nicolabs/Open-Sora
1
0
Fork 0
mirror of https://github.com/hpcaitech/Open-Sora.git synced 2026-04-10 04:37:45 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

fix data_processing.md (#605)

Browse source
This commit is contained in:
ZXMMD 2025-02-20 16:41:27 +08:00 committed by GitHub
parent df5668cdf1
commit 8d132d7a84
1 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
docs/data_processing.md
View file

@ -46,19 +46,19 @@ torchrun --nproc_per_node 8 -m tools.scoring.aesthetic.inference \
--bs 1024 \
--num_workers 16
# 3.2 Filter by aesthetic scores. This should output ${ROOT_META}/meta_clips_info_fmin1_aes_aesmin5.csv
# 3.2 Filter by aesthetic scores. This should output ${ROOT_META}/meta_clips_info_fmin1_aes_aesmin5.0.csv
python -m tools.datasets.datautil ${ROOT_META}/meta_clips_info_fmin1_aes.csv --aesmin 5
# 4.1 Generate caption. This should output ${ROOT_META}/meta_clips_info_fmin1_aes_aesmin5_caption_part*.csv
# 4.1 Generate caption. This should output ${ROOT_META}/meta_clips_info_fmin1_aes_aesmin5.0_caption_part*.csv
torchrun --nproc_per_node 8 --standalone -m tools.caption.caption_llava \
${ROOT_META}/meta_clips_info_fmin1_aes_aesmin5.csv \
${ROOT_META}/meta_clips_info_fmin1_aes_aesmin5.0.csv \
--dp-size 8 \
--tp-size 1 \
--model-path /path/to/llava-v1.6-mistral-7b \
--prompt video
# 4.2 Merge caption results. This should output ${ROOT_META}/meta_clips_caption.csv
python -m tools.datasets.datautil ${ROOT_META}/meta_clips_info_fmin1_aes_aesmin5_caption_part*.csv --output ${ROOT_META}/meta_clips_caption.csv
python -m tools.datasets.datautil ${ROOT_META}/meta_clips_info_fmin1_aes_aesmin5.0_caption_part*.csv --output ${ROOT_META}/meta_clips_caption.csv
# 4.3 Clean caption. This should output ${ROOT_META}/meta_clips_caption_cleaned.csv
python -m tools.datasets.datautil \