How to infer mask for multiple images?

Thanks for your great work!

I would like to use the mask generator (see [notebooks/automatic_mask_generator_example.ipynb](https://github.com/facebookresearch/segment-anything/blob/main/notebooks/automatic_mask_generator_example.ipynb)) to get masks for multiple images. Therefore, the dimension will be 4 (**batch, channel, height, width**). It seems that only predictor can do that?

Start with notebooks/automatic_mask_generator_example.ipynb and trace the mask generator and predictor entry points for their expected image dimensions. Determine whether multiple images with batch, channel, height, and width are supported; done means the repository has a clear answer or documented support path for batched inference.

Written by the indexing model from the issue text.