SthPhoenix

Hi! `src/converters` are outdated. You can try checking [src/api_trt/modules/model_zoo/getter.py](https://github.com/SthPhoenix/InsightFace-REST/blob/master/src/api_trt/modules/model_zoo/getter.py) lines 146-163 for you desired use-case. Something like this should work: ``` import onnx from ..converters.onnx_to_trt import convert_onnx from ..converters.reshape_onnx import...

Hi! First of all face image must be properly aligned 112x112 image from detection step, you can't just take arbitrary image containing face and resize it to 112x112. Secondly you...

How did you get this error? This doesn't seems to be related to this repo.

Hi! I'll check benchmarks with latest version, but if I recall correctly you can achieve speeds around 1000 im/sec on rtx2080 only with fastest and lower quality models and small...

Well, in this scenario with w600k_r50 model and batch_size=64 you could achieve up to 2k faces/sec if you will use 2 rtx2080 GPU setup one for detection one for recognition....

Accuracy is pretty good, I'd say its mostly performs better. Yes, glintr100 is approx. 2x slower. You can set time threshold for example 0.1s for waiting for batch, if there...

Hi! I haven't worked in this direction yet, you could try looking at FastMOT object tracker, which seems a good fit for this task. Alternatively you could try use faster...

You can try checking FAISS as base for vector search, it can work on both CPU and GPU. CPU is most practical and cheap, though if you need really fast...

Hi! I haven't tested image on windows. Have you checked container logs?

Have you tried running other GPU based containers on wsl2, like TensorFlow benchmarks, to verify your wsl2 is properly configured for GPU usage?