Matheus Correia Ferreira

Ok, by using the code pointed to [here](https://github.com/czczup/ViT-Adapter/issues/127), I converted the weights that had been pre-trained using `patch_size=14`. However, I'm still hitting the same error. I'm using the weights for...

Same here. An EarlyStopping feature would be great. I have been trying to implement it somehow, but so far I've had no luck.

Ok, thanks! One thing is still not clear to me, though. Do we have the script for training the Mask2Former model?

Thanks a bunch for the thoughtful response. I had tried training through MMSegmentation but bumped into some odd errors, so I thought that maybe the training had been done in...

> > It's run using MMLab, specifically [MMSegmentation](https://github.com/open-mmlab/mmsegmentation/tree/main). You can follow the notebook [here](https://github.com/facebookresearch/dinov2/blob/main/notebooks/semantic_segmentation.ipynb) to load the mmsegmentation config file used to run the model. You may have to modify...

Anyone? =)

@Meoooww, sometime after my post there was an update to the [VIT code]( https://github.com/open-mmlab/mmsegmentation/blob/c685fe6767c4cadf6b051983ca6208f1b9d1ccb8/mmseg/models/backbones/vit.py#L178) allowing the backbone weights to be frozen via the frozen_exclude parameter. In order to freeze all...

> > @Meoooww, sometime after my post there was an update to the [VIT code](https://github.com/open-mmlab/mmsegmentation/blob/c685fe6767c4cadf6b051983ca6208f1b9d1ccb8/mmseg/models/backbones/vit.py#L178) allowing the backbone weights to be frozen via the frozen_exclude parameter. > > In order...

Yeah, I'll try to do that. Thanks!

This was happening when I tried to use the Mask2Former model. I've since abandoned it in favor of an Upernet, so I didn't have to deal with this problem anymore....