face-recognition

I've ran into this issue for a couple hours and I ended up editing the dist library adding two new functions called fetchVideo and bufferToVideo that works pretty much like the fetchImage and bufferToImage functions.

I'll leave it here to help somebody else with the same issue and in case someone wants to include it on future releases.

face-api.js

...
exports.fetchVideo = fetc

Hi
when I do classification with the pretrained vggface2 model, how do I match a probability to a name? do you have a list of labels for the trained model?

Thanks

To improve performance on huge images, we resize it before face detection. The downside of this is that small faces could be not recognized.

Some users complain that we do not catch too small faces in their 1080p camera.

We need to make resizing a configurable variable, so users choose if we need to resize at all, or what resize to apply

Here is where we init the variable in Python:
htt