Songyuanwei 468be76a35 | 4 weeks ago | |
---|---|---|
.. | ||
README.md | 4 weeks ago | |
eval_videos_metrics.py | 4 weeks ago |
This folder is a collection of utility scripts, listed and explained below.
All scripts need to be run in the root path of project, unless otherwise noted.
This script contains code and scripts for diffusion model evaluation, e.g.,
Note that all the above metrics are computed based on neural network models.
A convincing evaluation for diffusion models requires both visually qualitative comparision and quantitative measure. A higher CLIP score does not necessarily show one model is better than another.
To compute the CLIP score on all frames of output video and report the average cosine similarity between all video frame pairs, please run
python ./scripts/eval_videos_metrics.py --video_data_dir <path-to-video-dir> --video_caption_path <path-to-video-caption-path> --model_name <HF-model-name> --metric clip_score_frame
To compute the average CLIP score between all frames of the output video and the corresponding editing prompts, please run
python ./scripts/eval_videos_metrics.py --video_data_dir <path-to-video-dir> --video_caption_path <path-to-video-caption-path> --model_name <HF-model-name> --metric clip_score_text
Format of .csv
:
video,caption
video_name1.mp4,"an airliner is taxiing on the tarmac at Dubai Airport"
video_name2.mp4,"a pigeon sitting on the street near the house"
...
one for all, Optimal generator with No Exception
https://github.com/mindspore-lab/mindone
Python Text Markdown Shell
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》