Please note that in both Python and C++, you hand over the image to the model as BGR while the insightface models have been trained on RGB images. You will get better results when converting the channel order to RGB before sending the image through the net.
--- [Visit Topic](https://discuss.mxnet.apache.org/t/how-to-use-the-model-of-insightface-by-cpp-package-to-extract-features-of-face-for-recognition/2049/8) or reply to this email to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.mxnet.apache.org/email/unsubscribe/e4a4f67766feeb5bb267e25f4a4230f0fbbe583f8a8efd731c454e4058ec19e7).
