Go implementation of Arcface inference

• The onnx-format models used in the code is "buffalo_l" from insightface.
• ONNX Runtime (v1.12.1 in my environment) is required.
• OpenCV (v4.5.5 in my environment) is required, because some codes borrowed from gocv to implement EstimateAffinePartial2DWithParams().

The example is too simple, detect faces in the input image and retrieve features of the first face.

CGO_CPPFLAGS="-I/usr/local/include/opencv4" CGO_LDFLAGS="-lopencv_core -lopencv_calib3d -lopencv_imgproc" LD_LIBRARY_PATH=/usr/local/lib go run example.go

• If your onnxruntime and opencv is not installed in /usr/local, some paths in CGO flags and LD_LIARARY_PATH should be corrected.
• path to "buffalo_l" should be corrected in example.go .

arcface-go-api