File size: 371 Bytes
a618bc2
 
 
 
 
1
2
3
4
5
# Download datasets:  
* Download and decompress tsv file from here: https://github.com/google-research-datasets/wit/blob/main/DATA.md  
* Use `prepare_wit.py` to download images from Wikipedia.  
* Use `discard_incorrect_files` to filter out corrupt files.`TODO: Still some corrupt files are being kept.` `TODO: Make it a CLI`.  
* Finally, use `run-clip.sh` to train.