Program crashes when there is no face in the image

[ltt-gddxz]

I tested the mtcnn with a image with no face, the program crashed.

It seems that code in detect_faces did not handle the case that there is no bounding box detected in the image. Is that so ?

[miaoct]

yes
do not use

[miaoct]

I also meet this issue. Have you solve it?

[mayuanjason]

Hi miaoct,

I just refactor this repo, you can check it in https://github.com/mayuanjason/MTCNN_face_detection_alignment_pytorch

• Transfer all numpy operation to torch operation, so that it can benefit from GPU acceleration.
• Automatic run on 'CPU' or 'GPU'.
• Based on the latest version of pytorch (1.3)
• Real-time face tracking

And it will not crash when there is no face in the image.

[miaoct]

Hi miaoct,

I just refactor this repo, you can check it in https://github.com/mayuanjason/MTCNN_face_detection_alignment_pytorch

• Transfer all numpy operation to torch operation, so that it can benefit from GPU acceleration.
• Automatic run on 'CPU' or 'GPU'.
• Based on the latest version of pytorch (1.3)
• Real-time face tracking

And it will not crash when there is no face in the image.

Thank you very much

[miaoct]

Hi miaoct,

I just refactor this repo, you can check it in https://github.com/mayuanjason/MTCNN_face_detection_alignment_pytorch

• Transfer all numpy operation to torch operation, so that it can benefit from GPU acceleration.
• Automatic run on 'CPU' or 'GPU'.
• Based on the latest version of pytorch (1.3)
• Real-time face tracking

And it will not crash when there is no face in the image.

The code is no issue. It's very well !