SthPhoenix

Hello! Also noticed great accuracy drop with `20180402-114759` model. My use case is as follows: 1. I have a DB of 100k persons, 1 image per person. 2. I index...

In string: `.constant('euiHost', 'http://localhost:9200');` Isn't _euiHost_ a parameter name? If so, why did you changed it to _elasticsearch-drupal-1_?

Currently batch inference is supported only for TensorRT

All insightface models runs on triton after conversion to onnx or trt, though I'm not sure if this repo currently works with Triton, since I haven't updated its support for...

Yes, just run it with `deploy_cpu.sh`

Previously `onnxruntime` was a dependency of `onnx-simplifier` and was installed with it, looks like now it should be specified in `requirements.txt` directly. I'll fix it right now.

> 问题1:scrfd模型 bnkps 跟gnkps是什么意思? 问题2: scrfd怎么多batch输入, 我把onnx改为动态batch,可是输入多张图片进去,输出维度跟一张图片一样.这是为什么 1. KPS - means those models extracts facial landmarks in addition to bounding boxes. BN - means model use BatchNorm layers and GN...

Hi! What exactly do you mean by different outputs? Various TRT versions might provide a bit different outputs, though they should not be very different.

Hi! this is older debug script based on old versions of official insightface pip package, now it's not working because official package have changed and depreciated some models. I'll look...

Great work @a7ypically ! Unfortunately I have no Jetson to test it, could you create a separate dockerfile and entrypoint.sh for Jetson so I could accept your pull request without...