Question for Preprocessing Input of ArcFace Model

[clariojohan]

Hi, I just want to make sure of the preprocessing method for the arcface model is the one here below or the one named inv_preprocess here

Because, when i tried to use the preprocessing the 512 embedding output is always random, but when i tried to use for example facenet preprocessing input, the embedding output is similar each time its generated.

I am looking forward to hear the explanation, Thank You !

[prashant-saxena]

You can try this

img = #aligned image of face of size 112x112 or what ever size you are looking for
self.input_size = (112, 112)
self.input_mean = 127.5
self.input_std = 127.5
blob = cv2.dnn.blobFromImage(img, 1.0 / self.input_std, self.input_size,
                                    (self.input_mean, self.input_mean, self.input_mean), swapRB=True)

You can pass blob to session created using w600k_r50.onnx (ArcFace) as a single input.
How OpenCV’s blobFromImage works