Alexandre Chapin

> It seems the `SamAutomaticMaskGenerator` does a lot of deep copy in [MaskData.cat](https://github.com/facebookresearch/segment-anything/blob/6fdee8f2727f4506cfbbe553e23b895e27956588/segment_anything/utils/amg.py#L59) that cause most of the slowdown. Apparently these deep copies could be avoided since every time this...

The demo is not working at all, each time I want to try to segment an image I get an error as return : 

Hello, no no updates...

> @alexcbb Hello, > > Have you solved the evaluation code? I have encountered some problems now. In addition, your homepage email does not show this information, could you please...

Thank you for your quick answer ! I'm would be very interested to explore whether such training would be beneficial for Vision Transformer (even for a small version like ViT-S...

For the pre-training on COCO it is indicated that it was performed on 8 GPU NVIDIA 2080 Ti for 800 epochs. Do you have maybe an average time required for...

I made some small changes to launch the training (I created a Pytorch Lightning module to ease the deployment on clusters) and began to launch a 800 epoch training on...

It seems that I'm not able to replicate your figure 3 after pre-training and I don't understand why, the prototypes seems a bit weird and there's no mask on my...

Hello, the problem was in my visualization file, it seems that I'm now able to obtain well aligned concepts ! I've seen in the paper that you say one would...

Hello, I would have a question concerning the slot loss part. You specify in equation (5) a masking over the slots that do not occupy dominating groups, that you then...