about post-processing

[lawo123]

if config.TEST.POST_PROCESS:
        for n in range(coords.shape[0]):
            for p in range(coords.shape[1]):
                hm = batch_heatmaps[n][p]
                px = int(math.floor(coords[n][p][0] + 0.5))
                py = int(math.floor(coords[n][p][1] + 0.5))
                if 1 < px < heatmap_width-1 and 1 < py < heatmap_height-1:
                    diff = np.array(
                        [
                            hm[py][px+1] - hm[py][px-1],
                            hm[py+1][px]-hm[py-1][px]
                        ]
                    )
                    coords[n][p] += np.sign(diff) * .25

    preds = coords.copy()

why do this?

[kuldeepbrd1]

It's a compensation technique to recover quantization error.
HRNet/HRNet-Facial-Landmark-Detection#26 (comment)
Hope it helps

[lawo123]

It's a compensation technique to recover quantization error.
HRNet/HRNet-Facial-Landmark-Detection#26 (comment)
Hope it helps

Thank you very much for your reply, it helped me a lot