antoine77340 / S3D_HowTo100M

S3D Text-Video model trained on HowTo100M using MIL-NCE
Apache License 2.0
191 stars 21 forks source link

Question in Sentence Embedding #13

Closed JoanFM closed 2 years ago

JoanFM commented 2 years ago

I have a question about the Sentence_Embedding model forward implementation.

Why is torch max applied after the first Fully Conbected layer? Is this better than doing it before and averaging all the word embeddings of a sentence before the FC Layers?

Thanks for the clarification

antoine77340 commented 2 years ago

Yes it was better to do the max than the average.

JoanFM commented 2 years ago

Thanks!