Open rookiecm opened 4 years ago
Could you please expalin why you crop Xs to Xs[19:237, 19:237] before sending to arcface ? The code lies in Line 100 of train_AEI.py ?
embed, Xs_feats = arcface(F.interpolate(Xs[:, :, 19:237, 19:237], [112, 112], mode='bilinear', align_corners=True))
When I perform face alignment on face datasets which method is used in arcface, I found that the aligned faces usually miss chin. So I enlarge the side of all the bounding box by a factor of 1/0.85.
So Xs[:, :, 19:237, 19:237] is the aligned face for arcface
So Xs[:, :, 19:237, 19:237] is the aligned face for arcface
Great discovery !
Could you please explain how do you find that Xs[:, :, 19:237, 19:237] is the aligned face for arcface? @taotaonice
Could you please explain how do you find that Xs[:, :, 19:237, 19:237] is the aligned face for arcface? @taotaonice
...... I enlarge the face alignment bounding box by a factor of 1/0.85 and crop size is (256, 256), so Xs[:, :, 19:237, 19:237] is the aligned face
Could you please expalin why you crop Xs to Xs[19:237, 19:237] before sending to arcface ? The code lies in Line 100 of train_AEI.py ?
embed, Xs_feats = arcface(F.interpolate(Xs[:, :, 19:237, 19:237], [112, 112], mode='bilinear', align_corners=True))