Created
November 4, 2024 11:21
-
-
Save theSoberSobber/346d2d282e9251833531ad34d3302f6f to your computer and use it in GitHub Desktop.
Trying Slide Extraction by Clustering on Clip Embeddings in Embeddings Space
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
yt-dlp https://www.youtube.com/watch?v=6T46sgty4Mk -o test-2 | |
mkdir img | |
git clone https://github.com/LexCybermac/smlr | |
ffmpeg -i test-2.mp4 -vf "fps=1" img/frame_%04d.png | |
pip install torch torchvision numpy Pillow transformers tqdm pathlib annoy scipy | |
python .\smlr.py --image_directory .\img\ --clip_model openai/clip-vit-base-patch16 --threshold 0.22 --batch_size 192 | |
Or (didn't try) | |
https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/image_embeddings_analysis_part_1.ipynb |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment