fail to get 2d landmark in float dtype

[cavalier501]

I test "fa.get_landmarks_from_image" on some images in 256 * 256 and 512 * 512 resolution. While the result is numpy with dtype float32, but the decimal place of result is always 0, in other words, the dtype of result is int in fact.

Is that a bug? Or how can I solve the problem?

[Aria-Zhangjl]

I test "fa.get_landmarks_from_image" on some images in 256 * 256 and 512 * 512 resolution. While the result is numpy with dtype float32, but the decimal place of result is always 0, in other words, the dtype of result is int in fact.

Is that a bug? Or how can I solve the problem?

Hello,

I encountered a similar issue. Have you found a solution for it yet?

Thank you.

[cavalier501]

I test "fa.get_landmarks_from_image" on some images in 256 * 256 and 512 * 512 resolution. While the result is numpy with dtype float32, but the decimal place of result is always 0, in other words, the dtype of result is int in fact.
Is that a bug? Or how can I solve the problem?

Hello,

I encountered a similar issue. Have you found a solution for it yet?

Thank you.

sorry, but since it's been a while, I can't remember exactly how I handled this matter.😂

[Aria-Zhangjl]

Thank you for your reply 💖
I finally figure out that most of the detection models are designed to directly output the coordinates of facial keypoints, hence, the outputs are typically integers (representing pixel locations).