0.3.0
·
396 commits
to master
since this release
model weights have been quantized, to reduce the model size by ~75%:
- face detection model: 21.7 MB -> 5.4 MB
- face recognition model: 28.7 MB -> 7.0 MB
- face landmark model: 21.9 MB -> 6.2 MB
plus model weights are sharded in chunks of 4 MB to allow them to be cached in the browser