Mirrors
/
EveryDream2trainer
mirror of https://github.com/victorchall/EveryDream2trainer.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update CAPTION.md

This commit is contained in:
Victor Hall 2023-07-11 15:46:41 -04:00 committed by GitHub
parent 8d133b6193
commit a6032bee35
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
doc/CAPTION.md
View File

@ -4,7 +4,7 @@
`python caption_fl.py --data_root input --min_new_tokens 20 --max_new_tokens 30 --num_beams 3 --model "openflamingo/OpenFlamingo-9B-vitl-mpt7b"` `python caption_fl.py --data_root input --min_new_tokens 20 --max_new_tokens 30 --num_beams 3 --model "openflamingo/OpenFlamingo-9B-vitl-mpt7b"`
This script uses two example image/caption pairs located in the example folder to prime the system to caption, then captions the images in the input folder. It will save a `.txt` file of the same base filename with the captoin in the same folder. This script uses two example image/caption pairs located in the `/example` folder to prime the system to caption, then captions the images in the input folder. It will save a `.txt` file of the same base filename with the captoin in the same folder.
This script currently requires an AMPERE or newer GPU due to using bfloat16. This script currently requires an AMPERE or newer GPU due to using bfloat16.