search

simon-ging / coot-videotext

COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning
Apache License 2.0
288 stars 55 forks source link

how can i get a h5 like this "provided_embeddings/yc2_100m_coot_val.h5" #36

Open yuhao910716 opened 3 years ago

yuhao910716 commented 3 years ago

Describe the bug A clear and concise description of what the bug is.

To Reproduce Steps to reproduce the behavior.

Expected behavior A clear and concise description of what you expected to happen.

Screenshots If applicable, add screenshots to help explain your problem.

System Info:

Additional context i want to test a MP4，but idont know how to transform MP4 into.h5 someone can help me? thank you!

simon-ging commented 3 years ago

Hi,

You would extract features as described in this issue https://github.com/gingsi/coot-videotext/issues/17

Then you run the retrieval model to generate the embeddings as described in the readme.

Best