deepinsight / deepinsight/insightface

RetinaFace Makefile

Open
#2,464 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
29.7k
Forks
6.1k
PR merge metrics
No merged PRs in 30d

Description

Hello
I've been working on the face detection model and followed instructions on the README. I want to use my camera to carry out real time detection, so I implemented the basic openCV to capture and process frames in the test.py file. I am able to detect faces however the test.py only works when I set the gpuid = -1 (cpu), when I change it to gpuid = 0 there are no errors but the script does not execute. After researching I found out that not all the files have been built properly in the cython folder; the gpu_nms.pyx file is causing errors while building. So I figured maybe this is why I'm able to bind the model in test.py to the GPU.

I'm using Windows as my OS, Python 3.9, CUDA 10.2 and I've installed mxnet-cu10.2 version 1.7.0.

This is the message I get when I run the Makefile
```
PS C:\Users\OMEN 45L\Desktop\gitlab\detectionservice\retinaface> make
cd rcnn/cython/ && python setup.py build_ext --inplace && del -rf build
CUDA is found
cl : Command line warning D9024 : unrecognized source file type 'gcc', object file assumed
cl : Command line warning D9027 : source file 'gcc' ignored
cl : Command line warning D9024 : unrecognized source file type 'nvcc', object file assumed
cl : Command line warning D9027 : source file 'nvcc' ignored
gpu_nms.cpp
c:\users\omen 45l\appdata\local\programs\python\python39\lib\site-packages\numpy\core\include\numpy\npy_1_7_deprecated_api.h(14) : Warning Msg: Using deprecated NumPy API, disable it with #define NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION
gpu_nms.cpp(4598): warning C4244: '=': conversion from 'npy_intp' to 'int', possible loss of data
gpu_nms.cpp(4608): warning C4244: '=': conversion from 'npy_intp' to 'int', possible loss of data
gpu_nms.cpp(4793): error C2664: 'void _nms(int *,int *,const float *,int,int,float,int)': cannot convert argument 1 from '__pyx_t_5numpy_int32_t *' to 'int *'
gpu_nms.cpp(4793): note: Types pointed to are unrelated; conversion requires reinterpret_cast, C-style cast or function-style cast
error: command 'C:\\Program Files (x86)\\Microsoft Visual Studio\\2017\\Community\\VC\\Tools\\MSVC\\14.16.27023\\bin\\HostX86\\x64\\cl.exe' failed with exit code 2
make: *** [Makefile:2: all] Error 1
```

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.