotations of validation split represented by word index; 3. annotations of test split represented by word index; 4. the mapping from a real word to a word index; 5. the mapping from a word index to a real word. 6. pretrained word embedding from GloVe-840B-300d.
I think you can recreate such pickle with the help of my description and the provided word mapping.

The reference pickle files consists of three parts: 1. the human-readable ground truth of training split; 2. the human-readable ground truth of validation split; 3. the human-readable ground truth of test split.

The preprocess codes of npy files have been provided in the repository.

from semantics-assistedvideocaptioning.

Thanks a lot

from semantics-assistedvideocaptioning.