SthPhoenix

For some reason now it's working ) I have tried your dataset with dlib Chinese whispers with threshold 0.85, it gives around 2500 clusters with a lot of outliers -...

> What do you mean by If you filter your dataset by embedding norm > 20 ? You can normalize embedding following way: ``` embedding_norm = np.linalg.norm(embedding) normed_embedding = embedding...

> @SthPhoenix Sorry for abandoning this post for so long! > > I'm a little confused about the embedding norm, are you saying to filter with `embedding_norm > 20`, and...

> But then how would you classify newly incoming points? Would you also have to use `np.linalg.norm` on new point before passing into a trained classifier? Exactlу! Though that's not...

Normalization should not influence clustering, have you tried manually inspecting those clusters? Possibly in such cases input data is of lower quality.

Hi! I have no much experience in such scenario, as I have noted somewhere else you could try combining detection\feature extraction with some kind of tracker algo, like FastMOT. Also...

Hi! As for detection I would recommend using yolov5m or even yolov5l for best accuracy and recall including hard faces (strongly rotated ones etc.) But if your use case dont...

Hi! I can't figure out what have you missed, looks like you have done everything needed to add model. I have just committed code to support `adaface_ir101_webface12m` model, including automatic...

Here's conversion code: ```python import os import numpy as np import torch import onnx import net adaface_models = { "ir_101": "./pretrained/adaface_ir101_webface12m.ckpt", } def load_pretrained_model(architecture="ir_101"): # load model and pretrained statedict...

Hi! Yes, all the difference is in GN vs BN, nothing else was changed during training. I've commited GN config to main insightface repo, if I recall correctly, so all...