How to train on a custom dataset?

[chandanasreemala]

1. How to train the model on a custom dataset. I have seen the commit you pushed to train with voxceleb2 dataset which it downloads the data from the internet. But how can I train the model with a completely new dataset which is in my local pc?

2)This may be a dumb question but is there any cap on the maximum number of different classes(In this case people) the model can identify? Is it in the range of hundreads or thousands?

[Wadaboa]

Hi,

Thanks for opening the issue. Let me answer in order.

1. I've already provide some guidelines on how to support custom datasets. You can refer to issues data set #3 and voxceleb dataset #5 for that. If you have more specific questions, I'm happy to help, but please elaborate your ask.
2. There is no cap on the maximum number of classes the model can work with. Though, when you get to the order of thousands it is generally better to work with metric-learning-based losses (such as the ArcFace loss I mention in the README), instead of the standard classification-based losses (such as cross-entropy).

Alessio.