DebugMeN0t

@Chilicyy Hi, I know, but i want to do NMS inside the code logic, not in the model...

Hi. If your model is not performing well just on one class, it highly likely means that there is no enough data/data quality for this class in the dataset. Try...

Building from source: ~/openmmlab $ conda create --name openmmlab_2 python=3.8 -y Collecting package metadata (current_repodata.json): done Solving environment: done (...) ca-certificates pkgs/main/osx-arm64::ca-certificates-2023.08.22-hca03da5_0 libcxx pkgs/main/osx-arm64::libcxx-14.0.6-h848a8c0_0 libffi pkgs/main/osx-arm64::libffi-3.4.4-hca03da5_0 ncurses pkgs/main/osx-arm64::ncurses-6.4-h313beb8_0 openssl pkgs/main/osx-arm64::openssl-3.0.11-h1a28f6b_2...

Hi! Any schedule to return back MPS support? 2.1.0 is already released but MPS is disabled :( There are lots of new MPS functions supported in Torch 2.1...

ref: https://github.com/wolfSSL/wolfssl/blob/master/wolfssl/openssl/opensslv.h @dgarske

I've already changed to musl. But there were larger amount of patching in other modules that depend on glibc, than patching 2 functions (that i've already did also), but for...

Maybe there is more "petalish" way :) but for now its an ready2go alternative to something like ":live_select" (hex)