get_landmarks_from_batch returns an empty list

My code is as follows:
```
imgs = imgs.permute(0, 3, 1, 2)# B x C x H x W
landmark = self.face_algm.get_landmarks_from_batch(imgs)
```
The picture I used is the frame intercepted by the MEAD dataset, but it returned an empty list to me, what did I do wrong?

Check the face-alignment library's documentation for input format expectations. The issue mentions permuting dimensions; verify the correct tensor shape and data type. Look at the get_landmarks_from_batch method in the source code to understand its requirements. Test with a known good image to isolate the problem.

Rédigé par le modèle d'indexation à partir du texte de l'issue.