Make face detection a generator

Rudrabha / Wav2Lip

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs

https://synclabs.so

9.74k stars 2.11k forks source link

Make face detection a generator #14

Closed kousu closed 3 years ago

kousu commented 3 years ago

face_detect() is by far the slowest part of inference.py, and it also buffers all its results. This means getting results is slow and RAM is wasted. You could make face_detect() a generator instead and the output video would start being written immediately and your RAM usage would be bounded (by the batch size).

prajwalkr commented 3 years ago

Could you please submit a pull request for this change as well? Currently busy for a few days.

kousu commented 3 years ago

I am happy to do this. I love writing generators.

On September 5, 2020 3:58:41 AM EDT, Prajwal notifications@github.com wrote:

Closed #14.

-- You are receiving this because you authored the thread. Reply to this email directly or view it on GitHub: https://github.com/Rudrabha/Wav2Lip/issues/14#event-3732708295

-- kousu